W0219 01:46:19.215000 2110507 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0219 01:46:19.215000 2110507 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:19.215000 2110507 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0219 01:46:19.215000 2110507 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.051000 661040 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0219 01:46:20.051000 661040 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.051000 661040 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0219 01:46:20.051000 661040 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.085000 1982123 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0219 01:46:20.085000 1982123 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.085000 1982123 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0219 01:46:20.085000 1982123 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.201000 1983947 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0219 01:46:20.201000 1983947 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.201000 1983947 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0219 01:46:20.201000 1983947 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.203000 1990262 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0219 01:46:20.203000 1990262 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.203000 1990262 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0219 01:46:20.203000 1990262 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.209000 1986959 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0219 01:46:20.209000 1986959 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.209000 1986959 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0219 01:46:20.209000 1986959 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.213000 1988962 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0219 01:46:20.213000 1988962 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.213000 1988962 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0219 01:46:20.213000 1988962 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.226000 1987087 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0219 01:46:20.226000 1987087 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.226000 1987087 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0219 01:46:20.226000 1987087 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.278000 1987887 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0219 01:46:20.278000 1987887 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.278000 1987887 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0219 01:46:20.278000 1987887 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.329000 673195 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0219 01:46:20.329000 673195 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.329000 673195 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0219 01:46:20.329000 673195 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.420000 1985034 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0219 01:46:20.420000 1985034 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.420000 1985034 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0219 01:46:20.420000 1985034 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.456000 1983838 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0219 01:46:20.456000 1983838 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.456000 1983838 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0219 01:46:20.456000 1983838 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.517000 1985442 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0219 01:46:20.517000 1985442 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.517000 1985442 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0219 01:46:20.517000 1985442 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.557000 1986836 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0219 01:46:20.557000 1986836 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.557000 1986836 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0219 01:46:20.557000 1986836 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.722000 2033589 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0219 01:46:20.722000 2033589 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.722000 2033589 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0219 01:46:20.722000 2033589 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.773000 651329 .local/lib/python3.10/site-packages/torch/distributed/run.py:793]
W0219 01:46:20.773000 651329 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
W0219 01:46:20.773000 651329 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0219 01:46:20.773000 651329 .local/lib/python3.10/site-packages/torch/distributed/run.py:793] *****************************************
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
PyTorch: setting up devices
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]loading configuration file config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/config.json
You are using a model of type qwen2_5_vl to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
Model config LlavaQwenConfig {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "llava_qwen",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"spatial_patch_size": 14,
"tokens_per_second": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}
loading weights file model.safetensors from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/model.safetensors.index.json
Instantiating LlavaQwenForCausalLM model under default dtype torch.bfloat16.
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:03, 1.02it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.71it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.81it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.84it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.83it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.78it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.70it/s]
Loading checkpoint shards: 2
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.27it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:01<00:04, 1.01s/it]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.00it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.24it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.09it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.00it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.84it/s]
Loading checkpoint shards: 2
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.26it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.46it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.86it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.31it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.18it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.81it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.07it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.38it/s]
Loading checkpoin
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.50it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.87it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.76it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.16it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:03, 1.23it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.58it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.57it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.67it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.93it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.36it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.35it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:03, 1.16it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.04it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.17it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.42it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.40it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.13it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.93it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.86it/s]
Loading checkpoint shards: 40%|████
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.41it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.74it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.66it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.51it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:03, 1.15it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.35it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.34it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.09it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.79it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.38it/s]
Loading checkpoint shards: 40%|████
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.37it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.79it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.66it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.21it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.00it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.83it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.04it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.11it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.66it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.39it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.98it/s]
Loading checkpoint shards: 40%|�
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:03, 1.08it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.80it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.41it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.78it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.43it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.48it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.32it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.04it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.89it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.10it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.12it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.82it/s]
Loading checkpoint
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.98it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.20it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:03, 1.25it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.69it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.00it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.41it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.16it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.96it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.15it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.85it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.07it/s]
Loading checkpoint shards: 40%|�
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.48it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.44it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.47it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.37it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.36it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.35it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.34it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:03, 1.02it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.59it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.02it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.87it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.91it/s]
Loading checkpoint
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.24it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.08it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.85it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:03, 1.29it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.98it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.76it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.15it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.40it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.77it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.54it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:01<00:01, 1.93it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.34it/s]
Loading checkpoint
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.44it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.02it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.66it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.07it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.31it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.08it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.32it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.94it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 4.02it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.85it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.47it/s]
Loading checkpoint shards: 40%|�
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.37it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.15it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.10it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.21it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.21it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.96it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.94it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 3.12it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.15it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.98it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.05it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.10it/s]
Loading checkpoint
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.66it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.37it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.46it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.19it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.24it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.12it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.33it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.91it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.14it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.32it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.20it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.04it/s]
Loading checkpoint
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.96it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.36it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.94it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.18it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.29it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.48it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.88it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.75it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.90it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.56it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.97it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.78it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.87it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.04it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.98it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:02, 1.81it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:01, 2.17it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.03it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.75it/s]
Loading checkpoint shards: 40%|████ 0%|██ | 1/5 [00:00<00:02, 1.89it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:01<00:01, 1.73it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.82it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.76it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.92it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.72it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.81it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.82it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.75it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.26it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.27it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.15it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00,t shards: 40%|████ | 2/5 [00:00<00:01, 2.92it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.06it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.91it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.13it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.55it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.84it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.93it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.56it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.22it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.12it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.32it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.15it/s]
Loading checkpoint shards: 60%|██████ | 2/5 [00:00<00:00, 3.19it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.22it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.07it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.76it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.69it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:01<00:01, 1.89it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.41it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.61it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.32it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.29it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.22it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.41it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.60%|██ | 1/5 [00:00<00:02, 1.75it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.42it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.45it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.46it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.47it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:01<00:01, 1.70it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.36it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.50it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.43it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.87it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.85it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.81it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00,| 2/5 [00:00<00:00, 3.15it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:01<00:01, 1.92it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.84it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.98it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.18it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.77it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.27it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.43it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.11it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.06it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.17it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.28it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.0�███ | 2/5 [00:00<00:00, 3.18it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.81it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.52it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.72it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.77it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.53it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.25it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.39it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 4.01it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.27it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.14it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.54it/s]
Loading checkpoint shards: 60%|██████ | 3/00, 3.48it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.45it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.52it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.10it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.15it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.24it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:01<00:01, 1.97it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.49it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.64it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.44it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.51it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.30it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.12it/s]
Loading check| 2/5 [00:00<00:00, 3.39it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.79it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.12it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.88it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.70it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.03it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.50it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.75it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.36it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.85it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.26it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.38it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.200, 3.26it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.80it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.29it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.70it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.10it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.94it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.76it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.38it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.63it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.35it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.56it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.27it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.68it/s]
Loading check�███ | 2/5 [00:00<00:00, 3.72it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.15it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.67it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 4.13it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.48it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 4.48it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.12it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.53it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.61it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.31it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.42it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.39it/s]
Loading checkpoint shards: 60%|██████ | 3/�███ | 2/5 [00:00<00:01, 2.91it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.73it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:01<00:01, 1.91it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.96it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.53it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.26it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 4.38it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.57it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.05it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.39it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.17it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.04it/s]
Loading checkpoint shards: 60%|██████ | 3/ shards: 40%|████ | 2/5 [00:01<00:01, 1.67it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.90it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.63it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.57it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.10it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.23it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.22it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.24it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.06it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.10it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.51it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.86it/s]
Loading checkpoint shards: 80%|██ shards: 40%|████ | 2/5 [00:00<00:01, 2.85it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.84it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:01<00:01, 1.74it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.81it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.22it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.53it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.20it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.13it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.08it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.07it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.07it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.24it/s]
Loading checkpoint shards: 80%|██ shards: 40%|████ | 2/5 [00:00<00:00, 3.00it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.16it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.09it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.49it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.41it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.52it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.66it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.45it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.51it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.33it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.35it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.77it/s]
Loading checkpoint shards: 80%|██ shards: 40%|████ | 2/5 [00:00<00:01, 2.46it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.45it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.58it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.85it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.71it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.98it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.90it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.72it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.81it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.79it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.06it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.26it/s]
Loading checkpoint shards: 80%|██ shards: 40%|████ | 2/5 [00:00<00:01, 2.89it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.81it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:01, 2.78it/s]
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 3.69it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.30it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.38it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.12it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.19it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.16it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.15it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.98it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.84it/s]
Loading checkpoint shards: 80%|██ 2.21it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.74it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.86it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.81it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.72it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.03it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.02it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.04it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 2.99it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 2.99it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 2.95it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 2.55it/s]
Loading checkpoint shards: 80%|█████� 2.22it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.11it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.02it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.97it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.94it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.31it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 2.62it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.30it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.31it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.20it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.13it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.13it/s]
Loading checkpoint shards: 80%|█████�██████ | 4/5 [00:01<00:00, 2.60it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.20it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.28it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.25it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.14it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.19it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.44it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.97it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:02<00:00, 3.18it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:02<00:00, 2.45it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.73it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.34it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
██████ | 4/5 [00:01<00:00, 3.56it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.38it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.45it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.41it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.44it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.37it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.70it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.35it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.04it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.68it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.90it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.50it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
5 [00:00<00:00, 3.87it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:00<00:00, 4.08it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.29it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.48it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.26it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.15it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.19it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 2.66it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.94it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.45it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.22it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
██████ | 4/5 [00:01<00:00, 3.46it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.31it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.20it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 2.62it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.21it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.18it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.10it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 2.99it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.95it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.73it/s]
point shards: 60%|██████ | 3/5 [00:00<00:00, 3.50it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.26it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.91it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.72it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.69it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.49it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.88it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.52it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.71it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.56it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.17it/s]
Loading checkpoint shards: 100%|██████████All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
| 5/5 [00:01<00:00, 3.72it/s]
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.31it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.78it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.80it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.48it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
| 3/5 [00:01<00:00, 3.07it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.88it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 3.10it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.85it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.33it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.19it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.22it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.24it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.17it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.05it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.18it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.02it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.73it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.33it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
3it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.58it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.49it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.36it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.31it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.31it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 2.70it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.50it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.49it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.10it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.98it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.78it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
5 [00:00<00:00, 3.97it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.29it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.45it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.72it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.37it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.29it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.80it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.19it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.46it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.81it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.32it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.94it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.74it/s]
point shards: 60%|██████ | 3/5 [00:00<00:00, 3.12it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.37it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.53it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.43it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.40it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.43it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.34it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.31it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.32it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 2.71it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.00it/s]
Loading checkpoint shards: 100%|██████████All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
| 5/5 [00:01<00:00, 3.79it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.78it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.42it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.81it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.53it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.83it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.48it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
6it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 3.44it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.63it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.85it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.67it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.68it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.77it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.58it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.73it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.35it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.26it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.13it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.83it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.91it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.67it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.62it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.75it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.32it/s]
5 [00:00<00:00, 3.87it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:00<00:00, 3.97it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.26it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.52it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.35it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.43it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.40it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.41it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 4.01it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.36it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.21it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.95it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.61it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
4it/s]
Loading checkpoint shards: 60%|██████ | 3/5 [00:01<00:00, 2.94it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.21it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.30it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.45it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.26it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.22it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.23it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.03it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 2.60it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.73it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.32it/s]
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.80it/s]All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.90it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.68it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.45it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.82it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.48it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.91it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.55it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.77it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.46it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
�██ | 4/5 [00:01<00:00, 3.09it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.80it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.37it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:02<00:00, 3.19it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:02<00:00, 2.44it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.16it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.93it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.77it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.29it/s]
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.80it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.30it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.87it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.58it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.13it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.49it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.80it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.51it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
██████ | 4/5 [00:01<00:00, 3.60it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.15it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.07it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.01it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 2.72it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 2.86it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 2.88it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.00it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.05it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.85it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.81it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.39it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.93it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.61it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.95it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.79it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.68it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.22it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
██████ | 4/5 [00:01<00:00, 3.32it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.37it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.26it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.30it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.23it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.22it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.21it/s]
Loading checkpoint shards: 80%|████████ | 4/5 [00:01<00:00, 3.85it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.77it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.43it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.82it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.45it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.76it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.31it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.72it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.33it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.77it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.40it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.89it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.42it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.55it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.15it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.60it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.31it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.79it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.40it/s]
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
�██ | 4/5 [00:01<00:00, 3.00it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.55it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.06it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.64it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.52it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.74it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.45it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.60it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.31it/s]
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.62it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.29it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.70it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.41it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.06it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.81it/s]
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.47it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.01it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.67it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.41it/s]
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.10it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.77it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.17it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 2.55it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.56it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.22it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.82it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.68it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.83it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.70it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.68it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.45it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.45it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.04it/s]
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.45it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.01it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.76it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.67it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.81it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.69it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.76it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.48it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.93it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.48it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.03it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.89it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.59it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.24it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.56it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.21it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.63it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.40it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.73it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.56it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.60it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.31it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:02<00:00, 3.06it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:02<00:00, 2.41it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.45it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.17it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.57it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.27it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.50it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.15it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.78it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.62it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.94it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.75it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.56it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.26it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.66it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.35it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.70it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.60it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.53it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.25it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.51it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.22it/s]
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.38it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 2.94it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.54it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.27it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.63it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.42it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.26it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.97it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.98it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.58it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.48it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.11it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.06it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 2.51it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.51it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.24it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.55it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.21it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.79it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.33it/s]
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:02<00:00, 2.99it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:02<00:00, 2.36it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.54it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.28it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.65it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.37it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.72it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.61it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.37it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 2.97it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.35it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.00it/s]
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.43it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.13it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.14it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 2.56it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.33it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 2.98it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.81it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.36it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.15it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 2.57it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.52it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.18it/s]
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.51it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.19it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.90it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.57it/s]
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.09it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.89it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.52it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.24it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.05it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 2.53it/s]
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.47it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.27it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.59it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.28it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.22it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 2.92it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.63it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.27it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.01it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.86it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.42it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.17it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.54it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.55it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.19it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 2.84it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.18it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 2.84it/s]
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 4.17it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.94it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.28it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.16it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 3.21it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:01<00:00, 2.90it/s]
All model checkpoint weights were used when initializing LlavaQwenForCausalLM.
All the weights of LlavaQwenForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaQwenForCausalLM for predictions without further training.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file generation_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/generation_config.json
Generate config GenerationConfig {
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file added_tokens.json from cache at None
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file special_tokens_map.json from cache at None
loading file special_tokens_map.json from cache at None
loading file special_tokens_map.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file added_tokens.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file chat_template.jinja from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file special_tokens_map.json from cache at None
loading file chat_template.jinja from cache at None
loading file chat_template.jinja from cache at None
loading file chat_template.jinja from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file special_tokens_map.json from cache at None
loading file chat_template.jinja from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file added_tokens.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file special_tokens_map.json from cache at None
loading file special_tokens_map.json from cache at None
loading file chat_template.jinja from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file added_tokens.json from cache at None
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file special_tokens_map.json from cache at None
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file added_tokens.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file special_tokens_map.json from cache at None
loading file added_tokens.json from cache at None
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file chat_template.jinja from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file chat_template.jinja from cache at None
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file added_tokens.json from cache at None
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file special_tokens_map.json from cache at None
loading file added_tokens.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file special_tokens_map.json from cache at None
loading file chat_template.jinja from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file chat_template.jinja from cache at None
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file chat_template.jinja from cache at None
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file special_tokens_map.json from cache at None
loading file chat_template.jinja from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file special_tokens_map.json from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file chat_template.jinja from cache at None
loading file chat_template.jinja from cache at None
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file added_tokens.json from cache at None
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file added_tokens.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file special_tokens_map.json from cache at None
loading file chat_template.jinja from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading configuration file preprocessor_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/preprocessor_config.json
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Image processor Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
loading file vocab.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/vocab.json
loading file merges.txt from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/merges.txt
loading file tokenizer.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer.json
loading file added_tokens.json from cache at None
loading file special_tokens_map.json from cache at None
loading file tokenizer_config.json from cache at /fsx_0/user/zhaojiang/models/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/6e6556e8ce728c7b3e438d75ebf04ec93403dc19/tokenizer_config.json
loading file chat_template.jinja from cache at None
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
Processor Qwen2_5_VLProcessor:
- image_processor: Qwen2VLImageProcessor {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}
- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
)
{
"processor_class": "Qwen2_5_VLProcessor"
}
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 151668. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/model/multimodal_encoder/eva_clip/eva_vit.py:622: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(checkpoint_path, map_location=map_location)
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Using custom data configuration default-5e4e9de28fd39dca
Loading Dataset Infos from /home/zhaojiang/.local/lib/python3.10/site-packages/datasets/packaged_modules/webdataset
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
Found cached dataset webdataset (/fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f)
Loading Dataset info from /fsx_0/user/zhaojiang/wb/webdataset/default-5e4e9de28fd39dca/0.0.0/e9ef0843eead451e800ef3bd9a9ee86b731520f88aa20be2d598ddfeef5b3f7f
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Using auto half precision backend
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Using auto half precision backend
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Using auto half precision backend
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Using auto half precision backend
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Using auto half precision backend
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Using auto half precision backend
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Using auto half precision backend
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Using auto half precision backend
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Using auto half precision backend
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Using auto half precision backend
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Using auto half precision backend
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Using auto half precision backend
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Using auto half precision backend
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Using auto half precision backend
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Using auto half precision backend
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Using auto half precision backend
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
/opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/llava/train/train.py:1637: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `LLaVATrainer.__init__`. Use `processing_class` instead.
trainer = LLaVATrainer(
Attempting to resume from /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000
Attempting to resume from /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000
Attempting to resume from /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000
Attempting to resume from /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000
Attempting to resume from /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000
Attempting to resume from /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000
Attempting to resume from /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000
Attempting to resume from /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000
Attempting to resume from /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000
Attempting to resume from /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000
Attempting to resume from /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000
Attempting to resume from /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000
Attempting to resume from /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000
Attempting to resume from /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000
Attempting to resume from /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000
Attempting to resume from /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000
***** Running training *****
Num examples = 194,420,624
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 1,024
Gradient Accumulation steps = 1
Total optimization steps = 569,592
Number of trainable parameters = 1,365,239,712
Continuing training from checkpoint, will skip to saved global_step
Continuing training from epoch 0
Continuing training from global step 30000
Will skip the first 0 epochs then the first 30000 batches in the first epoch.
***** Running training *****
Num examples = 194,420,624
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 1,024
Gradient Accumulation steps = 1
Total optimization steps = 569,592
Number of trainable parameters = 1,365,239,712
Continuing training from checkpoint, will skip to saved global_step
Continuing training from epoch 0
Continuing training from global step 30000
Will skip the first 0 epochs then the first 30000 batches in the first epoch.
***** Running training *****
Num examples = 194,420,624
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 1,024
Gradient Accumulation steps = 1
Total optimization steps = 569,592
Number of trainable parameters = 1,365,239,712
Continuing training from checkpoint, will skip to saved global_step
Continuing training from epoch 0
Continuing training from global step 30000
Will skip the first 0 epochs then the first 30000 batches in the first epoch.
***** Running training *****
Num examples = 194,420,624
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 1,024
Gradient Accumulation steps = 1
Total optimization steps = 569,592
Number of trainable parameters = 1,365,239,712
Continuing training from checkpoint, will skip to saved global_step
Continuing training from epoch 0
Continuing training from global step 30000
Will skip the first 0 epochs then the first 30000 batches in the first epoch.
***** Running training *****
Num examples = 194,420,624
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 1,024
Gradient Accumulation steps = 1
Total optimization steps = 569,592
Number of trainable parameters = 1,365,239,712
Continuing training from checkpoint, will skip to saved global_step
Continuing training from epoch 0
Continuing training from global step 30000
Will skip the first 0 epochs then the first 30000 batches in the first epoch.
***** Running training *****
Num examples = 194,420,624
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 1,024
Gradient Accumulation steps = 1
Total optimization steps = 569,592
Number of trainable parameters = 1,365,239,712
Continuing training from checkpoint, will skip to saved global_step
Continuing training from epoch 0
Continuing training from global step 30000
Will skip the first 0 epochs then the first 30000 batches in the first epoch.
***** Running training *****
Num examples = 194,420,624
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 1,024
Gradient Accumulation steps = 1
Total optimization steps = 569,592
Number of trainable parameters = 1,365,239,712
Continuing training from checkpoint, will skip to saved global_step
Continuing training from epoch 0
Continuing training from global step 30000
Will skip the first 0 epochs then the first 30000 batches in the first epoch.
***** Running training *****
Num examples = 194,420,624
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 1,024
Gradient Accumulation steps = 1
Total optimization steps = 569,592
Number of trainable parameters = 1,365,239,712
***** Running training *****
Num examples = 194,420,624
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 1,024
Gradient Accumulation steps = 1
Total optimization steps = 569,592
Number of trainable parameters = 1,365,239,712
Continuing training from checkpoint, will skip to saved global_step
Continuing training from epoch 0
Continuing training from global step 30000
Will skip the first 0 epochs then the first 30000 batches in the first epoch.
Continuing training from checkpoint, will skip to saved global_step
Continuing training from epoch 0
Continuing training from global step 30000
Will skip the first 0 epochs then the first 30000 batches in the first epoch.
***** Running training *****
Num examples = 194,420,624
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 1,024
Gradient Accumulation steps = 1
Total optimization steps = 569,592
Number of trainable parameters = 1,365,239,712
Continuing training from checkpoint, will skip to saved global_step
Continuing training from epoch 0
Continuing training from global step 30000
Will skip the first 0 epochs then the first 30000 batches in the first epoch.
***** Running training *****
Num examples = 194,420,624
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 1,024
Gradient Accumulation steps = 1
Total optimization steps = 569,592
Number of trainable parameters = 1,365,239,712
Continuing training from checkpoint, will skip to saved global_step
Continuing training from epoch 0
Continuing training from global step 30000
Will skip the first 0 epochs then the first 30000 batches in the first epoch.
***** Running training *****
Num examples = 194,420,624
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 1,024
Gradient Accumulation steps = 1
Total optimization steps = 569,592
Number of trainable parameters = 1,365,239,712
Continuing training from checkpoint, will skip to saved global_step
Continuing training from epoch 0
Continuing training from global step 30000
Will skip the first 0 epochs then the first 30000 batches in the first epoch.
***** Running training *****
Num examples = 194,420,624
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 1,024
Gradient Accumulation steps = 1
Total optimization steps = 569,592
Number of trainable parameters = 1,365,239,712
Continuing training from checkpoint, will skip to saved global_step
Continuing training from epoch 0
Continuing training from global step 30000
Will skip the first 0 epochs then the first 30000 batches in the first epoch.
***** Running training *****
Num examples = 194,420,624
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 1,024
Gradient Accumulation steps = 1
Total optimization steps = 569,592
Number of trainable parameters = 1,365,239,712
Continuing training from checkpoint, will skip to saved global_step
Continuing training from epoch 0
Continuing training from global step 30000
Will skip the first 0 epochs then the first 30000 batches in the first epoch.
***** Running training *****
Num examples = 194,420,624
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 1,024
Gradient Accumulation steps = 1
Total optimization steps = 569,592
Number of trainable parameters = 1,365,239,712
Continuing training from checkpoint, will skip to saved global_step
Continuing training from epoch 0
Continuing training from global step 30000
Will skip the first 0 epochs then the first 30000 batches in the first epoch.
***** Running training *****
Num examples = 194,420,624
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 1,024
Gradient Accumulation steps = 1
Total optimization steps = 569,592
Number of trainable parameters = 1,365,239,712
Continuing training from checkpoint, will skip to saved global_step
Continuing training from epoch 0
Continuing training from global step 30000
Will skip the first 0 epochs then the first 30000 batches in the first epoch.
Automatic Weights & Biases logging enabled, to disable set os.environ["WANDB_DISABLED"] = "true"
wandb: Currently logged in as: jchen169 to https://api.wandb.ai. Use `wandb login --relogin` to force relogin
wandb: Using wandb-core as the SDK backend. Please refer to https://wandb.me/wandb-core for more information.
wandb: Tracking run with wandb version 0.19.6
wandb: Run data is saved locally in /opt/hpcaas/.mounts/fs-036153e63d56f4dc2/home/zhaojiang/interleaved-llava/wandb/run-20250219_020918-b3we4gqr
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run qwen-vl-diff-clip-16-nodes_early_pool2d_4
wandb: ⭐️ View project at https://wandb.ai/jchen169/huggingface
wandb: 🚀 View run at https://wandb.ai/jchen169/huggingface/runs/b3we4gqr
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
0%| | 0/569592 [00:00, ?it/s]/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
/home/zhaojiang/.local/lib/python3.10/site-packages/transformers/trainer.py:3119: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint_rng_state = torch.load(rng_file)
5%|▌ | 30001/569592 [00:37<11:21, 791.77it/s]
5%|▌ | 30001/569592 [00:55<11:21, 791.77it/s]
5%|▌ | 30001/569592 [00:55<11:21, 791.77it/s]
5%|▌ | 30002/569592 [00:56<19:21, 464.62it/s]
5%|▌ | 30002/569592 [00:56<19:21, 464.62it/s]
5%|▌ | 30003/569592 [00:57<19:54, 451.75it/s]
5%|▌ | 30003/569592 [00:57<19:54, 451.75it/s]
5%|▌ | 30004/569592 [00:58<20:45, 433.35it/s]
5%|▌ | 30004/569592 [00:58<20:45, 433.35it/s]
5%|▌ | 30005/569592 [00:59<21:58, 409.30it/s]
5%|▌ | 30005/569592 [00:59<21:58, 409.30it/s]
5%|▌ | 30006/569592 [01:00<23:39, 380.17it/s]
5%|▌ | 30006/569592 [01:00<23:39, 380.17it/s]
5%|▌ | 30007/569592 [01:01<26:03, 345.16it/s]
5%|▌ | 30007/569592 [01:01<26:03, 345.16it/s]
5%|▌ | 30008/569592 [01:02<29:24, 305.72it/s]
5%|▌ | 30008/569592 [01:02<29:24, 305.72it/s]
5%|▌ | 30009/569592 [01:03<34:15, 262.51it/s]
5%|▌ | 30009/569592 [01:03<34:15, 262.51it/s]
5%|▌ | 30010/569592 [01:08<1:16:58, 116.83it/s]
5%|▌ | 30010/569592 [01:08<1:16:58, 116.83it/s]
5%|▌ | 30011/569592 [01:09<1:27:16, 103.05it/s]
5%|▌ | 30011/569592 [01:09<1:27:16, 103.05it/s]
5%|▌ | 30012/569592 [01:11<1:46:09, 84.72it/s]
5%|▌ | 30012/569592 [01:11<1:46:09, 84.72it/s]
5%|▌ | 30013/569592 [01:12<2:06:39, 71.00it/s]
5%|▌ | 30013/569592 [01:12<2:06:39, 71.00it/s]
5%|▌ | 30014/569592 [01:18<5:10:14, 28.99it/s]
5%|▌ | 30014/569592 [01:18<5:10:14, 28.99it/s]
5%|▌ | 30015/569592 [01:21<7:37:55, 19.64it/s]
5%|▌ | 30015/569592 [01:21<7:37:55, 19.64it/s]
5%|▌ | 30016/569592 [01:22<8:40:49, 17.27it/s]
5%|▌ | 30016/569592 [01:22<8:40:49, 17.27it/s]
5%|▌ | 30017/569592 [01:23<9:56:47, 15.07it/s]
5%|▌ | 30017/569592 [01:23<9:56:47, 15.07it/s]
5%|▌ | 30018/569592 [01:29<21/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (100920000 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
:41:15, 6.91it/s]
5%|▌ | 30018/569592 [01:29<21:41:15, 6.91it/s]
5%|▌ | 30019/569592 [01:30<25:05:35, 5.97it/s]
5%|▌ | 30019/569592 [01:30<25:05:35, 5.97it/s]
5%|▌ | 30020/569592 [01:31<28:42:49, 5.22it/s]
5%|▌ | 30020/569592 [01:31<28:42:49, 5.22it/s]
5%|▌ | 30021/569592 [01:33<35:12:44, 4.26it/s]
5%|▌ | 30021/569592 [01:33<35:12:44, 4.26it/s]
5%|▌ | 30022/569592 [01:38<74:12:00, 2.02it/s]
5%|▌ | 30022/569592 [01:38<74:12:00, 2.02it/s]
5%|▌ | 30023/569592 [01:39<81:18:59, 1.84it/s]
5%|▌ | 30023/569592 [01:39<81:18:59, 1.84it/s]
5%|▌ | 30024/569592 [01:41<91:26:18, 1.64it/s]
5%|▌ | 30024/569592 [01:41<91:26:18, 1.64it/s]
5%|▌ | 30025/569592 [01:43<121:02:27, 1.24it/s]
5%|▌ | 30025/569592 [01:43<121:02:27, 1.24it/s]
5%|▌ | 30026/569592 [01:49<235:03:10, 1.57s/it]
5%|▌ | 30026/569592 [01:49<235:03:10, 1.57s/it]
5%|▌ | 30027/569592 [01:51<223:06:39, 1.49s/it]
5%|▌ | 30027/569592 [01:51<223:06:39, 1.49s/it]
5%|▌ | 30028/569592 [01:52<213:40:34, 1.43s/it]
5%|▌ | 30028/569592 [01:52<213:40:34, 1.43s/it]
5%|▌ | 30029/569592 [01:53<215:48:56, 1.44s/it]
5%|▌ | 30029/569592 [01:53<215:48:56, 1.44s/it]
5%|▌ | 30030/569592 [01:59<382:16:52, 2.55s/it]
5%|▌ | 30030/569592 [01:59<382:16:52, 2.55s/it]
5%|▌ | 30031/569592 [02:01<336:11:00, 2.24s/it]
5%|▌ | 30031/569592 [02:01<336:11:00, 2.24s/it]
5%|▌ | 30032/569592 [02:02<286:26:04, 1.91s/it]
5%|▌ | 30032/569592 [02:02<286:26:04, 1.91s/it]
5%|▌ | 30033/569592 [02:03<246:01:35, 1.64s/it]
5%|▌ | 30033/569592 [02:03<246:01:35, 1.64s/it]
5%|▌ | 30034/569592 [02:11<520:57:19, 3.48s/it]
5%|▌ | 30034/569592 [02:11<520:57:19, 3.48s/it]
5%|▌ | 30035/569592 [02:12<417:48:05, 2.79s/it]
5%|▌ | 30035/569592 [02:12<417:48:05, 2.79s/it]
5%|▌ | 30036/569592 [02:13<340:54:18, 2.27s/it]
5%|▌ | 30036/569592 [02:13<340:54:18, 2.27s/it]
5%|▌ | 30037/569592 [02:14<283:42:24, 1.89s/it]
5%|▌ | 30037/569592 [02:14<283:42:24, 1.89s/it]
5%|▌ | 30038/569592 [02:21<500:15:47, 3.34s/it]
5%|▌ | 30038/569592 [02:21<500:15:47, 3.34s/it]
5%|▌ | 30039/569592 [02:22<410:02:18, 2.74s/it]
5%|▌ | 30039/569592 [02:22<410:02:18, 2.74s/it]
5%|▌ | 30040/569592 [02:23<333:20:23, 2.22s/it]
5%|▌ | 30040/569592 [02:23<333:20:23, 2.22s/it]
5%|▌ | 30041/569592 [02:24<276:23:32, 1.84s/it]
5%|▌ | 30041/569592 [02:24<276:23:32, 1.84s/it]
5%|▌ | 30042/569592 [02:31<493:52:35, 3.30s/it]
5%|▌ | 30042/569592 [02:31<493:52:35, 3.30s/it]
5%|▌ | 30043/569592 [02:32<408:36:25, 2.73s/it]
5%|▌ | 30043/569592 [02:32<408:36:25, 2.73s/it]
5%|▌ | 30044/569592 [02:33<327:42:26, 2.19s/it]
5%|▌ | 30044/569592 [02:33<327:42:26, 2.19s/it]
5%|▌ | 30045/569592 [02:34<272:33:47, 1.82s/it]
5%|▌ | 30045/569592 [02:34<272:33:47, 1.82s/it]
5%|▌ | 30046/569592 [02:40<446:06:17, 2.98s/it]
5%|▌ | 30046/569592 [02:40<446:06:17, 2.98s/it]
5%|▌ | 30047/569592 [02:42<398:53:40, 2.66s/it]
5%|▌ | 30047/569592 [02:42<398:53:40, 2.66s/it]
5%|▌ | 30048/569592 [02:42<320:03:24, 2.14s/it]
5%|▌ | 30048/569592 [02:42<320:03:24, 2.14s/it]
5%|▌ | 30049/569592 [02:44<282:48:45, 1.89s/it]
5%|▌ | 30049/569592 [02:44<282:48:45, 1.89s/it]
5%|▌ | 30050/569592 [02:50<498:23:20, 3.33s/it]
5%|▌ | 30050/569592 [02:50<498:23:20, 3.33s/it]
5%|▌ | 30051/569592 [02:53<444:30:48, 2.97s/it]
5%|▌ | 30051/569592 [02:53<444:30:48, 2.97s/it]
5%|▌ | 30052/569592 [02:53<352:50:59, 2.35s/it]
5%|▌ | 30052/569592 [02:53<352:50:59, 2.35s/it]
5%|▌ | 30053/569592 [02:54<288:48:25, 1.93s/it]
5%|▌ | 30053/569592 [02:54<288:48:25, 1.93s/it]
5%|▌ | 30054/569592 [03:00<445:50:34, 2.97s/it]
5%|▌ | 30054/569592 [03:00<445:50:34, 2.97s/it]
5%|▌ | 30055/569592 [03:03<442:59:15, 2.96s/it]
5%|▌ | 30055/569592 [03:03<442:59:15, 2.96s/it]
5%|▌ | 30056/569592 [03:04<352:05:12, 2.35s/it]
5%|▌ | 30056/569592 [03:04<352:05:12, 2.35s/it]
5%|▌ | 30057/569592 [03:05<289:53:54, 1.93s/it]
5%|▌ | 30057/569592 [03:05<289:53:54, 1.93s/it]
5%|▌ | 30058/569592 [03:09<421:20:44, 2.81s/it]
5%|▌ | 30058/569592 [03:10<421:20:44, 2.81s/it]
5%|▌ | 30059/569592 [03:13<439:39:01, 2.93s/it]
5%|▌ | 30059/569592 [03:13<439:39:01, 2.93s/it]
5%|▌ | 30060/569592 [03:14<350:56:50, 2.34s/it]
5%|▌ | 30060/569592 [03:14<350:56:50, 2.34s/it]
5%|▌ | 30061/569592 [03:15<288:04:14, 1.92s/it]
5%|▌ | 30061/569592 [03:15<288:04:14, 1.92s/it]
5%|▌ | 30062/569592 [03:21<480:15:04, 3.20s/it]
5%|▌ | 30062/569592 [03:21<480:15:04, 3.20s/it]
5%|▌ | 30063/569592 [03:24<464:21:05, 3.10s/it]
5%|▌ | 30063/569592 [03:24<464:21:05, 3.10s/it]
5%|▌ | 30064/569592 [03:25<365:02:26, 2.44s/it]
5%|▌ | 30064/569592 [03:25<365:02:26, 2.44s/it]
5%|▌ | 30065/569592 [03:25<297:15:33, 1.98s/it]
5%|▌ | 30065/569592 [03:25<297:15:33, 1.98s/it]
5%|▌ | 30066/569592 [03:31<448:34:04, 2.99s/it]
5%|▌ | 30066/569592 [03:31<448:34:04, 2.99s/it]
5%|▌ | 30067/569592 [03:33<429:16:43, 2.86s/it]
5%|▌ | 30067/569592 [03:33<429:16:43, 2.86s/it]
5%|▌ | 30068/569592 [03:34<342:38:08, 2.29s/it]
5%|▌ | 30068/569592 [03:34<342:38:08, 2.29s//home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (100920000 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
it]
5%|▌ | 30069/569592 [03:35<283:13:53, 1.89s/it]
5%|▌ | 30069/569592 [03:35<283:13:53, 1.89s/it]
5%|▌ | 30070/569592 [03:41<472:52:23, 3.16s/it]
5%|▌ | 30070/569592 [03:41<472:52:23, 3.16s/it]
5%|▌ | 30071/569592 [03:43<420:53:22, 2.81s/it]
5%|▌ | 30071/569592 [03:43<420:53:22, 2.81s/it]
5%|▌ | 30072/569592 [03:44<336:05:54, 2.24s/it]
5%|▌ | 30072/569592 [03:44<336:05:54, 2.24s/it]
5%|▌ | 30073/569592 [03:45<277:50:10, 1.85s/it]
5%|▌ | 30073/569592 [03:45<277:50:10, 1.85s/it]
5%|▌ | 30074/569592 [03:52<475:10:06, 3.17s/it]
5%|▌ | 30074/569592 [03:52<475:10:06, 3.17s/it]
5%|▌ | 30075/569592 [03:53<402:43:11, 2.69s/it]
5%|▌ | 30075/569592 [03:53<402:43:11, 2.69s/it]
5%|▌ | 30076/569592 [03:56<404:09:27, 2.70s/it]
5%|▌ | 30076/569592 [03:56<404:09:27, 2.70s/it]
5%|▌ | 30077/569592 [03:57<324:48:17, 2.17s/it]
5%|▌ | 30077/569592 [03:57<324:48:17, 2.17s/it]
5%|▌ | 30078/569592 [04:02<455:13:20, 3.04s/it]
5%|▌ | 30078/569592 [04:02<455:13:20, 3.04s/it]
5%|▌ | 30079/569592 [04:03<360:51:34, 2.41s/it]
5%|▌ | 30079/569592 [04:06<360:51:34, 2.41s/it]
5%|▌ | 30080/569592 [04:07<423:33:27, 2.83s/it]
5%|▌ | 30080/569592 [04:07<423:33:27, 2.83s/it]
5%|▌ | 30081/569592 [04:07<337:16:58, 2.25s/it]
5%|▌ | 30081/569592 [04:07<337:16:58, 2.25s/it]
5%|▌ | 30082/569592 [04:10<364:58:53, 2.44s/it]
5%|▌ | 30082/569592 [04:10<364:58:53, 2.44s/it]
5%|▌ | 30083/569592 [04:13<374:06:38, 2.50s/it]
5%|▌ | 30083/569592 [04:13<374:06:38, 2.50s/it]
5%|▌ | 30084/569592 [04:14<315:09:58, 2.10s/it]
5%|▌ | 30084/569592 [04:14<315:09:58, 2.10s/it]
5%|▌ | 30085/569592 [04:15<264:31:28, 1.77s/it]
5%|▌ | 30085/569592 [04:15<264:31:28, 1.77s/it]
5%|▌ | 30086/569592 [04:20<416:33:09, 2.78s/it]
5%|▌ | 30086/569592 [04:20<416:33:09, 2.78s/it]
5%|▌ | 30087/569592 [04:22<370:12:23, 2.47s/it]
5%|▌ | 30087/569592 [04:22<370:12:23, 2.47s/it]
5%|▌ | 30088/569592 [04:25<400:47:41, 2.67s/it]
5%|▌ | 30088/569592 [04:25<400:47:41, 2.67s/it]
5%|▌ | 30089/569592 [04:26<321:46:31, 2.15s/it]
5%|▌ | 30089/569592 [04:26<321:46:31, 2.15s/it]
5%|▌ | 30090/569592 [04:30<410:36:30, 2.74s/it]
5%|▌ | 30090/569592 [04:30<410:36:30, 2.74s/it]
5%|▌ | 30091/569592 [04:32<390:41:31, 2.61s/it]
5%|▌ | 30091/569592 [04:33<390:41:31, 2.61s/it]
5%|▌ | 30092/569592 [04:35<387:26:47, 2.59s/it]
5%|▌ | 30092/569592 [04:35<387:26:47, 2.59s/it]
5%|▌ | 30093/569592 [04:36<313:58:06, 2.10s/it]
5%|▌ | 30093/569592 [04:36<313:58:06, 2.10s/it]
5%|▌ | 30094/569592 [04:41<448:24:59, 2.99s/it]
5%|▌ | 30094/569592 [04:41<448:24:59, 2.99s/it]
5%|▌ | 30095/569592 [04:43<408:02:18, 2.72s/it]
5%|▌ | 30095/569592 [04:43<408:02:18, 2.72s/it]
5%|▌ | 30096/569592 [04:44<328:17:28, 2.19s/it]
5%|▌ | 30096/569592 [04:44<328:17:28, 2.19s/it]
5%|▌ | 30097/569592 [04:46<325:47:48, 2.17s/it]
5%|▌ | 30097/569592 [04:46<325:47:48, 2.17s/it]
5%|▌ | 30098/569592 [04:50<398:04:24, 2.66s/it]
5%|▌ | 30098/569592 [04:50<398:04:24, 2.66s/it]
5%|▌ | 30099/569592 [04:54<443:14:55, 2.96s/it]
5%|▌ | 30099/569592 [04:54<443:14:55, 2.96s/it]
5%|▌ | 30100/569592 [04:55<353:08:26, 2.36s/it]
5%|▌ | 30100/569592 [04:55<353:08:26, 2.36s/it]
5%|▌ | 30101/569592 [04:56<314:28:57, 2.10s/it]
5%|▌ | 30101/569592 [04:56<314:28:57, 2.10s/it]
5%|▌ | 30102/569592 [05:00<416:08:48, 2.78s/it]
5%|▌ /home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (90151490 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
| 30102/569592 [05:01<416:08:48, 2.78s/it]
5%|▌ | 30103/569592 [05:04<439:15:41, 2.93s/it]
5%|▌ | 30103/569592 [05:04<439:15:41, 2.93s/it]
5%|▌ | 30104/569592 [05:05<348:47:55, 2.33s/it]
5%|▌ | 30104/569592 [05:05<348:47:55, 2.33s/it]
5%|▌ | 30105/569592 [05:06<285:38:41, 1.91s/it]
5%|▌ | 30105/569592 [05:06<285:38:41, 1.91s/it]
5%|▌ | 30106/569592 [05:10<395:08:29, 2.64s/it]
5%|▌ | 30106/569592 [05:10<395:08:29, 2.64s/it]
5%|▌ | 30107/569592 [05:14<453:51:34, 3.03s/it]
5%|▌ | 30107/569592 [05:14<453:51:34, 3.03s/it]
5%|▌ | 30108/569592 [05:15<363:11:48, 2.42s/it]
5%|▌ | 30108/569592 [05:15<363:11:48, 2.42s/it]
5%|▌ | 30109/569592 [05:21<505:16:26, 3.37s/it]
5%|▌ | 30109/569592 [05:21<505:16:26, 3.37s/it]
5%|▌ | 30110/569592 [05:27<630:26:17, 4.21s/it]
5%|▌ | 30110/569592 [05:27<630:26:17, 4.21s/it]
5%|▌ | 30111/569592 [05:32<690:34:49, 4.61s/it]
5%|▌ | 30111/569592 [05:32<690:34:49, 4.61s/it]
5%|▌ | 30112/569592 [05:38<737:02:09, 4.92s/it]
5%|▌ | 30112/569592 [05:38<737:02:09, 4.92s/it]
5%|▌ | 30113/569592 [05:43<761:14:03, 5.08s/it]
5%|▌ | 30113/569592 [05:43<761:14:03, 5.08s/it]
5%|▌ | 30114/569592 [05:49<769:42:51, 5.14s/it]
5%|▌ | 30114/569592 [05:49<769:42:51, 5.14s/it]
5%|▌ | 30115/569592 [05:49<577:24:13, 3.85s/it]
5%|▌ | 30115/569592 [05:49<577:24:13, 3.85s/it]
5%|▌ | 30116/569592 [05:50<446:54:06, 2.98s/it]
5%|▌ | 30116/569592 [05:50<446:54:06, 2.98s/it]
5%|▌ | 30117/569592 [05:51<356:23:50, 2.38s/it]
5%|▌ | 30117/569592 [05:51<356:23:50, 2.38s/it]
5%|▌ | 30118/569592 [05:52<292:57:06, 1.95s/it]
5%|▌ | 30118/569592 [05:52<292:57:06, 1.95s/it]
5%|▌ | 30119/569592 [05:53<248:01:22, 1.66s/it]
5%|▌ | 30119/569592 [05:53<248:01:22, 1.66s/it]
5%|▌ | 30120/569592 [05:54<215:40:33, 1.44s/it]
5%|▌ | 30120/569592 [05:54<215:40:33, 1.44s/it]
5%|▌ | 30121/569592 [05:55<192:34:33, 1.29s/it]
5%|▌ | 30121/569592 [05:55<192:34:33, 1.29s/it]
5%|▌ | 30122/569592 [05:56<178:23:49, 1.19s/it]
5%|▌ | 30122/569592 [05:56<178:23:49, 1.19s/it]
5%|▌ | 30123/569592 [06:02<388:01:03, 2.59s/it]
5%|▌ | 30123/569592 [06:02<388:01:03, 2.59s/it]
5%|▌ | 30124/569592 [06:03<339:15:13, 2.26s/it]
5%|▌ | 30124/569592 [06:03<339:15:13, 2.26s/it]
5%|▌ | 30125/569592 [06:04<280:41:20, 1.87s/it]
5%|▌ | 30125/569592 [06:04<280:41:20, 1.87s/it]
5%|▌ | 30126/569592 [06:05<239:49:31, 1.60s/it]
5%|▌ | 30126/569592 [06:05<239:49:31, 1.60s/it]/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (100920000 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
5%|▌ | 30127/569592 [06:12<458:04:28, 3.06s/it]
5%|▌ | 30127/569592 [06:12<458:04:28, 3.06s/it]
5%|▌ | 30128/569592 [06:14<402:06:59, 2.68s/it]
5%|▌ | 30128/569592 [06:14<402:06:59, 2.68s/it]
5%|▌ | 30129/569592 [06:15<327:20:55, 2.18s/it]
5%|▌ | 30129/569592 [06:15<327:20:55, 2.18s/it]
5%|▌ | 30130/569592 [06:16<272:56:56, 1.82s/it]
5%|▌ | 30130/569592 [06:16<272:56:56, 1.82s/it]
5%|▌ | 30131/569592 [06:22<482:15:03, 3.22s/it]
5%|▌ | 30131/569592 [06:22<482:15:03, 3.22s/it]
5%|▌ | 30132/569592 [06:23<395:38:32, 2.64s/it]
5%|▌ | 30132/569592 [06:23<395:38:32, 2.64s/it]
5%|▌ | 30133/569592 [06:25<352:11:25, 2.35s/it]
5%|▌ | 30133/569592 [06:25<352:11:25, 2.35s/it]
5%|▌ | 30134/569592 [06:26<290:04:29, 1.94s/it]
5%|▌ | 30134/569592 [06:26<290:04:29, 1.94s/it]
5%|▌ | 30135/569592 [06:32<455:53:47, 3.04s/it]
5%|▌ | 30135/569592 [06:32<455:53:47, 3.04s/it]
5%|▌ | 30136/569592 [06:34<403:09:00, 2.69s/it]
5%|▌ | 30136/569592 [06:34<403:09:00, 2.69s/it]
5%|▌ | 30137/569592 [06:34<324:08:22, 2.16s/it]
5%|▌ | 30137/569592 [06:35<324:08:22, 2.16s/it]
5%|▌ | 30138/569592 [06:36<273:49:58, 1.83s/it]
5%|▌ | 30138/569592 [06:36<273:49:58, 1.83s/it]
5%|▌ | 30139/569592 [06:42<481:40:22, 3.21s/it]
5%|▌ | 30139/569592 [06:42<481:40:22, 3.21s/it]
5%|▌ | 30140/569592 [06:43<383:03:16, 2.56s/it]
5%|▌ | 30140/569592 [06:43<383:03:16, 2.56s/it]
5%|▌ | 30141/569592 [06:45<373:04:19, 2.49s/it]
5%|▌ | 30141/569592 [06:45<373:04:19, 2.49s/it]
5%|▌ | 30142/569592 [06:47<357:48:03, 2.39s/it]
5%|▌ | 30142/569592 [06:48<357:48:03, 2.39s/it]
5%|▌ | 30143/569592 [06:52<436:54:10, 2.92s/it]
5%|▌ | 30143/569592 [06:52<436:54:10, 2.92s/it]
5%|▌ | 30144/569592 [06:54<405:13:50, 2.70s/it]
5%|▌ | 30144/569592 [06:54<405:13:50, 2.70s/it]
5%|▌ | 30145/569592 [06:55<338:51:20, 2.26s/it]
5%|▌ | 30145/569592 [06:55<338:51:20, 2.26s/it]
5%|▌ | 30146/569592 [07:00<475:31:47, 3.17s/it]
5%|▌ | 30146/569592 [07:00<475:31:47, 3.17s/it]
5%|▌ | 30147/569592 [07:03<448:14:51, 2.99s/it]
5%|▌ | 30147/569592 [07:03<448:14:51, 2.99s/it]
5%|▌ | 30148/569592 [07:04<370:56:35, 2.48s/it]
5%|▌ | 30148/569592 [07:04<370:56:35, 2.48s/it]
5%|▌ | 30149/569592 [07:05<311:51:55, 2.08s/it]
5%|▌ | 30149/569592 [07:05<311:51:55, 2.08s/it]
5%|▌ | 30150/569592 [07:09<387:15:42, 2.58s/it]
5%|▌ | 30150/569592 [07:09<387:15:42, 2.58s/it]
5%|▌ | 30151/569592 [07:12<394:22:29, 2.63s/it]
5%|▌ | 30151/569592 [07:12<394:22:29, 2.63s/it]
5%|▌ | 30152/569592 [07:14<389:51:57, 2.60s/it]
5%|▌ | 30152/569592 [07:14<389:51:57, 2.60s/it]
5%|▌ | 30153/569592 [07:15<315:28:58, 2.11s/it]
5%|▌ | 30153/569592 [07:15<315:28:58, 2.11s/it]
5%|▌ | 30154/569592 [07:19<390:23:43, 2.61s/it]
5%|▌ | 30154/569592 [07:19<390:23:43, 2.61s/it]
5%|▌ | 30155/569592 [07:23<449:21:56, 3.00s/it]
5%|▌ | 30155/569592 [07:23<449:21:56, 3.00s/it]
5%|▌ | 30156/569592 [07:25<401:30:36, 2.68s/it]
5%|▌ | 30156/569592 [07:25<401:30:36, 2.68s/it]
5%|▌ | 30157/569592 [07:26<323:15:08, 2.16s/it]
5%|▌ | 30157/569592 [07:26<323:15:08, 2.16s/it]
5%|▌ | 30158/569592 [07:28<327:59:55, 2.19s/it]
5%|▌ | 30158/569592 [07:28<327:59:55, 2.19s/it]
5%|▌ | 30159/569592 [07:33<450:16:22, 3.00s/it]
5%|▌ | 30159/569592 [07:33<450:16:22, 3.00s/it]
5%|▌ | 30160/569592 [07:35<400:19:15, 2.67s/it]
5%|▌ | 30160/569592 [07:35<400:19:15, 2.67s/it]
5%|▌ | 30161/569592 [07:36<323:42:46, 2.16s/it]
5%|▌ | 30161/569592 [07:36<323:42:46, 2.16s/it]
5%|▌ | 30162/569592 [07:39<377:55:34, 2.52s/it]
5%|▌ | 30162/569592 [07:39<377:55:34, 2.52s/it]
5%|▌ | 30163/569592 [07:43<437:48:43, 2.92s/it]
5%|▌ | 30163/569592 [07:44<437:48:43, 2.92s/it]
5%|▌ | 30164/569592 [07:46<441:54:47, 2.95s/it]
5%|▌ | 30164/569592 [07:46<441:54:47, 2.95s/it]
5%|▌ | 30165/569592 [07:47<350:58:17, 2.34s/it]
5%|▌ | 30165/569592 [07:47<350:58:17, 2.34s/it]
5%|▌ | 30166/569592 [07:48<293:12:54, 1.96s/it]
5%|▌ | 30166/569592 [07:48<293:12:54, 1.96s/it]
5%|▌ | 30167/569592 [07:54<455:08:04, 3.04s/it]
5%|▌ | 30167/569592 [07:54<455:08:04, 3.04s/it]
5%|▌ | 30168/569592 [07:56<441:37:00, 2.95s/it]
5%|▌ | 30168/569592 [07:56<441:37:00, 2.95s/it]
5%|▌ | 30169/569592 [07:57<350:53:38, 2.34s/it]
5%|▌ | 30169/569592 [07:57<350:53:38, 2.34s/it]
5%|▌ | 30170/569592 [08:01<404:40:01, 2.70s/it]
5%|▌ | 30170/569592 [08:01<404:40:01, 2.70s/it]
5%|▌ | 30171/569592 [08:04<410:14:44, 2.74s/it]
5%|▌ | 30171/569592 [08:04<410:14:44, 2.74s/it]
5%|▌ | 30172/569592 [08:08<463:03:14, 3.09s/it]
5%|▌ | 30172/569592 [08:08<463:03:14, 3.09s/it]
5%|▌ | 30173/569592 [08:09<365:00:21, 2.44s/it]
5%|▌ | 30173/569592 [08:09<365:00:21, 2.44s/it]
5%|▌ | 30174/569592 [08:10<298:00:31, 1.99s/it]
5%|▌ | 30174/569592 [08:10<298:00:31, 1.99s/it]
5%|▌ | 30175/569592 [08:14<396:26:05, 2.65s/it]
5%|▌ | 30175/569592 [08:14<396:26:05, 2.65s/it]
5%|▌ | 30176/569592 [08:18<470:36:56, 3.14s/it]
5%|▌ | 30176/569592 [08:18<470:36:56, 3.14s/it]
5%|▌ | 30177/569592 [08:19<371:21:52, 2.48s/it]
5%|▌ | 30177/569592 [08:19<371:21:52, 2.48s/it]
5%|▌ | 30178/569592 [08:20<303:05:35, 2.02s/it]
5%|▌ | 30178/569592 [08:20<303:05:35, 2.02s/it]
5%|▌ | 30179/569592 [08:24<403:46:54, 2.69s/it]
5%|▌ | 30179/569592 [08:24<403:46:54, 2.69s/it]
5%|▌ | 30180/569592 [08:28<469:48:30, 3.14s/it]
5%|▌ | 30180/569592 [08:28<469:48:30, 3.14s/it]
5%|▌ | 30181/569592 [08:29<369:14:55, 2.46s/it]
5%|▌ | 30181/569592 [08:29<369:14:55, 2.46s/it]
5%|▌ | 30182/569592 [08:30<300:08:08, 2.00s/it]
5%|▌ | 30182/569592 [08:30<300:08:08, 2.00s/it]
5%|▌ | 30183/569592 [08:34<401:42:12, 2.68s/it]
5%|▌ | 30183/569592 [08:34<401:42:12, 2.68s/it]
5%|▌ | 30184/569592 [08:38<447:22:53, 2.99s/it]
5%|▌ | 30184/569592 [08:38<447:22:53, 2.99s/it]
5%|▌ | 30185/569592 [08:39<356:17:21, 2.38s/it]
5%|▌ | 30185/569592 [08:39<356:17:21, 2.38s/it]
5%|▌ | 30186/569592 [08:40<292:28:22, 1.95s/it]
5%|▌ | 30186/569592 [08:40<292:28:22, 1.95s/it]
5%|▌ | 30187/569592 [08:45<414:57:29, 2.77s/it]
5%|▌ | 30187/569592 [08:45<414:57:29, 2.77s/it]
5%|▌ | 30188/569592 [08:48<419:46:09, 2.80s/it]
5%|▌ | 30188/569592 [08:48<4/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (94657684 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
19:46:09, 2.80s/it]
5%|▌ | 30189/569592 [08:49<340:36:38, 2.27s/it]
5%|▌ | 30189/569592 [08:49<340:36:38, 2.27s/it]
5%|▌ | 30190/569592 [08:50<286:05:19, 1.91s/it]
5%|▌ | 30190/569592 [08:50<286:05:19, 1.91s/it]
5%|▌ | 30191/569592 [08:55<442:38:33, 2.95s/it]
5%|▌ | 30191/569592 [08:55<442:38:33, 2.95s/it]
5%|▌ | 30192/569592 [08:58<461:04:59, 3.08s/it]
5%|▌ | 30192/569592 [08:58<461:04:59, 3.08s/it]
5%|▌ | 30193/569592 [08:59<363:56:14, 2.43s/it]
5%|▌ | 30193/569592 [08:59<363:56:14, 2.43s/it]
5%|▌ | 30194/569592 [09:00<297:05:08, 1.98s/it]
/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (100920000 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
5%|▌ | 30194/569592 [09:00<297:05:08, 1.98s/it]
5%|▌ | 30195/569592 [09:05<424:08:32, 2.83s/it]
5%|▌ | 30195/569592 [09:05<424:08:32, 2.83s/it]
5%|▌ | 30196/569592 [09:08<414:20:13, 2.77s/it]
5%|▌ | 30196/569592 [09:08<414:20:13, 2.77s/it]
5%|▌ | 30197/569592 [09:09<369:34:02, 2.47s/it]
5%|▌ | 30197/569592 [09:09<369:34:02, 2.47s/it]
5%|▌ | 30198/569592 [09:11<305:53:04, 2.04s/it]
5%|▌ | 30198/569592 [09:11<305:53:04, 2.04s/it]
5%|▌ | 30199/569592 [09:15<424:09:56, 2.83s/it]
5%|▌ | 30199/569592 [09:15<424:09:56, 2.83s/it]
5%|▌ | 30200/569592 [09:17<387:19:27, 2.59s/it]
5%|▌ | 30200/569592 [09:17<387:19:27, 2.59s/it]
5%|▌ | 30201/569592 [09:18<318:15:31, 2.12s/it]
5%|▌ | 30201/569592 [09:18<318:15:31, 2.12s/it]
5%|▌ | 30202/569592 [09:20<297:01:57, 1.98s/it]
5%|▌ | 30202/569592 [09:20<297:01:57, 1.98s/it]
5%|▌ | 30203/569592 [09:25<449:20:58, 3.00s/it]
5%|▌ | 30203/569592 [09:25<449:20:58, 3.00s/it]
5%|▌ | 30204/569592 [09:28<423:35:39, 2.83s/it]
5%|▌ | 30204/569592 [09:28<423:35:39, 2.83s/it]
5%|▌ | 30205/569592 [09:29<339:03:01, 2.26s/it]
5%|▌ | 30205/569592 [09:29<339:03:01, 2.26s/it]
5%|▌ | 30206/569592 [09:30<283:45:54, 1.89s/it]
5%|▌ | 30206/569592 [09:30<283:45:54, 1.89s/it]
5%|▌ | 30207/569592 [09:36<486:06:59, 3.24s/it]
5%|▌ | 30207/569592 [09:36<486:06:59, 3.24s/it]
5%|▌ | 30208/569592 [09:38<418:16:08, 2.79s/it]
5%|▌ | 30208/569592 [09:38<418:16:08, 2.79s/it]
5%|▌ | 30209/569592 [09:39<364:28:54, 2.43s/it]
5%|▌ | 30209/569592 [09:39<364:28:54, 2.43s/it]
5%|▌ | 30210/569592 [09:41<334:28:15, 2.23s/it]
5%|▌ | 30210/569592 [09:41<334:28:15, 2.23s/it]
5%|▌ | 30211/569592 [09:45<418:10:17, 2.79s/it]
5%|▌ | 30211/569592 [09:45<418:10:17, 2.79s/it]
5%|▌ | 30212/569592 [09:48<400:48:30, 2.68s/it]
5%|▌ | 30212/569592 [09:48<400:48:30, 2.68s/it]
5%|▌ | 30213/569592 [09:49<323:30:42, 2.16s/it]
5%|▌ | 30213/569592 [09:49<323:30:42, 2.16s/it]
5%|▌ | 30214/569592 [09:51<321:13:09, 2.14s/it]
5%|▌ | 30214/569592 [09:51<321:13:09, 2.14s/it]
5%|▌ | 30215/569592 [09:56<462:00:43, 3.08s/it]
5%|▌ | 30215/569592 [09:56<462:00:43, 3.08s/it]
5%|▌ | 30216/569592 [09:59<452:09:09, 3.02s/it]
5%|▌ | 30216/569592 [09:59<452:09:09, 3.02s/it]
5/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (93331640 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
%|▌ | 30217/569592 [10:00<373:34:54, 2.49s/it]
5%|▌ | 30217/569592 [10:00<373:34:54, 2.49s/it]
5%|▌ | 30218/569592 [10:01<303:47:55, 2.03s/it]
5%|▌ | 30218/569592 [10:01<303:47:55, 2.03s/it]
5%|▌ | 30219/569592 [10:06<425:52:15, 2.84s/it]
5%|▌ | 30219/569592 [10:06<425:52:15, 2.84s/it]
5%|▌ | 30220/569592 [10:08<374:38:32, 2.50s/it]
5%|▌ | 30220/569592 [10:08<374:38:32, 2.50s/it]
5%|▌ | 30221/569592 [10:09<328:08:58, 2.19s/it]
5%|▌ | 30221/569592 [10:09<328:08:58, 2.19s/it]
5%|▌ | 30222/569592 [10:15<484:17:44, 3.23s/it]
5%|▌ | 30222/569592 [10:15<484:17:44, 3.23s/it]
5%|▌ | 30223/569592 [10:18<498:35:36, 3.33s/it]
5%|▌ | 30223/569592 [10:18<498:35:36, 3.33s/it]
5%|▌ | 30224/569592 [10:22<539:48:04, 3.60s/it]
5%|▌ | 30224/569592 [10:22<539:48:04, 3.60s/it]
5%|▌ | 30225/569592 [10:27<570:12:49, 3.81s/it]
5%|▌ | 30225/569592 [10:27<570:12:49, 3.81s/it]
5%|▌ | 30226/569592 [10:31<610:24:36, 4.07s/it]
5%|▌ | 30226/569592 [10:31<610:24:36, 4.07s/it]
5%|▌ | 30227/569592 [10:35<582:21:09, 3.89s/it]
5%|▌ | 30227/569592 [10:35<582:21:09, 3.89s/it]
5%|▌ | 30228/569592 [10:40<640:46:23, 4.28s/it]
5%|▌ | 30228/569592 [10:40<640:46:23, 4.28s/it]
5%|▌ | 30229/569592 [10:41<488:57:54, 3.26s/it]
5%|▌ | 30229/569592 [10:41<488:57:54, 3.26s/it]
5%|▌ | 30230/569592 [10:45<511:24:22, 3.41s/it]
5%|▌ | 30230/569592 [10:45<511:24:22, 3.41s/it]
5%|▌ | 30231/569592 [10:48<512:35:07, 3.42s/it]
5%|▌ | 30231/569592 [10:48<512:35:07, 3.42s/it]
5%|▌ | 30232/569592 [10:51<496:55:46, 3.32s/it]
5%|▌ | 30232/569592 [10:51<496:55:46, 3.32s/it]
5%|▌ | 30233/569592 [10:52<388:35:26, 2.59s/it]
5%|▌ | 30233/569592 [10:52<388:35:26, 2.59s/it]
5%|▌ | 30234/569592 [10:53<317:58:25, 2.12s/it]
5%|▌ | 30234/569592 [10:53<317:58:25, 2.12s/it]
5%|▌ | 30235/569592 [10:54<267:57:52, 1.79s/it]
5%|▌ | 30235/569592 [10:54<267:57:52, 1.79s/it]
5%|▌ | 30236/569592 [10:55<232:23:39, 1.55s/it]
5%|▌ | 30236/569592 [10:55<232:23:39, 1.55s/it]
5%|▌ | 30237/569592 [10:56<204:31:36, 1.37s/it]
5%|▌ | 30237/569592 [10:56<204:31:36, 1.37s/it]
5%|▌ | 30238/569592 [10:57<185:34:17, 1.24s/it]
5%|▌ | 30238/569592 [10:57<185:34:17, 1.24s/it]
5%|▌ | 30239/569592 [10:58<172:52:06, 1.15s/it]
5%|▌ | 30239/569592 [10:58<172:52:06, 1.15s/it]
5%|▌ | 30240/569592 [11:01<255:31:39, 1.71s/it]
5%|▌ | 30240/569592 [11:01<255:31:39, 1.71s/it]
5%|▌ | 30241/569592 [11:05<354:08:23, 2.36s/it]
5%|▌ | 30241/569592 [11:05<354:08:23, 2.36s/it]
5%|▌ | 30242/569592 [11:06<290:37:59, 1.94s/it]
5%|▌ | 30242/569592 [11:06<290:37:59, 1.94s/it]
5%|▌ | 30243/569592 [11:07<263:12:42, 1.76s/it]
5%|▌ | 30243/569592 [11:07<263:12:42, 1.76s/it]
5%|▌ | 30244/569592 [11:11<358:06:09, 2.39s/it]
5%|▌ | 30244/569592 [11:11<358:06:09, 2.39s/it]
5%|▌ | 30245/569592 [11:15<409:06:55, 2.73s/it]
5%|▌ | 30245/569592 [11:15<409:06:55, 2.73s/it]
5%|▌ | 30246/569592 [11:16<333:14:01, 2.22s/it]
5%|▌ | 30246/569592 [11:16<333:14:01, 2.22s/it]
5%|▌ | 30247/569592 [11:18<346:53:03, 2.32s/it]
5%|▌ | 30247/569592 [11:19<346:53:03, 2.32s/it]
5%|▌ | 30248/569592 [11:21<375:59:21, 2.51s/it]
5%|▌ | 30248/569592 [11:21<375:59:21, 2.51s/it]
5%|▌ | 30249/569592 [11:25<452:05:11, 3.02s/it]
5%|▌ | 30249/569592 [11:25<452:05:11, 3.02s/it]
5%|▌ | 30250/569592 [11:26<363:39:43, 2.43s/it]
5%|▌ | 30250/569592 [11:26<363:39:43, 2.43s/it]
5%|▌ | 30251/569592 [11:28<349:35:54, 2.33s/it]
5%|▌ | 30251/569592 [11:29<349:35:54, 2.33s/it]
5%|▌ | 30252/569592 [11:31<369:12:18, 2.46s/it]
5%|▌ | 30252/569592 [11:31<369:12:18, 2.46s/it]
5%|▌ | 30253/569592 [11:35<436:44:11, 2.92s/it]
5%|▌ | 30253/569592 [11:35<436:44:11, 2.92s/it]
5%|▌ | 30254/569592 [11:36<348:43:02, 2.33s/it]
5%|▌ | 30254/569592 [11:36<348:43:02, 2.33s/it]
5%|▌ | 30255/569592 [11:38<329:30:01, 2.20s/it]
5%|▌ | 30255/569592 [11:38<329:30:01, 2.20s/it]
5%|▌ | 30256/569592 [11:42<395:54:56, 2.64s/it]
5%|▌ | 30256/569592 [11:42<395:54:56, 2.64s/it]
5%|▌ | 30257/569592 [11:46<458:19:27, 3.06s/it]
5%|▌ | 30257/569592 [11:46<458:19:27, 3.06s/it]
5%|▌ | 30258/569592 [11:47<368:17:08, 2.46s/it]
5%|▌ | 30258/569592 [11:47<368:17:08, 2.46s/it]
5%|▌ | 30259/569592 [11:48<314:47:21, 2.10s/it]
5%|▌ | 30259/569592 [11:48<314:47:21, 2.10s/it]
5%|▌ | 30260/569592 [11:52<390:04:24, 2.60s/it]
5%|▌ | 30260/569592 [11:52<390:04:24, 2.60s/it]
5%|▌ | 30261/569592 [11:57<492:40:29, 3.29s/it]
5%|▌ | 30261/569592 [11:57<492:40:29, 3.29s/it]
5%|▌ | 30262/569592 [11:58<391:15:55, 2.61s/it]
5%|▌ | 30262/569592 [11:58<391:15:55, 2.61s/it]
5%|▌ | 30263/569592 [11:59<315:26:23, 2.11s/it]
5%|▌ | 30263/569592 [11:59<315:26:23, 2.11s/it]
5%|▌ | 30264/569592 [12:02<371:00:28, 2.48s/it]
5%|▌ | 30264/569592 [12:02<371:00:28, 2.48s/it]
5%|▌ | 30265/569592 [12:07<463:11:53, 3.09s/it]
5%|▌ | 30265/569592 [12:07<463:11:53, 3.09s/it]
5%|▌ | 30266/569592 [12:09<425:00:30, 2.84s/it]
5%|▌ | 30266/569592 [12:09<425:00:30, 2.84s/it]
5%|▌ | 30267/569592 [12:10<339:21:19, 2.27s/it]
5%|▌ | 30267/569592 [12:10<339:21:19, 2.27s/it]
5%|▌ | 30268/569592 [12:12<353:22:04, 2.36s/it]
5%|▌ | 30268/569592 [12:12<353:22:04, 2.36s/it]
5%|▌ | 30269/569592 [12:19<528:59:49, 3.53s/it]
5%|▌ | 30269/569592 [12:19<528:59:49, 3.53s/it]
5%|▌ | 30270/569592 [12:20<438:04:21, 2.92s/it]
5%|▌ | 30270/569592 [12:20<438:04:21, 2.92s/it]
5%|▌ | 30271/569592 [12:21<350:51:30, 2.34s/it]
5%|▌ | 30271/569592 [12:21<350:51:30, 2.34s/it]
5%|▌ | 30272/569592 [12:23<326:27:36, 2.18s/it]
5%|▌ | 30272/569592 [12:23<326:27:36, 2.18s/it]
5%|▌ | 30273/569592 [12:29<479:23:01, 3.20s/it]
5%|▌ | 30273/569592 [12:29<479:23:01, 3.20s/it]
5%|▌ | 30274/569592 [12:30<384:46:25, 2.57s/it]
5%|▌ | 30274/569592 [12:30<384:46:25, 2.57s/it]
5%|▌ | 30275/569592 [12:31<310:43:10, 2.07s/it]
5%|▌ | 30275/569592 [12:31<310:43:10, 2.07s/it]
5%|▌ | 30276/569592 [12:33<311:52:01, 2.08s/it]
5%|▌ | 30276/569592 [12:33<311:52:01, 2.08s/it]
5%|▌ | 30277/569592 [12:40<536:58:03, 3.58s/it]
5%|▌ | 30277/569592 [12:40<536:58:03, 3.58s/it]
5%|▌ | 30278/569592 [12:41<419:59:28, 2.80s/it]
5%|▌ | 30278/569592 [12:41<419:5/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (100920000 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
9:28, 2.80s/it]
5%|▌ | 30279/569592 [12:42<336:24:43, 2.25s/it]
5%|▌ | 30279/569592 [12:42<336:24:43, 2.25s/it]
5%|▌ | 30280/569592 [12:43<284:43:00, 1.90s/it]
5%|▌ | 30280/569592 [12:43<284:43:00, 1.90s/it]
5%|▌ | 30281/569592 [12:48<444:17:06, 2.97s/it]
5%|▌ | 30281/569592 [12:48<444:17:06, 2.97s/it]
5%|▌ | 30282/569592 [12:49<354:14:14, 2.36s/it]
5%|▌ | 30282/569592 [12:49<354:14:14, 2.36s/it]
5%|▌ | 30283/569592 [12:50<306:45:18, 2.05s/it]
5%|▌ | 30283/569592 [12:50<306:45:18, 2.05s/it]
5%|▌ | 30284/569592 [12:53<318:38:52, 2.13s/it]
5%|▌ | 30284/569592 [12:53<318:38:52, 2.13s/it]
5%|▌ | 30285/569592 [12:59<493:42:56, 3.30s/it]
5%|▌ | 30285/569592 [12:59<493:42:56, 3.30s/it]
5%|▌ | 30286/569592 [13:00<387:51:15, 2.59s/it]
5%|▌ | 30286/569592 [13:00<387:51:15, 2.59s/it]
5%|▌ | 30287/569592 [13:01<314:10:23, 2.10s/it]
5%|▌ | 30287/569592 [13:01<314:10:23, 2.10s/it]
5%|▌ | 30288/569592 [13:03<339:20:24, 2.27s/it]
5%|▌ | 30288/569592 [13:03<339:20:24, 2.27s/it]
5%|▌ | 30289/569592 [13:07<414:49:26, 2.77s/it]
5%|▌ | 30289/569592 [13:07<414:49:26, 2.77s/it]
5%|▌ | 30290/5695/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (100920000 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
92 [13:09<347:00:55, 2.32s/it]
5%|▌ | 30290/569592 [13:09<347:00:55, 2.32s/it]
5%|▌ | 30291/569592 [13:11<375:31:51, 2.51s/it]
5%|▌ | 30291/569592 [13:11<375:31:51, 2.51s/it]
5%|▌ | 30292/569592 [13:14<353:43:31, 2.36s/it]
5%|▌ | 30292/569592 [13:14<353:43:31, 2.36s/it]
5%|▌ | 30293/569592 [13:18<467:50:52, 3.12s/it]
5%|▌ | 30293/569592 [13:18<467:50:52, 3.12s/it]
5%|▌ | 30294/569592 [13:20<394:45:49, 2.64s/it]
5%|▌ | 30294/569592 [13:20<394:45:49, 2.64s/it]
5%|▌ | 30295/569592 [13:21<323:21:23, 2.16s/it]
5%|▌ | 30295/569592 [13:21<323:21:23, 2.16s/it]
5%|▌ | 30296/569592 [13:23<325:17:31, 2.17s/it]
5%|▌ | 30296/569592 [13:23<325:17:31, 2.17s/it]
5%|▌ | 30297/569592 [13:30<516:22:50, 3.45s/it]
5%|▌ | 30297/569592 [13:30<516:22:50, 3.45s/it]
5%|▌ | 30298/569592 [13:30<402:02:55, 2.68s/it]
5%|▌ | 30298/569592 [13:31<402:02:55, 2.68s/it]
5%|▌ | 30299/569592 [13:32<336:11:27, 2.24s/it]
5%|▌ | 30299/569592 [13:32<336:11:27, 2.24s/it]
5%|▌ | 30300/569592 [13:34<328:17:15, 2.19s/it]
5%|▌ | 30300/569592 [13:34<328:17:15, 2.19s/it]
5%|▌ | 30301/569592 [13:38<441:29:58, 2.95s/it]
5%|▌ | 30301/569592 [13:39<441:29:58, 2.95s/it]
5%|▌ | 30302/569592 [13:40<369:57:37, 2.47s/it]
5%|▌ | 30302/569592 [13:40<369:57:37, 2.47s/it]
5%|▌ | 30303/569592 [13:41<302:13:17, 2.02s/it]
5%|▌ | 30303/569592 [13:41<302:13:17, 2.02s/it]
5%|▌ | 30304/569592 [13:43<330:09:44, 2.20s/it]
5%|▌ | 30304/569592 [13:43<330:09:44, 2.20s/it]
5%|▌ | 30305/569592 [13:49<475:59:51, 3.18s/it]
5%|▌ | 30305/569592 [13:49<475:59:51, 3.18s/it]
5%|▌ | 30306/569592 [13:50<380:43:18, 2.54s/it]
5%|▌ | 30306/569592 [13:50<380:43:18, 2.54s/it]
5%|▌ | 30307/569592 [13:51<308:42:26, 2.06s/it]
5%|▌ | 30307/569592 [13:51<308:42:26, 2.06s/it]
5%|▌ | 30308/569592 [13:54<359:36:26, 2.40s/it]
5%|▌ | 30308/569592 [13:54<359:36:26, 2.40s/it]
5%|▌ | 30309/569592 [13:59<486:48:20, 3.25s/it]
5%|▌ | 30309/569592 [13:59<486:48:20, 3.25s/it]
5%|▌ | 30310/569592 [14:00<383:34:52, 2.56s/it]
5%|▌ | 30310/569592 [14:00<383:34:52, 2.56s/it]
5%|▌ | 30311/569592 [14:02<336:13:14, 2.24s/it]
5%|▌ | 30311/569592 [14:02<336:13:14, 2.24s/it]
5%|▌ | 30312/569592 [14:05<373:43:24, 2.49s/it]
5%|▌ | 30312/569592 [14:05<373:43:24, 2.49s/it]
5%|▌ | 30313/569592 [14:09<443:24:17, 2.96s/it]
5%|▌ | 30313/569592 [14:09<443:24:17, 2.96s/it]
5%|▌ | 30314/569592 [14:10<354:15:54, 2.36s/it]
5%|▌ | 30314/569592 [14:10<354:15:54, 2.36s/it]
5%|▌ | 30315/569592 [14:11<316:18:56, 2.11s/it]
5%|▌ | 30315/569592 [14:11<316:18:56, 2.11s/it]
5%|▌ | 30316/569592 [14:15<366:56:40, 2.45s/it]
5%|▌ | 30316/569592 [14:15<366:56:40, 2.45s/it]
5%|▌ | 30317/569592 [14:20<507:21:17, 3.39s/it]
5%|▌ | 30317/569592 [14:20<507:21:17, 3.39s/it]
5%|▌ | 30318/569592 [14:21<396:29:00, 2.65s/it]
5%|▌ | 30318/569592 [14:21<396:29:00, 2.65s/it]
5%|▌ | 30319/569592 [14:22<320:14:18, 2.14s/it]
5%|▌ | 30319/569592 [14:22<320:14:18, 2.14s/it]
5%|▌ | 30320/569592 [14:25<335:48:26, 2.24s/it]
5%|▌ | 30320/569592 [14:25<335:48:26, 2.24s/it]
5%|▌ | 30321/569592 [14:30<489:21:20, 3.27s/it]
5%|▌ | 30321/569592 [14:30<489:21:20, 3.27s/it]
5%|▌ | 30322/569592 [14:31<384:49:01, 2.57s/it]
5%|▌ | 30322/569592 [14:31<384:49:01, 2.57s/it]
5%|▌ | 30323/569592 [14:32<311:45:43, 2.08s/it]
5%|▌ | 30323/569592 [14:32<311:45:43, 2.08s/it]
5%|▌ | 30324/569592 [14:34<319:42:32, 2.13s/it]
5%|▌ | 30324/569592 [14:34<319:42:32, 2.13s/it]
5%|▌ | 30325/569592 [14:40<491:30:45, 3.28s/it]
5%|▌ | 30325/569592 [14:40<491:30:45, 3.28s/it]
5%|▌ | 30326/569592 [14:41<384:58:18, 2.57s/it]
5%|▌ | 30326/569592 [14:41<384:58:18, 2.57s/it]
5%|▌ | 30327/569592 [14:42<313:25:59, 2.09s/it]
5%|▌ | 30327/569592 [14:42<313:25:59, 2.09s/it]
5%|▌ | 30328/569592 [14:45<345:57:47, 2.31s/it]
5%|▌ | 30328/569592 [14:45<345:57:47, 2.31s/it]
5%|▌ | 30329/569592 [14:50<481:32:48, 3.21s/it]
5%|▌ | 30329/569592 [14:50<481:32:48, 3.21s/it]
5%|▌ | 30330/569592 [14:51<379:17:38, 2.53s/it]
5%|▌ | 30330/569592 [14:51<379:17:38, 2.53s/it]
5%|▌ | 30331/569592 [14:52<307:28:48, 2.05s/it]
5%|▌ | 30331/569592 [14:53<307:28:48, 2.05s/it]
5%|▌ | 30332/569592 [14:55<340:32:38, 2.27s/it]
5%|▌ | 30332/569592 [14:55<340:32:38, 2.27s/it]
5%|▌ | 30333/569592 [15:00<466:53:08, 3.12s/it]
5%|▌ | 30333/569592 [15:00<466:53:08, 3.12s/it]
5%|▌ | 30334/569592 [15:05<564:40:06, 3.77s/it]
5%|▌ | 30334/569592 [15:05<564:40:06, 3.77s/it]
5%|▌ | 30335/569592 [15:10<623:55:44, 4.17s/it]
5%|▌ | 30335/569592 [15:10<623:55:44, 4.17s/it]
5%|▌ | 30336/569592 [15:14<605:44:42, 4.04s/it]
5%|▌ | 30336/569592 [15:14<605:44:42, 4.04s/it]
5%|▌ | 30337/569592 [15:18<613:14:43, 4.09s/it]
5%|▌ | 30337/569592 [15:18<613:14:43, 4.09s/it]
5%|▌ | 30338/569592 [15:23<649:36:43, 4.34s/it]
5%|▌ | 30338/569592 [15:23<649:36:43, 4.34s/it]
5%|▌ | 30339/569592 [15:29<694:09:30, 4.63s/it]
5%|▌ | 30339/569592 [15:29<694:09:30, 4.63s/it]
5%|▌ | 30340/569592 [15:34<725:46:10, 4.85s/it]
5%|▌ | 30340/569592 [15:34<725:46:10, 4.85s/it]
5%|▌ | 30341/569592 [15:39<714:14:23, 4.77s/it]
5%|▌ | 30341/569592 [15:39<714:14:23, 4.77s/it]
5%|▌ | 30342/569592 [15:42<670:57:29, 4.48s/it]
5%|▌ | 30342/569592 [15:42<670:57:29, 4.48s/it]
5%|▌ | 30343/569592 [15:46<624:49:49, 4.17s/it]
5%|▌ | 30343/569592 [15:46<624:49:49, 4.17s/it]
5%|▌ | 30344/569592 [15:47<479:02:24, 3.20s/it]
5%|▌ | 30344/569592 [15:47<479:02:24, 3.20s/it]
5%|▌ | 30345/569592 [15:48<377:09:04, 2.52s/it]
5%|▌ | 30345/569592 [15:48<377:09:04, 2.52s/it]
5%|▌ | 30346/569592 [15:53<507:37:35, 3.39s/it]
5%|▌ | 30346/569592 [15:53<507:37:35, 3.39s/it]
5%|▌ | 30347/569592 [15:54<403:03:21, 2.69s/it]
5%|▌ | 30347/569592 [15:54<403:03:21, 2.69s/it]
5%|▌ | 30348/569592 [16:00<531:25:23, 3.55s/it]
5%|▌ | 30348/569592 [16:00<531:25:23, 3.55s/it]
5%|▌ | 30349/569592 [16:01<414:02:18, 2.76s/it]
5%|▌ | 30349/569592 [16:01<414:02:18, 2.76s/it]
5%|▌ | 30350/569592 [16:04<435:00:48, 2.90s/it]
5%|▌ | 30350/569592 [16:04<435:00:48, 2.90s/it]
5%|▌ | 30351/569592 [16:05<347:31:30, 2.32s/it]
5%|▌ | 30351/569592 [16:05<347:31:30, 2.32s/it]
5%|▌ /home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (100920000 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
| 30352/569592 [16:06<288:16:19, 1.92s/it]
5%|▌ | 30352/569592 [16:06<288:16:19, 1.92s/it]
5%|▌ | 30353/569592 [16:07<248:39:23, 1.66s/it]
5%|▌ | 30353/569592 [16:07<248:39:23, 1.66s/it]
5%|▌ | 30354/569592 [16:08<216:35:59, 1.45s/it]
5%|▌ | 30354/569592 [16:08<216:35:59, 1.45s/it]
5%|▌ | 30355/569592 [16:09<195:26:14, 1.30s/it]
5%|▌ | 30355/569592 [16:09<195:26:14, 1.30s/it]
5%|▌ | 30356/569592 [16:10<181:27:16, 1.21s/it]
5%|▌ | 30356/569592 [16:10<181:27:16, 1.21s/it]
5%|▌ | 30357/569592 [16:14<327:21:02, 2.19s/it]
5%|▌ | 30357/569592 [16:14<327:21:02, 2.19s/it]
5%|▌ | 30358/569592 [16:15<276:54:22, 1.85s/it]
5%|▌ | 30358/569592 [16:15<276:54:22, 1.85s/it]
5%|▌ | 30359/569592 [16:19<373:22:05, 2.49s/it]
5%|▌ | 30359/569592 [16:19<373:22:05, 2.49s/it]
5%|▌ | 30360/569592 [16:20<304:46:06, 2.03s/it]
5%|▌ | 30360/569592 [16:20<304:46:06, 2.03s/it]
5%|▌ | 30361/569592 [16:23<340:53:41, 2.28s/it]
5%|▌ | 30361/569592 [16:23<340:53:41, 2.28s/it]
5%|▌ | 30362/569592 [16:25<307:01:34, 2.05s/it]
5%|▌ | 30362/569592 [16:25<307:01:34, 2.05s/it]
5%|▌ | 30363/569592 [16:28<385:53:45, 2.58/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (98263910 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
s/it]
5%|▌ | 30363/569592 [16:28<385:53:45, 2.58s/it]
5%|▌ | 30364/569592 [16:29<314:14:54, 2.10s/it]
5%|▌ | 30364/569592 [16:29<314:14:54, 2.10s/it]
5%|▌ | 30365/569592 [16:34<423:40:47, 2.83s/it]
5%|▌ | 30365/569592 [16:34<423:40:47, 2.83s/it]
5%|▌ | 30366/569592 [16:36<387:55:58, 2.59s/it]
5%|▌ | 30366/569592 [16:36<387:55:58, 2.59s/it]
5%|▌ | 30367/569592 [16:40<433:42:03, 2.90s/it]
5%|▌ | 30367/569592 [16:40<433:42:03, 2.90s/it]
5%|▌ | 30368/569592 [16:41<347:52:41, 2.32s/it]
5%|▌ | 30368/569592 [16:41<347:52:41, 2.32s/it]
5%|▌ | 30369/569592 [16:44<396:19:46, 2.65s/it]
5%|▌ | 30369/569592 [16:44<396:19:46, 2.65s/it]
5%|▌ | 30370/569592 [16:46<376:31:49, 2.51s/it]
5%|▌ | 30370/569592 [16:46<376:31:49, 2.51s/it]
5%|▌ | 30371/569592 [16:49<398:25:15, 2.66s/it]
5%|▌ | 30371/569592 [16:49<398:25:15, 2.66s/it]
5%|▌ | 30372/569592 [16:51<359:40:58, 2.40s/it]
5%|▌ | 30372/569592 [16:51<359:40:58, 2.40s/it]
5%|▌ | 30373/569592 [16:55<423:38:47, 2.83s/it]
5%|▌ | 30373/569592 [16:55<423:38:47, 2.83s/it]
5%|▌ | 30374/569592 [16:56<339:33:13, 2.27s/it]
5%|▌ | 30374/569592 [16:56<339:33:13, 2.27s/it]
5%|▌ | 30375/569592 [16:59<369:31:29, 2.47s/it]
5%|▌ | 30375/569592 [16:59<369:31:29, 2.47s/it]
5%|▌ | 30376/569592 [17:00<314:45:57, 2.10s/it]
5%|▌ | 30376/569592 [17:00<314:45:57, 2.10s/it]
5%|▌ | 30377/569592 [17:05<460:19:00, 3.07s/it]
5%|▌ | 30377/569592 [17:05<460:19:00, 3.07s/it]
5%|▌ | 30378/569592 [17:06<370:19:31, 2.47s/it]
5%|▌ | 30378/569592 [17:06<370:19:31, 2.47s/it]
5%|▌ | 30379/569592 [17:08<352:19:33, 2.35s/it]
5%|▌ | 30379/569592 [17:08<352:19:33, 2.35s/it]
5%|▌ | 30380/569592 [17:11<361:10:09, 2.41s/it]
5%|▌ | 30380/569592 [17:11<361:10:09, 2.41s/it]
5%|▌ | 30381/569592 [17:15<429:59:58, 2.87s/it]
5%|▌ | 30381/569592 [17:15<429:59:58, 2.87s/it]
5%|▌ | 30382/569592 [17:16<365:27:40, 2.44s/it]
5%|▌ | 30382/569592 [17:16<365:27:40, 2.44s/it]
5%|▌ | 30383/569592 [17:19<382:12:07, 2.55s/it]
5%|▌ | 30383/569592 [17:19<382:12:07, 2.55s/it]
5%|▌ | 30384/569592 [17:21<354:52:56, 2.37s/it]
5%|▌ | 30384/569592 [17:21<354:52:56, 2.37s/it]
5%|▌ | 30385/569592 [17:25<419:48:36, 2.80s/it]
5%|▌ | 30385/569592 [17:25<419:48:36, 2.80s/it]
5%|▌ | 30386/569592 [17:26<351:44:27, 2.35s/it]
5%|▌ | 30386/569592 [17:26<351:44:27, 2.35s/it]
5%|▌ | 30387/569592 [17:29<388:29:48, 2.59s/it]
5%|▌ | 30387/569592 [17:29<388:29:48, 2.59s/it]
5%|▌ | 30388/569592 [17:31<355:41:12, 2.37s/it]
5%|▌ | 30388/569592 [17:31<355:41:12, 2.37s/it]
5%|▌ | 30389/569592 [17:35<410:28:09, 2.74s/it]
5%|▌ | 30389/569592 [17:35<410:28:09, 2.74s/it]
5%|▌ | 30390/569592 [17:37<369:20:36, 2.47s/it]
5%|▌ | 30390/569592 [17:37<369:20:36, 2.47s/it]
5%|▌ | 30391/569592 [17:40<408:30:41, 2.73s/it]
5%|▌ | 30391/569592 [17:40<408:30:41, 2.73s/it]
5%|▌ | 30392/569592 [17:42<380:54:41, 2.54s/it]
5%|▌ | 30392/569592 [17:42<380:54:41, 2.54s/it]
5%|▌ | 30393/569592 [17:45<381:08:13, 2.54s/it]
5%|▌ | 30393/569592 [17:45<381:08:13, 2.54s/it]
5%|▌ | 30394/569592 [17:47<353:20:43, 2.36s/it]
5%|▌ | 30394/569592 [17:47<353:20:43, 2.36s/it]
5%|▌ | 30395/569592 [17:50<404:47:17, 2.70s/it]
5%|▌ | 30395/569592 [17:50<404:47:17, 2.70s/it]
5%|▌ | 30396/569592 [17:52<383:15:23, 2.56s/it]
5%|▌ | 30396/569592 [17:52<383:15:23, 2.56s/it]
5%|▌ | 30397/569592 [17:55<408:18:37, 2.73s/it]
5%|▌ | 30397/569592 [17:55<408:18:37, 2.73s/it]
5%|▌ | 30398/569592 [17:57<345:21:27, 2.31s/it]
5%|▌ | 30398/569592 [17:57<345:21:27, 2.31s/it]
5%|▌ | 30399/569592 [18:00<398:17:17, 2.66s/it]
5%|▌ | 30399/569592 [18:00<398:17:17, 2.66s/it]
5%|▌ | 30400/569592 [18:02<375:58:34, 2.51s/it]
5%|▌ | 30400/569592 [18:02<375:58:34, 2.51s/it]
5%|▌ | 30401/569592 [18:05<378:14:22, 2.53s/it]
5%|▌ | 30401/569592 [18:05<378:14:22, 2.53s/it]
5%|▌ | 30402/569592 [18:07<357:23:25, 2.39s/it]
5%/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (95971008 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
|▌ | 30402/569592 [18:07<357:23:25, 2.39s/it]
5%|▌ | 30403/569592 [18:10<401:08:55, 2.68s/it]
5%|▌ | 30403/569592 [18:10<401:08:55, 2.68s/it]
5%|▌ | 30404/569592 [18:13<380:45:07, 2.54s/it]
5%|▌ | 30404/569592 [18:13<380:45:07, 2.54s/it]
5%|▌ | 30405/569592 [18:16<418:24:30, 2.79s/it]
5%|▌ | 30405/569592 [18:16<418:24:30, 2.79s/it]
5%|▌ | 30406/569592 [18:19<424:25:00, 2.83s/it]
5%|▌ | 30406/569592 [18:19<424:25:00, 2.83s/it]
5%|▌ | 30407/569592 [18:21<389:17:56, 2.60s/it]
5%|▌ | 30407/569592 [18:21<389:17:56, 2.60s/it]
5%|▌ | 30408/569592 [18:24<407:29:57, 2.72s/it]
5%|▌ | 30408/569592 [18:24<407:29:57, 2.72s/it]
5%|▌ | 30409/569592 [18:26<366:50:39, 2.45s/it]
5%|▌ | 30409/569592 [18:26<366:50:39, 2.45s/it]
5%|▌ | 30410/569592 [18:28<347:03:39, 2.32s/it]
5%|▌ | 30410/569592 [18:28<347:03:39, 2.32s/it]
5%|▌ | 30411/569592 [18:31<393:41:29, 2.63s/it]
5%|▌ | 30411/569592 [18:31<393:41:29, 2.63s/it]
5%|▌ | 30412/569592 [18:32<317:43:29, 2.12s/it]
5%|▌ | 30412/569592 [18:32<317:43:29, 2.12s/it]
5%|▌ | 30413/569592 [18:37<426:50:32, 2.85s/it]
5%|▌ | 30413/569592 [18:37<426:50:32, 2.85s/it]
5%|▌ | 30414/569592 [18:38<351:39:00, 2.35s/it]
5%|▌ | 30414/569592 [18:38<351:39:00, 2.35s/it]
5%|▌ | 30415/569592 [18:42<430:32:18, 2.87s/it]
5%|▌ | 30415/569592 [18:42<430:32:18, 2.87s/it]
5%|▌ | 30416/569592 [18:43<365:25:05, 2.44s/it]
5%|▌ | 30416/569592 [18:43<365:25:05, 2.44s/it]
5%|▌ | 30417/569592 [18:47<405:03:09, 2.70s/it]
5%|▌ | 30417/569592 [18:47<405:03:09, 2.70s/it]
5%|▌ | 30418/569592 [18:49<368:42:59, 2.46s/it]
5%|▌ | 30418/569592 [18:49<368:42:59, 2.46s/it]
5%|▌ | 30419/569592 [18:52<396:55:48, 2.65s/it]
5%|▌ | 30419/569592 [18:52<396:55:48, 2.65s/it]
5%|▌ | 30420/569592 [18:53<336:12:44, 2.24s/it]
5%|▌ | 30420/569592 [18:53<336:12:44, 2.24s/it]
5%|▌ | 30421/569592 [18:57<402:20:00, 2.69s/it]
5%|▌ | 30421/569592 [18:57<402:20:00, 2.69s/it]
5%|▌ | 30422/569592 [18:59<394:21:15, 2.63s/it]
5%|▌ | 30422/569592 [18:59<394:21:15, 2.63s/it]
5%|▌ | 30423/569592 [19:02<412:51:42, 2.76s/it]
5%|▌ | 30423/569592 [19:02<412:51:42, 2.76s/it]
5%|▌ | 30424/569592 [19:03<331:04:45, 2.21s/it]
5%|▌ | 30424/569592 [19:03<331:04:45, 2.21s/it]
5%|▌ | 30425/569592 [19:06<379:44:31, 2.54s/it]
5%|▌ | 30425/569592 [19:07<379:44:31, 2.54s/it]
5%|▌ | 30426/569592 [19:09<362:16:45, 2.42s/it]
5%|▌ | 30426/569592 [19:09<362:16:45, 2.42s/it]
5%|▌ | 30427/569592 [19:13<462:40:02, 3.09s/it]
5%|▌ | 30427/569592 [19:13<462:40:02, 3.09s/it]
5%|▌ | 30428/569592 [19:14<364:38:38, 2.43s/it]
5%|▌ | 30428/569592 [19:14<364:38:38, 2.43s/it]
5%|▌ | 30429/569592 [19:16<355:26:33, 2.37s/it]
5%|▌ | 30429/569592 [19:16<355:26:33, 2.37s/it]
5%|▌ | 30430/569592 [19:20<407:55:46, 2.72s/it]
5%|▌ | 30430/569592 [19:20<407:55:46, 2.72s/it]
5%|▌ | 30431/569592 [19:23<422:42:06, 2.82s/it]
5%|▌ | 30431/569592 [19:23<422:42:06, 2.82s/it]
5%|▌ | 30432/569592 [19:24<337:05:45, 2.25s/it]
5%|▌ | 30432/569592 [19:24<337:05:45, 2.25s/it]
5%|▌ | 30433/569592 [19:26<329:56:31, 2.20s/it]
5%|▌ | 30433/569592 [19:26<329:56:31, 2.20s/it]
5%|▌ | 30434/569592 [19:30<427:35:20, 2.86s/it]
5%|▌ | 30434/569592 [19:30<427:35:20, 2.86s/it]
5%|▌ | 30435/569592 [19:32<361:43:16, 2.42s/it]
5%|▌ | 30435/569592 [19:32<361:43:16, 2.42s/it]
5%|▌ | 30436/569592 [19:33<317:31:19, 2.12s/it]
5%|▌ | 30436/569592 [19:33<317:31:19, 2.12s/it]
5%|▌ | 30437/569592 [19:37<404:02:01, 2.70s/it]
5%|▌ | 30437/569592 [19:37<404:02:01, 2.70s/it]
5%|▌ | 30438/569592 [19:40<387:16:17, 2.59s/it]
5%|▌ | 30438/569592 [19:40<387:16:17, 2.59s/it]
5%|▌ | 30439/569592 [19:43<413:15:13, 2.76s/it]
5%|▌ | 30439/569592 [19:43<413:15:13, 2.76s/it]
5%|▌ | 30440/569592 [19:44<332:19:58, 2.22s/it]
5%|▌ | 30440/569592 [19:44<332:19:58, 2.22s/it]
5%|▌ | 30441/569592 [19:48<424:46:31, 2.84s/it]
5%|▌ | 30441/569592 [19:48<424:46:31, 2.84s/it]
5%|▌ | 30442/569592 [19:51<417:26:33, 2.79s/it]
5%|▌ | 30442/569592 [19:51<417:26:33, 2.79s/it]
5%|▌ | 30443/569592 [19:53<380:39:27, 2.54s/it]
5%|▌ | 30443/569592 [19:53<380:39:27, 2.54s/it]
5%|▌ | 30444/569592 [19:54<307:58:26, 2.06s/it]
5%|▌ | 30444/569592 [19:54<307:58:26, 2.06s/it]
5%|▌ | 30445/569592 [20:00<515:21:59, 3.44s/it]
5%|▌ | 30445/569592 [20:00<515:21:59, 3.44s/it]
5%|▌ | 30446/569592 [20:01<403:36:12, 2.69s/it]
5%|▌ | 30446/569592 [20:01<403:36:12, 2.69s/it]
5%|▌ | 30447/569592 [20:07<524:40:20, 3.50s/it]
5%|▌ | 30447/569592 [20:07<524:40:20, 3.50s/it]
5%|▌ | 30448/569592 [20:12<625:30:42, 4.18s/it]
5%|▌ | 30448/569592 [20:12<625:30:42, 4.18s/it]
5%|▌ | 30449/569592 [20:18<674:00:08, 4.50s/it]
5%|▌ | 30449/569592 [20:18<674:00:08, 4.50s/it]
5%|▌ | 30450/569592 [20:21<632:30:09, 4.22s/it]
5%|▌ | 30450/569592 [20:21<632:30:09, 4.22s/it]
5%|▌ | 30451/569592 [20:26<653:20:28, 4.36s/it]
5%|▌ | 30451/569592 [20:26<653:20:28, 4.36s/it]
5%|▌ | 30452/569592 [20:30<630:27:33, 4.21s/it]
5%|▌ | 30452/569592 [20:30<630:27:33, 4.21s/it]
5%|▌ | 30453/569592 [20:31<484:07:35, 3.23s/it]
5%|▌ | 30453/569592 [20:31<484:07:35, 3.23s/it]
5%|▌ | 30454/569592 [20:36<556:57:27, 3.72s/it]
5%|▌ | 30454/569592 [20:36<556:57:27, 3.72s/it]
5%|▌ | 30455/569592 [20:40<598:14:24, 3.99s/it]
5%|▌ | 30455/569592 [20:40<598:14:24, 3.99s/it]
5%|▌ | 30456/569592 [20:45<623:43:21, 4.16s/it]
5%|▌ | 30456/569592 [20:45<623:43:21, 4.16s/it]
5%|▌ | 30457/569592 [20:50<654:26:04, 4.37s/it]
5%|▌ | 30457/569592 [20:50<654:26:04, 4.37s/it]
5%|▌ | 30458/569592 [20:53<601:17:41, 4.02s/it]
5%|▌ | 30458/569592 [20:53<601:17:41, 4.02s/it]
5%|▌ | 30459/569592 [20:54<461:43:15, 3.08s/it]
5%|▌ | 30459/569592 [20:54<461:43:15, 3.08s/it]
5%|▌ | 30460/569592 [20:58<539:43:15, 3.60s/it]
5%|▌ | 30460/569592 [20:59<539:43:15, 3.60s/it]
5%|▌ | 30461/569592 [21:03<583:03:17, 3.89s/it]
5%|▌ | 30461/569592 [21:03<583:03:17, 3.89s/it]
5%|▌ | 30462/569592 [21:04<447:29:13, 2.99s/it]
5%|▌ | 30462/569592 [21:04<447:29:13, 2.99s/it]
5%|▌ | 30463/569592 [21:09<539:03:58, 3.60s/it]
5%|▌ | 30463/569592 [21:09<539:03:58, 3.60s/it]
5%|▌ | 30464/569592 [21:13<566:53:49, 3.79s/it]
5%|▌ | 30464/569592 [21:13<566:53:49, 3.79s/it]
5%|▌ | 30465/569592 [21:14<436:47:55, 2.92s/it]
5%|▌ | 30465/569592 [21:14<436:47:55, 2.92s/it]
5%|▌ | 30466/569592 [21:18<496:50:47, 3.32s/it]
5%|▌ | 30466/569592 [21:18<496:50:47, 3.32s/it]
5%|▌ | 30467/569592 [21:19<390:21:13, 2.61s/it]
5%|▌ | 30467/569592 [21:19<390:21:13, 2.61s/it]
5%|▌ | 30468/569592 [21:24<469:54:08, 3.14s/it]
5%|▌ | 30468/569592 [21:24<469:54:08, 3.14s/it]
5%|▌ | 30469/569592 [21:25<370:23:24, 2.47s/it]
5%|▌ | 30469/569592 [21:25<370:23:24, 2.47s/it]
5%|▌ | 30470/569592 [21:26<302:40:24, 2.02s/it]
5%|▌ | 30470/569592 [21:26<302:40:24, 2.02s/it]
5%|▌ | 30471/569592 [21:26<252:51:42, 1.69s/it]
5%|▌ | 30471/569592 [21:26<252:51:42, 1.69s/it]
5%|▌ | 30472/569592 [21:27<218:42:13, 1.46s/it]
5%|▌ | 30472/569592 [21:27<218:42:13, 1.46s/it]
5%|▌ | 30473/569592 [21:28<196:56:52, 1.32s/it]
5%|▌ | 30473/569592 [21:28<196:56:52, 1.32s/it]
5%|▌ | 30474/569592 [21:29<179:36:47, 1.20s/it]
5%|▌ | 30474/569592 [21:29<179:36:47, 1.20s/it]
5%|▌ | 30475/569592 [21:32<250:41:01, 1.67s/it]
5%|▌ | 30475/569592 [21:32<250:41:01, 1.67s/it]
5%|▌ | 30476/569592 [21:33<217:56:11, 1.46s/it]
5%|▌ | 30476/569592 [21:33<217:56:11, 1.46s/it]
5%|▌ | 30477/569592 [21:38<361:56:57, 2.42s/it]
5%|▌ | 30477/569592 [21:38<361:56:57, 2.42s/it]
5%|▌ | 30478/569592 [21:39<302:57:28, 2.02s/it]
5%|▌ | 30478/569592 [21:39<302:57:28, 2.02s/it]
5%|▌ | 30479/569592 [21:41<333:26:52, 2.23s/it]
5%|▌ | 30479/569592 [21:41<333:26:52, 2.23s/it]
5%|▌ | 30480/569592 [21:43<281:57:18, 1.88s/it]
5%|▌ | 30480/569592 [21:43<281:57:18, 1.88s/it]
5%|▌ | 30481/569592 [21:48<425:15:12, 2.84s/it]
5%|▌ | 30481/569592 [21:48<425:15:12, 2.84s/it]
5%|▌ | 30482/569592 [21:49<340:54:37, 2.28s/it]
5%|▌ | 30482/569592 [21:49<340:54:37, 2.28s/it]
5%|▌ | 30483/569592 [21:52<375:04:27, 2.50s/it]
5%|▌ | 30483/569592 [21:52<375:04:27, 2.50s/it]
5%|▌ | 30484/569592 [21:53<305:23:14, 2.04s/it]
5%|▌ | 30484/569592 [21:53<305:23:14, 2.04s/it]
5%|▌ | 30485/569592 [21:57<425:24:39, 2.84s/it]
5%|▌ | 30485/569592 [21:57<425:24:39, 2.84s/it]
5%|▌ | 30486/569592 [22:00<418:53:14, 2.80s/it]
5%|▌ | 30486/569592 [22:00<418:53:14, 2.80s/it]
5%|▌ | 30487/569592 [22:02<389:08:04, 2.60s/it]
5%|▌ | 30487/569592 [22:02<389:08:04, 2.60s/it]
5%|▌ | 30488/569592 [22:03<315:33:21, 2.11s/it]
5%|▌ | 30488/569592 [22:03<315:33:21, 2.11s/it]
5%|▌ | 30489/569592 [22:07<401:21:59, 2.68s/it]
5%|▌ | 30489/569592 [22:07<401:21:59, 2.68s/it]
5%|▌ | 30490/569592 [22:09<361:58:00, 2.42s/it]
5%|▌ | 30490/569592 [22:09<361:58:00, 2.42s/it]
5%|▌ | 30491/569592 [22:12<397:35:50, 2.66s/it]
5%|▌ | 30491/569592 [22:12<397:35:50, 2.66s/it]
5%|▌ | 30492/569592 [22:13<323:46:43, 2.16s/it]
5%|▌ | 30492/569592 [22:13<323:46:43, 2.16s/it]
5%|▌ | 30493/569592 [22:17<407:47:56, 2.72s/it]
5%|▌ | 30493/569592 [22:17<407:47:56, 2.72s/it]
5%|▌ | 30494/569592 [22:19<390:14:46, 2.61s/it]
5%|▌ | 30494/569592 [22:19<390:14:46, 2.61s/it]
5%|▌ | 30495/569592 [22:23<413:16:16, 2.76s/it]
5%|▌ | 30495/569592 [22:23<413:16:16, 2.76s/it]
5%|▌ | 30496/569592 [22:24<334:22:30, 2.23s/it]
5%|▌ | 30496/569592 [22:24<334:22:30, 2.23s/it]
5%|▌ | 30497/569592 [22:29<463:35:32, 3.10s/it]
5%|▌ | 30497/569592 [22:29<463:35:32, 3.10s/it]
5%|▌ | 30498/569592 [22:30<367:53:37, 2.46s/it]
5%|▌ | 30498/569592 [22:30<367:53:37, 2.46s/it]
5%|▌ | 30499/569592 [22:33<391:14:23, 2.61s/it]
5%|▌ | 30499/569592 [22:33<391:14:23, 2.61s/it]
5%|▌ | 30500/569592 [22:34<339:16:11, 2.27s/it]
5%|▌ | 30500/569592 [22:34<339:16:11, 2.27s/it]
5%|▌ | 30501/569592 [22:40<486:11:42, 3.25s/it]
5%|▌ | 30501/569592 [22:40<486:11:42, 3.25s/it]
5%|▌ | 30502/569592 [22:41<382:33:05, 2.55s/it]
5%|▌ | 30502/569592 [22:41<382:33:05, 2.55s/it]
5%|▌ | 30503/569592 [22:44<417:00:41, 2.78s/it]
5%|▌ | 30503/569592 [22:44<417:00:41, 2.7/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (98911692 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
8s/it]
5%|▌ | 30504/569592 [22:45<356:54:53, 2.38s/it]
5%|▌ | 30504/569592 [22:45<356:54:53, 2.38s/it]
5%|▌ | 30505/569592 [22:50<450:20:16, 3.01s/it]
5%|▌ | 30505/569592 [22:50<450:20:16, 3.01s/it]
5%|▌ | 30506/569592 [22:51<357:05:35, 2.38s/it]
5%|▌ | 30506/569592 [22:51<357:05:35, 2.38s/it]
5%|▌ | 30507/569592 [22:53<337:57:36, 2.26s/it]
5%|▌ | 30507/569592 [22:53<337:57:36, 2.26s/it]
5%|▌ | 30508/569592 [22:55<356:43:46, 2.38s/it]
5%|▌ | 30508/569592 [22:55<356:43:46, 2.38s/it]
5%|▌ | 30509/569592 [22:59<411:02:33, 2.74s/it]
5%|▌ | 30509/569592 [22:59<411:02:33, 2.74s/it]
5%|▌ | 30510/569592 [23:01<380:35:39, 2.54s/it]
5%|▌ | 30510/569592 [23:01<380:35:39, 2.54s/it]
5%|▌ | 30511/569592 [23:03<339:23:04, 2.27s/it]
5%|▌ | 30511/569592 [23:03<339:23:04, 2.27s/it]
5%|▌ | 30512/569592 [23:06<401:53:43, 2.68s/it]
5%|▌ | 30512/569592 [23:06<401:53:43, 2.68s/it]
5%|▌ | 30513/569592 [23:09<416:43:03, 2.78s/it]
5%|▌ | 30513/569592 [23:09<416:43:03, 2.78s/it]
5%|▌ | 30514/569592 [23:11<374:47:31, 2.50s/it]
5%|▌ | 30514/569592 [23:11<374:47:31, 2.50s/it]
5%|▌ | 30515/569592 [23:13<350:38:26, 2.34s/it]
5%|▌ | 30515/569592 [23:13<350:38:26, 2.34s/it]
5%|▌ | 30516/569592 [23:15<342:38:40, 2.29s/it]
5%|▌ | 30516/569592 [23:15<342:38:40, 2.29s/it]
5%|▌ | 30517/569592 [23:21<503:46:46, 3.36s/it]
5%|▌ | 30517/569592 [23:21<503:46:46, 3.36s/it]
5%|▌ | 30518/569592 [23:22<395:22:03, 2.64s/it]
5%|▌ | 30518/569592 [23:22<395:22:03, 2.64s/it]
5%|▌ | 30519/569592 [23:24<375:58:48, 2.51s/it]
5%|▌ | 30519/569592 [23:24<375:58:48, 2.51s/it]
5%|▌ | 30520/569592 [23:26<328:47:56, 2.20s/it]
5%|▌ | 30520/569592 [23:26<328:47:56, 2.20s/it]
5%|▌ | 30521/569592 [23:33<532:01:32, 3.55s/it]
5%|▌ | 30521/569592 [23:33<532:01:32, 3.55s/it]
5%|▌ | 30522/569592 [23:33<413:38:32, 2.76s/it]
5%|▌ | 30522/569592 [23:33<413:38:32, 2.76s/it]
5%|▌ | 30523/569592 [23:34<331:11:04, 2.21s/it]
5%|▌ | 30523/569592 [23:34<331:11:04, 2.21s/it]
5%|▌ | 30524/569592 [23:36<286:07:44, 1.91s/it]
5%|▌ | 30524/569592 [23:36<286:07:44, 1.91s/it]
5%|▌ | 30525/569592 [23:43<513:29:27, 3.43s/it]
5%|▌ | 30525/569592 [23:43<513:29:27, 3.43s/it]
5%|▌ | 30526/569592 [23:44<421:42:39, 2.82s/it]
5%|▌ | 30526/569592 [23:44<421:42:39, 2.82s/it]
5%|▌ | 30527/569592 [23:45<355:51:46, 2.38s/it]
5%|▌ | 30527/569592 [23:45<355:51:46, 2.38s/it]
5%|▌ | 30528/569592 [23:46<292:14:16, 1.95s/it]
5%|▌ | 30528/569592 [23:46<292:14:16, 1.95s/it]
5%|▌ | 30529/569592 [23:51<425:34:00, 2.84s/it]
5%|▌ | 30529/569592 [23:51<425:34:00, 2.84s/it]
5%|▌ | 30530/569592 [23:52<346:38:35, 2.31s/it]
5%|▌ | 30530/569592 [23:52<346:38:35, 2.31s/it]
5%|▌ | 30531/569592 [23:55<373:36:06, 2.50s/it]
5%|▌ | 30531/569592 [23:55<373:36:06, 2.50s/it]
5%|▌ | 30532/569592 [23:56<304:02:05, 2.03s/it]
5%|▌ | 30532/569592 [23:56<304:02:05, 2.03s/it]
5%|▌ | 30533/569592 [24:01<427:37:55, 2.86s/it]
5%|▌ | 30533/569592 [24:01<427:37:55, 2.86s/it]
5%|▌ | 30534/569592 [24:02<343:59:05, 2.30s/it]
5%|▌ | 30534/569592 [24:02<343:59:05, 2.30s/it]
5%|▌ | 30535/569592 [24:06<441:05:46, 2.95s/it]
5%|▌ | 30535/569592 [24:06<441:05:46, 2.95s/it]
5%|▌ | 30536/569592 [24:07<350:40:25, 2.34s/it]
5%|▌ | 30536/569592 [24:07<350:40:25, 2.34s/it]
5%|▌ | 30537/569592 [24:11<431:00:18, 2.88s/it]
5%|▌ /home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (105785470 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
| 30537/569592 [24:11<431:00:18, 2.88s/it]
5%|▌ | 30538/569592 [24:13<375:33:34, 2.51s/it]
5%|▌ | 30538/569592 [24:13<375:33:34, 2.51s/it]
5%|▌ | 30539/569592 [24:15<334:41:27, 2.24s/it]
5%|▌ | 30539/569592 [24:15<334:41:27, 2.24s/it]
5%|▌ | 30540/569592 [24:16<296:14:32, 1.98s/it]
5%|▌ | 30540/569592 [24:16<296:14:32, 1.98s/it]
5%|▌ | 30541/569592 [24:20<388:11:55, 2.59s/it]
5%|▌ | 30541/569592 [24:20<388:11:55, 2.59s/it]
5%|▌ | 30542/569592 [24:22<355:24:52, 2.37s/it]
5%|▌ | 30542/569592 [24:22<355:24:52, 2.37s/it]
5%|▌ | 30543/569592 [24:26<438:17:55, 2.93s/it]
5%|▌ | 30543/569592 [24:26<438:17:55, 2.93s/it]
5%|▌ | 30544/569592 [24:27<348:49:21, 2.33s/it]
5%|▌ | 30544/569592 [24:27<348:49:21, 2.33s/it]
5%|▌ | 30545/569592 [24:31<418:48:57, 2.80s/it]
5%|▌ | 30545/569592 [24:31<418:48:57, 2.80s/it]
5%|▌ | 30546/569592 [24:33<377:52:02, 2.52s/it]
5%|▌ | 30546/569592 [24:33<377:52:02, 2.52s/it]
5%|▌ | 30547/569592 [24:35<343:32:05, 2.29s/it]
5%|▌ | 30547/569592 [24:35<343:32:05, 2.29s/it]
5%|▌ | 30548/569592 [24:36<283:12:15, 1.89s/it]
5%|▌ | 30548/569592 [24:36<283:12:15, 1.89s/it]
5%|▌ | 30549/569592 [24:41<453:05:06, 3.03s/it]
5%|▌ | 30549/569592 [24:41<453:05:06, 3.03s/it]
5%|▌ | 30550/569592 [24:42<361:16:04, 2.41s/it]
5%|▌ | 30550/569592 [24:42<361:16:04, 2.41s/it]
5%|▌ | 30551/569592 [24:46<409:49:57, 2.74s/it]
5%|▌ | 30551/569592 [24:46<409:49:57, 2.74s/it]
5%|▌ | 30552/569592 [24:47<334:31:00, 2.23s/it]
5%|▌ | 30552/569592 [24:47<334:31:00, 2.23s/it]
5%|▌ | 30553/569592 [24:51<433:01:00, 2.89s/it]
5%|▌ | 30553/569592 [24:51<433:01:00, 2.89s/it]
5%|▌ | 30554/569592 [24:52<346:34:49, 2.31s/it]
/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (98911692 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
5%|▌ | 30554/569592 [24:52<346:34:49, 2.31s/it]
5%|▌ | 30555/569592 [24:55<370:03:45, 2.47s/it]
5%|▌ | 30555/569592 [24:55<370:03:45, 2.47s/it]
5%|▌ | 30556/569592 [24:57<327:43:56, 2.19s/it]
5%|▌ | 30556/569592 [24:57<327:43:56, 2.19s/it]
5%|▌ | 30557/569592 [25:01<437:48:53, 2.92s/it]
5%|▌ | 30557/569592 [25:01<437:48:53, 2.92s/it]
5%|▌ | 30558/569592 [25:02<349:53:34, 2.34s/it]
5%|▌ | 30558/569592 [25:02<349:53:34, 2.34s/it]
5%|▌ | 30559/569592 [25:05<373:23:39, 2.49s/it]
5%|▌ | 30559/569592 [25:05<373:23:39, 2.49s/it]
5%|▌ | 30560/569592 [25:06<328:24:17, 2.19s/it]
5%|▌ | 30560/569592 [25:07<328:24:17, 2.19s/it]
5%|▌ | 30561/569592 [25:14<567:48:43, 3.79s/it]
5%|▌ | 30561/569592 [25:14<567:48:43, 3.79s/it]
5%|▌ | 30562/569592 [25:19<610:37:24, 4.08s/it]
5%|▌ | 30562/569592 [25:19<610:37:24, 4.08s/it]
5%|▌ | 30563/569592 [25:23<639:13:25, 4.27s/it]
5%|▌ | 30563/569592 [25:23<639:13:25, 4.27s/it]
5%|▌ | 30564/569592 [25:28<672:25:34, 4.49s/it]
5%|▌ | 30564/569592 [25:28<672:25:34, 4.49s/it]
5%|▌ | 30565/569592 [25:32<608:33:50, 4.06s/it]
5%|▌ | 30565/569592 [25:32<608:33:50, 4.06s/it]
5%|▌ | 30566/569592 [25:36<635:39:04, 4.25s/it]
5%|▌ | 30566/569592 [25:36<635:39:04, 4.25s/it]
5%|▌ | 30567/569592 [25:39<590:38:22, 3.94s/it]
5%|▌ | 30567/569592 [25:39<590:38:22, 3.94s/it]
5%|▌ | 30568/569592 [25:44<620:20:45, 4.14s/it]
5%|▌ | 30568/569592 [25:44<620:20:45, 4.14s/it]
5%|▌ | 30569/569592 [25:48<601:49:42, 4.02s/it]
5%|▌ | 30569/569592 [25:48<601:49:42, 4.02s/it]
5%|▌ | 30570/569592 [25:53<644:04:04, 4.30s/it]
5%|▌ | 30570/569592 [25:53<644:04:04, 4.30s/it]
5%|▌ | 30571/569592 [25:58<668:06:35, 4.46s/it]
5%|▌ | 30571/569592 [25:58<668:06:35, 4.46s/it]
5%|▌ | 30572/569592 [26:02<675:25:05, 4.51s/it]
5%|▌ | 30572/569592 [26:02<675:25:05, 4.51s/it]
5%|▌ | 30573/569592 [26:05<609:10:49, 4.07s/it]
5%|▌ | 30573/569592 [26:05<609:10:49, 4.07s/it]
5%|▌ | 30574/569592 [26:10<648:09:15, 4.33s/it]
5%|▌ | 30574/569592 [26:10<648:09:15, 4.33s/it]
5%|▌ | 30575/569592 [26:13<599:22:12, 4.00s/it]
5%|▌ | 30575/569592 [26:13<599:22:12, 4.00s/it]
5%|▌ | 30576/569592 [26:18<643:38:55, 4.30s/it]
5%|▌ | 30576/569592 [26:18<643:38:55, 4.30s/it]
5%|▌ | 30577/569592 [26:21<586:27:56, 3.92s/it]
5%|▌ | 30577/569592 [26:21<586:27:56, 3.92s/it]
5%|▌ | 30578/569592 [26:25<568:52:36, 3.80s/it]
5%|▌ | 30578/569592 [26:25<568:52:36, 3.80s/it]
5%|▌ | 30579/569592 [26:28<549:13:12, 3.67s/it]
5%|▌ | 30579/569592 [26:28<549:13:12, 3.67s/it]
5%|▌ | 30580/569592 [26:29<425:45:17, 2.84s/it]
5%|▌ | 30580/569592 [26:29<425:45:17, 2.84s/it]
5%|▌ | 30581/569592 [26:34<514:38:03, 3.44s/it]
5%|▌ | 30581/569592 [26:34<514:38:03, 3.44s/it]
5%|▌ | 30582/569592 [26:37<508:59:07, 3.40s/it]
5%|▌ | 30582/569592 [26:37<508:59:07, 3.40s/it]
5%|▌ | 30583/569592 [26:43<588:26:20, 3.93s/it]
5%|▌ | 30583/569592 [26:43<588:26:20, 3.93s/it]
5%|▌ | 30584/569592 [26:46<544:13:40, 3.63s/it]
5%|▌ | 30584/569592 [26:46<544:13:40, 3.63s/it]
5%|▌ | 30585/569592 [26:49<522:18:56, 3.49s/it]
5%|▌ | 30585/569592 [26:49<522:18:56, 3.49s/it]
5%|▌ | 30586/569592 [26:50<407:53:51, 2.72s/it]
5%|▌ | 30586/569592 [26:50<407:53:51, 2.72s/it]
5%|▌ | 30587/569592 [26:51<327:39:08, 2.19s/it]
5%|▌ | 30587/569592 [26:51<327:39:08, 2.19s/it]
5%|▌ | 30588/569592 [26:51<272:10:08, 1.82s/it]
5%|▌ | 30588/569592 [26:52<272:10:08, 1.82s/it]
5%|▌ | 30589/569592 [26:52<232:29:38, 1.55s/it]
5%|▌ | 30589/569592 [26:52<232:29:38, 1.55s/it]
5%|▌ | 30590/569592 [26:53<205:48:48, 1.37s/it]
5%|▌ | 30590/569592 [26:53<205:48:48, 1.37s/it]
5%|▌ | 30591/569592 [26:54<188:52:23, 1.26s/it]
5%|▌ | 30591/569592 [26:54<188:52:23, 1.26s/it]
5%|▌ | 30592/569592 [26:55<175:33:22, 1.17s/it]
5%|▌ | 30592/569592 [26:55<175:33:22, 1.17s/it]
5%|▌ | 30593/569592 [26:58<258:40:13, 1.73s/it]
5%|▌ | 30593/569592 [26:58<258:40:13, 1.73s/i/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (100920000 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
t]
5%|▌ | 30594/569592 [27:03<379:13:53, 2.53s/it]
5%|▌ | 30594/569592 [27:03<379:13:53, 2.53s/it]
5%|▌ | 30595/569592 [27:04<308:52:01, 2.06s/it]
5%|▌ | 30595/569592 [27:04<308:52:01, 2.06s/it]
5%|▌ | 30596/569592 [27:05<263:35:21, 1.76s/it]
5%|▌ | 30596/569592 [27:05<263:35:21, 1.76s/it]
5%|▌ | 30597/569592 [27:09<382:10:15, 2.55s/it]
5%|▌ | 30597/569592 [27:09<382:10:15, 2.55s/it]
5%|▌ | 30598/569592 [27:13<442:41:05, 2.96s/it]
5%|▌ | 30598/569592 [27:13<442:41:05, 2.96s/it]
5%|▌ | 30599/569592 [27:14<354:45:07, 2.37s/it]
5%|▌ | 30599/569592 [27:14<354:45:07, 2.37s/it]
5%|▌ | 30600/569592 [27:16<313:02:24, 2.09s/it]
5%|▌ | 30600/569592 [27:16<313:02:24, 2.09s/it]
5%|▌ | 30601/569592 [27:19<374:15:13, 2.50s/it]
5%|▌ | 30601/569592 [27:19<374:15:13, 2.50s/it]
5%|▌ | 30602/569592 [27:23<419:40:59, 2.80s/it]
5%|▌ | 30602/569592 [27:23<419:40:59, 2.80s/it]
5%|▌ | 30603/569592 [27:24<382:34:20, 2.56s/it]
5%|▌ | 30603/569592 [27:25<382:34:20, 2.56s/it]
5%|▌ | 30604/569592 [27:26<327:46:45, 2.19s/it]
5%|▌ | 30604/569592 [27:26<327:46:45, 2.19s/it]
5%|▌ | 30605/569592 [27:29<385:12:54, 2.57s/it]
5%|▌ | 30605/569592 [27:29<385:12:54, 2.57s/it]
5%|▌ | 30606/569592 [27:33<435:44:49, 2.91s/it]
5%|▌ | 30606/569592 [27:33<435:44:49, 2.91s/it]
5%|▌ | 30607/569592 [27:34<350:55:19, 2.34s/it]
5%|▌ | 30607/569592 [27:34<350:55:19, 2.34s/it]
5%|▌ | 30608/569592 [27:36<330:55:02, 2.21s/it]
5%|▌ | 30608/569592 [27:36<330:55:02, 2.21s/it]
5%|▌ | 30609/569592 [27:40<404:08:05, 2.70s/it]
5%|▌ | 30609/569592 [27:40<404:08:05, 2.70s/it]
5%|▌ | 30610/569592 [27:44<460:34:16, 3.08s/it]
5%|▌ | 30610/569592 [27:44<460:34:16, 3.08s/it]
5%|▌ | 30611/569592 [27:45<400:23:45, 2.67s/it]
5%|▌ | 30611/569592 [27:45<400:23:45, 2.67s/it]
5%|▌ | 30612/569592 [27:46<324:28:49, 2.17s/it]
5%|▌ | 30612/569592 [27:46<324:28:49, 2.17s/it]
5%|▌ | 30613/569592 [27:50<377:22:24, 2.52s/it]
5%|▌ | 30613/569592 [27:50<377:22:24, 2.52s/it]
5%|▌ | 30614/569592 [27:54<449:55:43, 3.01s/it]
5%|▌ | 30614/569592 [27:54<449:55:43, 3.01s/it]
5%|▌ | 30615/569592 [27:55<373:51:16, 2.50s/it]
5%|▌ | 30615/569592 [27:55<373:51:16, 2.50s/it]
5%|▌ | 30616/569592 [27:56<312:27:26, 2.09s/it]
5%|▌ | 30616/569592 [27:56<312:27:26, 2.09s/it]
5%|▌ | 30617/569592 [28:02<451:34:13, 3.02s/it]
5%|▌ | 30617/569592 [28:02<451:34:13, 3.02s/it]
5%|▌ | 30618/569592 [28:04<421:45:50, 2.82s/it]
5%|▌ | 30618/569592 [28:04<421:45:50, 2.82s/it]
5%|▌ | 30619/569592 [28:05<356:53:16, 2.38s/it]
5%|▌ | 30619/569592 [28:05<356:53:16, 2.38s/it]
5%|▌ | 30620/569592 [28:06<291:50:41, 1.95s/it]
5%|▌ | 30620/569592 [28:06<291:50:41, 1.95s/it]
5%|▌ | 30621/569592 [28:12<448:29:39, 3.00s/it]
5%|▌ | 30621/569592 [28:12<448:29:39, 3.00s/it]
5%|▌ | 30622/569592 [28:13<395:18:53, 2.64s/it]
5%|▌ | 30622/569592 [28:13<395:18:53, 2.64s/it]
5%|▌ | 30623/569592 [28:15<352:07:56, 2.35s/it]
5%|▌ | 30623/569592 [28:15<352:07:56, 2.35s/it]
5%|▌ | 30624/569592 [28:17<312:08:27, 2.08s/it]
5%|▌ | 30624/569592 [28:17<312:08:27, 2.08s/it]
5%|▌ | 30625/569592 [28:24<534:59:25, 3.57s/it]
5%|▌ | 30625/569592 [28:24<534:59:25, 3.57s/it]
5%|▌ | 30626/569592 [28:25<420:05:16, 2.81s/it]
5%|▌ | 30626/569592 [28:25<420:05:16, 2.81s/it]
5%|▌ | 30627/569592 [28:26<345:13:17, 2.31s/it]
5%|▌ | 30627/569592 [28:26<345:13:17, 2.31s/it]
5%|▌ | 30628/569592 [28:27<291:23:18, 1.95s/it]
5%|▌ | 30628/569592 [28:27<291:23:18, 1.95s/it]
5%|▌ | 30629/569592 [28:33<476:27:54, 3.18s/it]
5%|▌ | 30629/569592 [28:33<476:27:54, 3.18s/it]
5%|▌ | 30630/569592 [28:35<430:48:41, 2.88s/it]
5%|▌ | 30630/569592 [28:35<430:48:41, 2.88s/it]
5%|▌ | 30631/569592 [28:36<344:23:44, 2.30s/it]
5%|▌ | 30631/569592 [28:36<344:23:44, 2.30s/it]
5%|▌ | 30632/569592 [28:37<284:12:08, 1.90s/it]
5%|▌ | 30632/569592 [28:37<284:12:08, 1.90s/it]
5%|▌ | 30633/569592 [28:44<526:45:08, 3.52s/it]
5%|▌ | 30633/569592 [28:44<526:45:08, 3.52s/it]
5%|▌ | 30634/569592 [28:47<477:11:31, 3.19s/it]
5%|▌ | 30634/569592 [28:47<477:11:31, 3.19s/it]
5%|▌ | 30635/569592 [28:48<376:04:17, 2.51s/it]
5%|▌ | 30635/569592 [28:48<376:04:17, 2.51s/it]
5%|▌ | 30636/569592 [28:49<305:23:15, 2.04s/it]
5%|▌ | 30636/569592 [28:49<305:23:15, 2.04s/it]
5%|▌ | 30637/569592 [28:54<454:18:02, 3.03s/it]
5%|▌ | 30637/569592 [28:54<454:18:02, 3.03s/it]
5%|▌ | 30638/569592 [28:58<496:46:00, 3.32s/it]
5%|▌ | 30638/569592 [28:58<496:46:00, 3.32s/it]
5%|▌ | 30639/569592 [28:59<392:14:30, 2.62s/it]
5%|▌ | 30639/569592 [28:59<392:14:30, 2.62s/it]
5%|▌ | 30640/569592 [29:00<317:21:58, 2.12s/it]
5%|▌ | 30640/569592 [29:00<317:21:58, 2.12s/it]
5%|▌ | 30641/569592 [29:04<391:02:53, 2.61s/it]
5%|▌ | 30641/569592 [29:04<391:02:53, 2.61s/it]
5%|▌ | 30642/569592 [29:07<420:40:45, 2.81s/it]
5%|▌ | 30642/569592 [29:07<420:40:45, 2.81s/it]
5%|▌ | 30643/569592 [29:08<338:45:40, 2.26s/it]
5%|▌ | 30643/569592 [29:08<338:45:40, 2.26s/it]
5%|▌ | 30644/569592 [29:09<284:34:20, 1.90s/it]
5%|▌ | 30644/569592 [29:09<284:34:20, 1.90s/it]
5%|▌ | 30645/569592 [29:14<407:07:06, 2.72s/it]
5%|▌ | 30645/569592 [29:14<407:07:06, 2.72s/it]
5%|▌ | 30646/569592 [29:19<518:13:26, 3.46s/it]
5%|▌ | 30646/569592 [29:19<518:13:26, 3.46s/it]
5%|▌ | 30647/569592 [29:20<403:33:52, 2.70s/it]
5%|▌ | 30647/569592 [29:20<403:33:52, 2.70s/it]
5%|▌ | 30648/569592 [29:21<324:17:22, 2.17s/it]
5%|▌ | 30648/569592 [29:21<324:17:22, 2.17s/it]
5%|▌ | 30649/569592 [29:22<297:58:40, 1.99s/it]
5%|▌ | 30649/569592 [29:22<297:58:40, 1.99s/it]
5%|▌ | 30650/569592 [29:29<513:40:29, 3.43s/it]
5%|▌ | 30650/569592 [29:29<513:40:29, 3.43s/it]
5%|▌ | 30651/569592 [29:30<401:00:09, 2.68s/it]
5%|▌ | 30651/569592 [29:30<401:00:09, 2.68s/it]
5%|▌ | 30652/569592 [29:31<322:18:40, 2.15s/it]
5%|▌ | 30652/569592 [29:31<322:18:40, 2.15s/it]
5%|▌ | 30653/569592 [29:34<351:43:18, 2.35s/it]
5%|▌ | 30653/569592 [29:34<351:43:18, 2.35s/it]
5%|▌ | 30654/569592 [29:38<446:24:40, 2.98s/it]
5%|▌ | 30654/569592 [29:38<446:24:40, 2.98s/it]
5%|▌ | 30655/569592 [29:39<355:55:10, 2.38s/it]
5%|▌ | 30655/569592 [29:39<355:55:10, 2.38s/it]
5%|▌ | 30656/569592 [29:40<291:29:07, 1.95s/it]
5%|▌ | 30656/569592 [29:40<291:29:07, 1.95s/it]
5%|▌ | 30657/569592 [29:45<423:34:07, 2.83s/it]
5%|▌ | 30657/569592 [29:45<423:34:07, 2.83s/it]
5%|▌ | 30658/569592 [29:49<481:55:11, 3.22s/it]
5%|▌ | 30658/569592 [29:49<481:55:11, 3.22s/it]
5%|▌ | 30659/569592 [29:50<379:15:41, 2.53s/it]
5%|▌ | 30659/569592 [29:50<379:15:41, 2.53s/it]
5%|▌ | 30660/569592 [29:51<307:33:04, 2.05s/it]
5%|▌ | 30660/569592 [29:51<307:33:04, 2.05s/it]
5%|▌ | 30661/569592 [29:55<385:58:43, 2.58s/it]
5%|▌ | 30661/569592 [29:55<385:58:43, 2.58s/it]
5%|▌ | 30662/569592 [29:58<405:11:09, 2.71s/it]
5%|▌ | 30662/569592 [29:58<405:11:09, 2.71s/it]
5%|▌ | 30663/569592 [29:59<326:34:16, 2.18s/it]
5%|▌ | 30663/569592 [29:59<326:34:16, 2.18s/it]
5%|▌ | 30664/569592 [30:00<271:41:15, 1.81s/it]
5%|▌ | 30664/569592 [30:00<271:41:15, 1.81s/it]
5%|▌ | 30665/569592 [30:05<425:46:14, 2.84s/it]
5%|▌ | 30665/569592 [30:05<425:46:14, 2.84s/it]
5%|▌ | 30666/569592 [30:09<490:48:41, 3.28s/it]
5%|▌ | 30666/569592 [30:10<490:48:41, 3.28s/it]
5%|▌ | 30667/569592 [30:10<397:39:18, 2.66s/it]
5%|▌ | 30667/569592 [30:10<397:39:18, 2.66s/it]
5%|▌ | 30668/569592 [30:11<322:46:05, 2.16s/it]
5%|▌ | 30668/569592 [30:11<322:46:05, 2.16s/it]
5%|▌ | 30669/569592 [30:14<345:06:15, 2.31s/it]
5%|▌ | 30669/569592 [30:14<345:06:15, 2.31s/it]
5%|▌ | 30670/569592 [30:18<411:12:21, 2.75s/it]
5%|▌ | 30670/569592 [30:18<411:12:21, 2.75s/it]
5%|▌ | 30671/569592 [30:19<334:26:36, 2.23s/it]
5%|▌ | 30671/569592 [30:19<334:26:36, 2.23s/it]
5%|▌ | 30672/569592 [30:20<281:57:44, 1.88s/it]
5%|▌ | 30672/569592 [30:20<281:57:44, 1.88s/it]
5%|▌ | 30673/569592 [30:25<433:37:39, 2.90s/it]
5%|▌ | 30673/569592 [30:25<433:37:39, 2.90s/it]
5%|▌ | 30674/569592 [30:30<505:42:17, 3.38s/it]
5%|▌ | 30674/569592 [30:30<505:42:17, 3.38s/it]
5%|▌ | 30675/569592 [30:33<487:46:40, 3.26s/it]
5%|▌ | 30675/569592 [30:33<487:46:40, 3.26s/it]
5%|▌ | 30676/569592 [30:37<539:46:16, 3.61s/it]
5%|▌ | 30676/569592 [30:37<539:46:16, 3.61s/it]
5%|▌ | 30677/569592 [30:41<560:19:24, 3.74s/it]
5%|▌ | 30677/569592 [30:41<560:19:24, 3.74s/it]
5%|▌ | 30678/569592 [30:46<612:20:15, 4.09s/it]
5%|▌ | 30678/569592 [30:46<612:20:15, 4.09s/it]
5%|▌ | 30679/569592 [30:49<559:06:19, 3.73s/it]
5%|▌ | 30679/569592 [30:49<559:06:19, 3.73s/it]
5%|▌ | 30680/569592 [30:53<568:09:21, 3.80s/it]
5%|▌ | 30680/569592 [30:53<568:09:21, 3.80s/it]
5%|▌ | 30681/569592 [30:56<544:17:12, 3.64s/it]
5%|▌ | 30681/569592 [30:56<544:17:12, 3.64s/it]
5%|▌ | 30682/569592 [31:01<610:15:56, 4.08s/it]
5%|▌ | 30682/569592 [31:01<610:15:56, 4.08s/it]
5%|▌ | 30683/569592 [31:05<601:34:55, 4.02s/it]
5%|▌ | 30683/569592 [31:05<601:34:55, 4.02s/it]
5%|▌ | 30684/569592 [31:08<564:58:05, 3.77s/it]
5%|▌ | 30684/569592 [31:08<564:58:05, 3.77s/it]
5%|▌ | 30685/569592 [31:13<609:05:12, 4.07s/it]
5%|▌ | 30685/569592 [31:13<609:05:12, 4.07s/it]
5%|▌ | 30686/569592 [31:17<582:05:13, 3.89s/it]
5%|▌ | 30686/569592 [31:17<582:05:13, 3.89s/it]
5%|▌ | 30687/569592 [31:21<625:46:19, 4.18s/it]
5%|▌ | 30687/569592 [31:21<625:46:19, 4.18s/it]
5%|▌ | 30688/569592 [31:26<650:42:47, 4.35s/it]
5%|▌ | 30688/569592 [31:26<650:42:47, 4.35s/it]
5%|▌ | 30689/569592 [31:31<678:04:08, 4.53s/it]
5%|▌ | 30689/569592 [31:31<678:04:08, 4.53s/it]
5%|▌ | 30690/569592 [31:35<646:20:10, 4.32s/it]
5%|▌ | 30690/569592 [31:35<646:20:10, 4.32s/it]
5%|▌ | 30691/569592 [31:39<649:56:25, 4.34s/it]
5%|▌ | 30691/569592 [31:39<649:56:25, 4.34s/it]
5%|▌ | 30692/569592 [31:43<598:00:58, 3.99s/it]
5%|▌ | 30692/569592 [31:43<598:00:58, 3.99s/it]
5%|▌ | 30693/569592 [31:48<652:00:55, 4.36s/it]
5%|▌ | 30693/569592 [31:48<652:00:55, 4.36s/it]
5%|▌ | 30694/569592 [31:53<673:37:57, 4.50s/it]
5%|▌ | 30694/569592 [31:53<673:37:57, 4.50s/it]
5%|▌ | 30695/569592 [31:55<603:46:52, 4.03s/it]
5%|▌ | 30695/569592 [31:56<603:46:52, 4.03s/it]
5%|▌ | 30696/569592 [31:59<584:56:36, 3.91s/it]
5%|▌ | 30696/569592 [31:59<584:56:36, 3.91s/it]
5%|▌ | 30697/569592 [32:00<450:32:22, 3.01s/it]
5%|▌ | 30697/569592 [32:00<450:32:22, 3.01s/it]
5%|▌ | 30698/569592 [32:04<485:32:08, 3.24s/it]
5%|▌ | 30698/569592 [32:04<485:32:08, 3.24s/it]
5%|▌ | 30699/569592 [32:09<566:40:51, 3.79s/it]
5%|▌ | 30699/569592 [32:09<566:40:51, 3.79s/it]
5%|▌ | 30700/569592 [32:13<588:26:37, 3.93s/it]
5%|▌ | 30700/569592 [32:13<588:26:37, 3.93s/it]
5%|▌ | 30701/569592 [32:18<642:20:08, 4.29s/it]
5%|▌ | 30701/569592 [32:18<642:20:08, 4.29s/it]
5%|▌ | 30702/569592 [32:22<634:45:00, 4.24s/it]
5%|▌ | 30702/569592 [32:22<634:45:00, 4.24s/it]
5%|▌ | 30703/569592 [32:23<485:24:52, 3.24s/it]
5%|▌ | 30703/569592 [32:23<485:24:52, 3.24s/it]
5%|▌ | 30704/569592 [32:24<384:02:42, 2.57s/it]
5%|▌ | 30704/569592 [32:24<384:02:42, 2.57s/it]
5%|▌ | 30705/569592 [32:25<313:31:58, 2.09s/it]
5%|▌ | 30705/569592 [32:25<313:31:58, 2.09s/it]
5%|▌ | 30706/569592 [32:26<261:56:25, 1.75s/it]
5%|▌ | 30706/569592 [32:26<261:56:25, 1.75s/it]
5%|▌ | 30707/569592 [32:27<225:59:30, 1.51s/it]
5%|▌ | 30707/569592 [32:27<225:59:30, 1.51s/it]
5%|▌ | 30708/569592 [32:28<201:12:47, 1.34s/it]
5%|▌ | 30708/569592 [32:28<201:12:47, 1.34s/it]
5%|▌ | 30709/569592 [32:29<182:10:43, 1.22s/it]
5%|▌ | 30709/569592 [32:29<182:10:43, 1.22s/it]
5%|▌ | 30710/569592 [32:31<217:22:30, 1.45s/it]
5%|▌ | 30710/569592 [32:31<217:22:30, 1.45s/it]
5%|▌ | 30711/569592 [32:35<344:53:09, 2.30s/it]
5%|▌ | 30711/569592 [32:35<344:53:09, 2.30s/it]
5%|▌ | 30712/569592 [32:37<312:59:46, 2.09s/it]
5%|▌ | 30712/569592 [32:37<312:59:46, 2.09s/it]
5%|▌ | 30713/569592 [32:38<279:55:45, 1.87s/it]
5%|▌ | 30713/569592 [32:38<279:55:45, 1.87s/it]
5%|▌ | 30714/569592 [32:41<332:19:00, 2.22s/it]
5%|▌ | 30714/569592 [32:41<332:19:00, 2.22s/it]
5%|▌ | 30715/569592 [32:47<468:24:54, 3.13s/it]
5%|▌ | 30715/569592 [32:47<468:24:54, 3.13s/it]
5%|▌ | 30716/569592 [32:48<375:29:49, 2.51s/it]
5%|▌ | 30716/569592 [32:48<375:29:49, 2.51s/it]
5%|▌ | 30717/569592 [32:49<309:11:39, 2.07s/it]
5%|▌ | 30717/569592 [32:49<309:11:39, 2.07s/it]
5%|▌ | 30718/569592 [32:52<345:21:24, 2.31s/it]
5%|▌ | 30718/569592 [32:52<345:21:24, 2.31s/it]
5%|▌ | 30719/569592 [32:56<440:30:26, 2.94s/it]
5%|▌ | 30719/569592 [32:56<440:30:26, 2.94s/it]
5%|▌ | 30720/569592 [32:57<370:12:52, 2.47s/it]
5%|▌ | 30720/569592 [32:57<370:12:52, 2.47s/it]
5%|▌ | 30721/569592 [32:58<303:59:43, 2.03s/it]
5%|▌ | 30721/569592 [32:58<303:59:43, 2.03s/it]
5%|▌ | 30722/569592 [33:02<384:48:26, 2.57s/it]
5%|▌ | 30722/569592 [33:02<384:48:26, 2.57s/it]
5%|▌ | 30723/569592 [33:06<451:32:01, 3.02s/it]
5%|▌ | 30723/569592 [33:06<451:32:01, 3.02s/it]
5%|▌ | 30724/569592 [33:08<375:41:55, 2.51s/it]
5%|▌ | 30724/569592 [33:08<375:41:55, 2.51s/it]
5%|▌ | 30725/569592 [33:08<305:10:08, 2.04s/it]
5%|▌ | 30725/569592 [33:09<305:10:08, 2.04s/it]
5%|▌ | 30726/569592 [33:12<383:29:10, 2.56s/it]
5%|▌ | 30726/569592 [33:12<383:29:10, 2.56s/it]
5%|▌ | 30727/569592 [33:17<475:55:55, 3.18s/it]
5%|▌ | 30727/569592 [33:17<475:55:55, 3.18s/it]
5%|▌ | 30728/569592 [33:18<377:52:41, 2.52s/it]
5%|▌ | 30728/569592 [33:18<377:52:41, 2.52s/it]
5%|▌ | 30729/569592 [33:19<308:50:02, 2.06s/it]
5%|▌ | 30729/569592 [33:19<308:50:02, 2.06s/it]
5%|▌ | 30730/569592 [33:21<324:37:30, 2.17s/it]
5%|▌ | 30730/569592 [33:21<324:37:30, 2.17s/it]
5%|▌ | 30731/569592 [33:27<472:04:08, 3.15s/it]
5%|▌ | 30731/569592 [33:27<472:04:08, 3.15s/it]
5%|▌ | 30732/569592 [33:28<373:25:33, 2.49s/it]
5%|▌ | 30732/569592 [33:28<373:25:33, 2.49s/it]
5%|▌ | 30733/569592 [33:29<302:37:40, 2.02s/it]
5%|▌ | 30733/569592 [33:29<302:37:40, 2.02s/it]
5%|▌ | 30734/569592 [33:33<399:04:10, 2.67s/it]
5%|▌ | 30734/569592 [33:33<399:04:10, 2.67s/it]
5%|▌ | 30735/569592 [33:37<475:15:52, 3.18s/it]
5%|▌ | 30735/569592 [33:37<475:15:52, 3.18s/it]
5%|▌ | 30736/569592 [33:38<378:41:53, 2.53s/it]
5%|▌ | 30736/569592 [33:38<378:41:53, 2.53s/it]
5%|▌ | 30737/569592 [33:39<306:55:13, 2.05s/it]
5%|▌ | 30737/569592 [33:39<306:55:13, 2.05s/it]
5%|▌ | 30738/569592 [33:43<375:15:56, 2.51s/it]
5%|▌ | 30738/569592 [33:43<375:15:56, 2.51s/it]
5%|▌ | 30739/569592 [33:48<489:30:10, 3.27s/it]
5%|▌ | 30739/569592 [33:48<489:30:10, 3.27s/it]
5%|▌ | 30740/569592 [33:49<396:37:33, 2.65s/it]
5%|▌ | 30740/569592 [33:49<396:37:33, 2.65s/it]
5%|▌ | 30741/569592 [33:50<331:48:15, 2.22s/it]
5%|▌ | 30741/569592 [33:50<331:48:15, 2.22s/it]
5%|▌ | 30742/569592 [33:53<361:45:15, 2.42s/it]
5%|▌ | 30742/569592 [33:53<361:45:15, 2.42s/it]
5%|▌ | 30743/569592 [33:58<469:01:52, 3.13s/it]
5%|▌ | 30743/569592 [33:58<469:01:52, 3.13s/it]
5%|▌ | 30744/569592 [33:59<374:52:13, 2.50s/it]
5%|▌ | 30744/569592 [33:59<374:52:13, 2.50s/it]
5%|▌ | 30745/569592 [34:00<318:23:29, 2.13s/it]
5%|▌ | 30745/569592 [34:00<318/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (90481664 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
:23:29, 2.13s/it]
5%|▌ | 30746/569592 [34:03<352:55:18, 2.36s/it]
5%|▌ | 30746/569592 [34:03<352:55:18, 2.36s/it]
5%|▌ | 30747/569592 [34:08<470:55:44, 3.15s/it]
5%|▌ | 30747/569592 [34:08<470:55:44, 3.15s/it]
5%|▌ | 30748/569592 [34:10<434:49:04, 2.91s/it]
5%|▌ | 30748/569592 [34:10<434:49:04, 2.91s/it]
5%|▌ | 30749/569592 [34:11<351:34:59, 2.35s/it]
5%|▌ | 30749/569592 [34:11<351:34:59, 2.35s/it]
5%|▌ | 30750/569592 [34:13<316:44:00, 2.12s/it]
5%|▌ | 30750/569592 [34:13<316:44:00, 2.12s/it]
5%|▌ | 30751/569592 [34:18<427:35:05, 2.86s/it]
5%|▌ | 30751/569592 [34:18<427:35:05, 2.86s/it]
5%|▌ | 30752/569592 [34:21<447:28:44, 2.99s/it]
5%|▌ | 30752/569592 [34:21<447:28:44, 2.99s/it]
5%|▌ | 30753/569592 [34:22<354:32:08, 2.37s/it]
5%|▌ | 30753/569592 [34:22<354:32:08, 2.37s/it]
5%|▌ | 30754/569592 [34:24<354:25:32, 2.37s/it]
5%|▌ | 30754/569592 [34:24<354:25:32, 2.37s/it]
5%|▌ | 30755/569592 [34:28<399:27:52, 2.67s/it]
5%|▌ | 30755/569592 [34:28<399:27:52, 2.67s/it]
5%|▌ | 30756/569592 [34:31<416:24:09, 2.78s/it]
5%|▌ | 30756/569592 [34:31<416:24:09, 2.78s/it]
5%|▌ | 30757/569592 [34:31<333:37:26, 2.23s/it]
5%|▌ | 30757/569592 [34:32<333:37:26, 2.23s/it]
5%|▌ | 30758/569592 [34:33<310:56:04, 2.08s/it]
5%|▌ | 30758/569592 [34:33<310:56:04, 2.08s/it]
5%|▌ | 30759/569592 [34:39<471:51:27, 3.15s/it]
5%|▌ | 30759/569592 [34:39<471:51:27, 3.15s/it]
5%|▌ | 30760/569592 [34:40<373:32:45, 2.50s/it]
5%|▌ | 30760/569592 [34:40<373:32:45, 2.50s/it]
5%|▌ | 30761/569592 [34:41<304:34:08, 2.03s/it]
5%|▌ | 30761/569592 [34:41<304:34:08, 2.03s/it]
5%|▌ | 30762/569592 [34:43<315:02:52, 2.10s/it]
5%|▌ | 3/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (99046487 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
0762/569592 [34:43<315:02:52, 2.10s/it]
5%|▌ | 30763/569592 [34:48<447:35:12, 2.99s/it]
5%|▌ | 30763/569592 [34:48<447:35:12, 2.99s/it]
5%|▌ | 30764/569592 [34:50<403:53:53, 2.70s/it]
5%|▌ | 30764/569592 [34:50<403:53:53, 2.70s/it]
5%|▌ | 30765/569592 [34:51<324:06:35, 2.17s/it]
5%|▌ | 30765/569592 [34:51<324:06:35, 2.17s/it]
5%|▌ | 30766/569592 [34:53<332:31:50, 2.22s/it]
5%|▌ | 30766/569592 [34:53<332:31:50, 2.22s/it]
5%|▌ | 30767/569592 [34:59<461:10:20, 3.08s/it]
5%|▌ | 30767/569592 [34:59<461:10:20, 3.08s/it]
5%|▌ | 30768/569592 [35:00<382:43:10, 2.56s/it]
5%|▌ | 30768/569592 [35:00<382:43:10, 2.56s/it]
5%|▌ | 30769/569592 [35:01<310:52:52, 2.08s/it]
5%|▌ | 30769/569592 [35:01<310:52:52, 2.08s/it]
5%|▌ | 30770/569592 [35:03<325:57:20, 2.18s/it]
5%|▌ | 30770/569592 [35:03<325:57:20, 2.18s/it]
5%|▌ | 30771/569592 [35:08<446:03:26, 2.98s/it]
5%|▌ | 30771/569592 [35:08<446:03:26, 2.98s/it]
5%|▌ | 30772/569592 [35:10<415:05:20, 2.77s/it]
5%|▌ | 30772/569592 [35:10<415:05:20, 2.77s/it]
5%|▌ | 30773/569592 [35:11<331:30:46, 2.21s/it]
5%|▌ | 30773/569592 [35:11<331:30:46, 2.21s/it]
5%|▌ | 30774/569592 [35:13<295:30:04, 1.97s/it]
5%|▌ | 30774/569592 [35:13<295:30:04, 1.97s/it]
5%|▌ | 30775/569592 [35:18<464:13:16, 3.10s/it]
5%|▌ | 30775/569592 [35:18<464:13:16, 3.10s/it]
5%|▌ | 30776/569592 [35:20<415:14:44, 2.77s/it]
5%|▌ | 30776/569592 [35:20<415:14:44, 2.77s/it]
5%|▌ | 30777/569592 [35:21<333:08:19, 2.23s/it]
5%|▌ | 30777/569592 [35:21<333:08:19, 2.23s/it]
5%|▌ | 30778/569592 [35:23<326:07:03, 2.18s/it]
5%|▌ | 30778/569592 [35:23<326:07:03, 2.18s/it]
5%|▌ | 30779/569592 [35:28<428:33:04, 2.86s/it]
5%|▌ | 30779/569592 [35:28<428:33:04, 2.86s/it]
5%|▌ | 30780/569592 [35:31<421:15:31, 2.81s/it]
5%|▌ | 30780/569592 [35:31<421:15:31, 2.81s/it]
5%|▌ | 30781/569592 [35:32<336:17:36, 2.25s/it]
5%|▌ | 30781/569592 [35:32<336:17:36, 2.25s/it]
5%|▌ | 30782/569592 [35:33<317:44:49, 2.12s/it]
5%|▌ | 30782/569592 [35:33<317:44:49, 2.12s/it]
5%|▌ | 30783/569592 [35:39<460:24:34, 3.08s/it]
5%|▌ | 30783/569592 [35:39<460:24:34, 3.08s/it]
5%|▌ | 30784/569592 [35:40<390:48:40, 2.61s/it]
5%|▌ | 30784/569592 [35:40<390:48:40, 2.61s/it]
5%|▌ | 30785/569592 [35:41<331:21:13, /home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (90481664 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
2.21s/it]
5%|▌ | 30785/569592 [35:41<331:21:13, 2.21s/it]
5%|▌ | 30786/569592 [35:43<321:19:32, 2.15s/it]
5%|▌ | 30786/569592 [35:43<321:19:32, 2.15s/it]
5%|▌ | 30787/569592 [35:48<439:51:57, 2.94s/it]
5%|▌ | 30787/569592 [35:48<439:51:57, 2.94s/it]
5%|▌ | 30788/569592 [35:52<463:57:23, 3.10s/it]
5%|▌ | 30788/569592 [35:52<463:57:23, 3.10s/it]
5%|▌ | 30789/569592 [35:55<484:17:02, 3.24s/it]
5%|▌ | 30789/569592 [35:55<484:17:02, 3.24s/it]
5%|▌ | 30790/569592 [36:00<546:35:16, 3.65s/it]
5%|▌ | 30790/569592 [36:00<546:35:16, 3.65s/it]
5%|▌ | 30791/569592 [36:03<536:29:43, 3.58s/it]
5%|▌ | 30791/569592 [36:03<536:29:43, 3.58s/it]
5%|▌ | 30792/569592 [36:07<541:42:41, 3.62s/it]
5%|▌ | 30792/569592 [36:07<541:42:41, 3.62s/it]
5%|▌ | 30793/569592 [36:12<617:07:57, 4.12s/it]
5%|▌ | 30793/569592 [36:12<617:07:57, 4.12s/it]
5%|▌ | 30794/569592 [36:13<471:25:33, 3.15s/it]
5%|▌ | 30794/569592 [36:13<471:25:33, 3.15s/it]
5%|▌ | 30795/569592 [36:18<546:33:13, 3.65s/it]
5%|▌ | 30795/569592 [36:18<546:33:13, 3.65s/it]
5%|▌ | 30796/569592 [36:23<609:11:14, 4.07s/it]
5%|▌ | 30796/569592 [36:23<609:11:14, 4.07s/it]
5%|▌ | 30797/569592 [36:28<637:22:29, 4.26s/it]
5%|▌ | 30797/569592 [36:28<637:22:29, 4.26s/it]
5%|▌ | 30798/569592 [36:33<658:52:39, 4.40s/it]
5%|▌ | 30798/569592 [36:33<658:52:39, 4.40s/it]
5%|▌ | 30799/569592 [36:37<671:46:57, 4.49s/it]
5%|▌ | 30799/569592 [36:37<671:46:57, 4.49s/it]
5%|▌ | 30800/569592 [36:42<693:41:33, 4.63s/it]
5%|▌ | 30800/569592 [36:42<693:41:33, 4.63s/it]
5%|▌ | 30801/569592 [36:47<687:51:58, 4.60s/it]
5%|▌ | 30801/569592 [36:47<687:51:58, 4.60s/it]
5%|▌ | 30802/569592 [36:50<641:58:32, 4.29s/it]
5%|▌ | 30802/569592 [36:50<641:58:32, 4.29s/it]
5%|▌ | 30803/569592 [36:55<663:56:27, 4.44s/it]
5%|▌ | 30803/569592 [36:55<663:56:27, 4.44s/it]
5%|▌ | 30804/569592 [36:58<603:18:17, 4.03s/it]
5%|▌ | 30804/569592 [36:58<603:18:17, 4.03s/it]
5%|▌ | 30805/569592 [37:01<572:07:15, 3.82s/it]
5%|▌ | 30805/569592 [37:01<572:07:15, 3.82s/it]
5%|▌ | 30806/569592 [37:02<440:14:28, 2.94s/it]
5%|▌ | 30806/569592 [37:02<440:14:28, 2.94s/it]
5%|▌ | 30807/569592 [37:07<535:21:31, 3.58s/it]
5%|▌ | 30807/569592 [37:07<535:21:31, 3.58s/it]
5%|▌ | 30808/569592 [37:12<569:05:44, 3.80s/it]
5%|▌ | 30808/569592 [37:12<569:05:44, 3.80s/it]
5%|▌ | 30809/569592 [37:15<562:22:58, 3.76s/it]
5%|▌ | 30809/569592 [37:15<562:22:58, 3.76s/it]
5%|▌ | 30810/569592 [37:20<602:00:45, 4.02s/it]
5%|▌ | 30810/569592 [37:20<602:00:45, 4.02s/it]
5%|▌ | 30811/569592 [37:23<563:34:13, 3.77s/it]
5%|▌ | 30811/569592 [37:23<563:34:13, 3.77s/it]
5%|▌ | 30812/569592 [37:24<434:02:34, 2.90s/it]
5%|▌ | 30812/569592 [37:24<434:02:34, 2.90s/it]
5%|▌ | 30813/569592 [37:28<461:39:39, 3.08s/it]
5%|▌ | 30813/569592 [37:28<461:39:39, 3.08s/it]
5%|▌ | 30814/569592 [37:32<536:42:07, 3.59s/it]
5%|▌ | 30814/569592 [37:32<536:42:07, 3.59s/it]
5%|▌ | 30815/569592 [37:33<424:14:49, 2.83s/it]
5%|▌ | 30815/569592 [37:33<424:14:49, 2.83s/it]
5%|▌ | 30816/569592 [37:38<490:47:48, 3.28s/it]
5%|▌ | 30816/569592 [37:38<490:47:48, 3.28s/it]
5%|▌ | 30817/569592 [37:41<488:48:22, 3.27s/it]
5%|▌ | 30817/569592 [37:41<488:48:22, 3.27s/it]
5%|▌ | 30818/569592 [37:42<383:45:45, 2.56s/it]
5%|▌ | 30818/569592 [37:42<383:45:45, 2.56s/it]
5%|▌ | 30819/569592 [37:46<473:05:20, 3.16s/it]
5%|▌ | 30819/569592 [37:46<473:05:20, 3.16s/it]
5%|▌ | 30820/569592 [37:51<544:17:12, 3.64s/it]
5%|▌ | 30820/569592 [37:51<544:17:12, 3.64s/it]
5%|▌ | 30821/569592 [37:52<419:28:34, 2.80s/it]
5%|▌ | 30821/569592 [37:52<419:28:34, 2.80s/it]
5%|▌ | 30822/569592 [37:53<335:06:28, 2.24s/it]
5%|▌ | 30822/569592 [37:53<335:06:28, 2.24s/it]
5%|▌ | 30823/569592 [37:54<280:16:21, 1.87s/it]
5%|▌ | 30823/569592 [37:54<280:16:21, 1.87s/it]
5%|▌ | 30824/569592 [37:55<240:58:22, 1.61s/it]
5%|▌ | 30824/569592 [37:55<240:58:22, 1.61s/it]
5%|▌ | 30825/569592 [37:56<210:25:07, 1.41s/it]
5%|▌ | 30825/569592 [37:56<210:25:07, 1.41s/it]
5%|▌ | 30826/569592 [37:57<189:44:19, 1.27s/it]
5%|▌ | 30826/569592 [37:57<189:44:19, 1.27s/it]
5%|▌ | 30827/569592 [37:58<174:29:21, 1.17s/it]
5%|▌ | 30827/569592 [37:58<174:29:21, 1.17s/it]
5%|▌ | 30828/569592 [37:59<190:00:20, 1.27s/it]
5%|▌ | 30828/569592 [37:59<190:00:20, 1.27s/it]
5%|▌ | 30829/569592 [38:05<372:27:50, 2.49s/it]
5%|▌ | 30829/569592 [38:05<372:27:50, 2.49s/it]
5%|▌ | 30830/569592 [38:06<315:45:33, 2.11s/it]
5%|▌ | 30830/569592 [38:06<315:45:33, 2.11s/it]
5%|▌ | 30831/569592 [38:07<268:05:19, 1.79s/it]
5%|▌ | 30831/569592 [38:07<268:05:19, 1.79s/it]
5%|▌ | 30832/569592 [38:09<285:17:47, 1.91s/it]
5%|▌ | 30832/569592 [38:09<285:17:47, 1.91s/it]
5%|▌ | 30833/569592 [38:15<464:21:26, 3.10s/it]
5%|▌ | 30833/569592 [38:15<464:21:26, 3.10s/it]
5%|▌ | 30834/569592 [38:16<382:06:12, 2.55s/it]
5%|▌ | 30834/569592 [38:17<382:06:12, 2.55s/it]
5%|▌ | 30835/569592 [38:18<323:27:51, 2.16s/it]
5%|▌ | 30835/569592 [38:18<323:27:51, 2.16s/it]
5%|▌ | 30836/569592 [38:20<317:00:35, 2.12s/it]
5%|▌ | 30836/569592 [38:20<317:00:35, 2.12s/it]
5%|▌ | 30837/569592 [38:26<502:45:13, 3.36s/it]
5%|▌ | 30837/569592 [38:26<502:45:13, 3.36s/it]
5%|▌ | 30838/569592 [38:27<394:16:16, 2.63s/it]
5%|▌ | 30838/569592 [38:27<394:16:16, 2.63s/it]
5%|▌ | 30839/569592 [38:28<320:57:33, 2.14s/it]
5%|▌ | 30839/569592 [38:28<320:57:33, 2.14s/it]
5%|▌ | 30840/569592 [38:30<332:40:35, 2.22s/it]
5%|▌ | 30840/569592 [38:30<332:40:35, 2.22s/it]
5%|▌ | 30841/569592 [38:36<475:22:03, 3.18s/it]
/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (101907408 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
5%|▌ | 30841/569592 [38:36<475:22:03, 3.18s/it]
5%|▌ | 30842/569592 [38:37<378:13:13, 2.53s/it]
5%|▌ | 30842/569592 [38:37<378:13:13, 2.53s/it]
5%|▌ | 30843/569592 [38:37<306:51:19, 2.05s/it]
5%|▌ | 30843/569592 [38:37<306:51:19, 2.05s/it]
5%|▌ | 30844/569592 [38:41<350:58:14, 2.35s/it]
5%|▌ | 30844/569592 [38:41<350:58:14, 2.35s/it]
5%|▌ | 30845/569592 [38:47<522:58:57, 3.49s/it]
5%|▌ | 30845/569592 [38:47<522:58:57, 3.49s/it]
5%|▌ | 30846/569592 [38:48<413:34:23, 2.76s/it]
5%|▌ | 30846/569592 [38:48<413:34:23, 2.76s/it]
5%|▌ | 30847/569592 [38:49<332:31:26, 2.22s/it]
5%|▌ | 30847/569592 [38:49<332:31:26, 2.22s/it]
5%|▌ | 30848/569592 [38:50<306:30:01, 2.05s/it]
5%|▌ | 30848/569592 [38:50<306:30:01, 2.05s/it]
5%|▌ | 30849/569592 [38:56<471:02:44, 3.15s/it]
5%|▌ | 30849/569592 [38:56<471:02:44, 3.15s/it]
5%|▌ | 30850/569592 [38:58<399:06:09, 2.67s/it]
5%|▌ | 30850/569592 [38:58<399:06:09, 2.67s/it]
5%|▌ | 30851/569592 [38:59<323:47:26, 2.16s/it]
5%|▌ | 30851/569592 [38:59<323:47:26, 2.16s/it]
5%|▌ | 30852/569592 [39:02<365:41:01, 2.44s/it]
5%|▌ | 30852/569592 [39:02<365:41:01, 2.44s/it]
5%|▌ | 30853/569592 [39:06<465:42:04, 3.11s/it]
5%|▌ | 30853/569592 [39:06<465:42:04, 3.11s/it]
5%|▌ | 30854/569592 [39:07<374:30:19, 2.50s/it]
5%|▌ | 30854/569592 [39:07<374:30:19, 2.50s/it]
5%|▌ | 30855/569592 [39:08<305:23:34, 2.04s/it]
5%|▌ | 30855/569592 [39:08<305:23:34, 2.04s/it]
5%|▌ | 30856/569592 [39:12<371:53:05, 2.49s/it]
5%|▌ | 30856/569592 [39:12<371:53:05, 2.49s/it]
5%|▌ | 30857/569592 [39:17<487:27:24, 3.26s/it]
5%|▌ | 30857/569592 [39:17<487:27:24, 3.26s/it]
5%|▌ | 30858/569592 [39:18<383:54:32, 2.57s/it]
5%|▌ | 30858/569592 [39:18<383:54:32, 2.57s/it]
5%|▌ | 30859/569592 [39:19<311:48:43, 2.08s/it]
5%|▌ | 30859/569592 [39:19<311:48:43, 2.08s/it]
5%|▌ | 30860/569592 [39:22<347:30:17, 2.32s/it]
5%|▌ | 30860/569592 [39:22<347:30:17, 2.32s/it]
5%|▌ | 30861/569592 [39:27<488:19:56, 3.26s/it]
5%|▌ | 30861/569592 [39:27<488:19:56, 3.26s/it]
5%|▌ | 30862/569592 [39:28<383:19:06, 2.56s/it]
5%|▌ | 30862/569592 [39:28<383:19:06, 2.56s/it]
5%|▌ | 30863/569592 [39:29<309:49:29, 2.07s/it]
5%|▌ | 30863/569592 [39:29<309:49:29, 2.07s/it]
5%|▌ | 30864/569592 [39:31<295:42:59, 1.98s/it]
5%|▌ | 30864/569592 [39:31<295:42:59, 1.98s/it]
5%|▌ | 30865/569592 [39:37<497:14:53, 3.32s/it]
5%|▌ | 30865/569592 [39:37<497:14:53, 3.32s/it]
5%|▌ | 30866/569592 [39:38<392:07:55, 2.62s/it]
5%|▌ | 30866/569592 [39:38<392:07:55, 2.62s/it]
5%|▌ | 30867/569592 [39:39<316:28:11, 2.11s/it]
5%|▌ | 30867/569592 [39:39<316:28:11, 2.11s/it]
5%|▌ | 30868/569592 [39:42<333:55:12, 2.23s/it]
5%|▌ | 30868/569592 [39:42<333:55:12, 2.23s/it]
5%|▌ | 30869/569592 [39:47<492:08:59, 3.29s/it]
5%|▌ | 30869/569592 [39:47<492:08:59, 3.29s/it]
5%|▌ | 30870/569592 [39:48<386:23:36, 2.58s/it]
5%|▌ | 30870/569592 [39:48<386:23:36, 2.58s/it]
5%|▌ | 30871/569592 [39:49<313:36:25, 2.10s/it]
5%|▌ | 30871/569592 [39:49<313:36:25, 2.10s/it]
5%|▌ | 30872/569592 [39:52<326:18:16, 2.18s/it]
5%|▌ | 30872/569592 [39:52<326:18:16, 2.18s/it]
5%|▌ | 30873/569592 [39:57<485:00:36, 3.24s/it]
5%|▌ | 30873/569592 [39:57<485:00:36, 3.24s/it]
5%|▌ | 30874/569592 [39:59<392:38:17, 2.62s/it]
5%|▌ | 30874/569592 [39:59<392:38:17, 2.62s/it]
5%|▌ | 30875/569592 [40:00<320:36:00, 2.14s/it]
5%|▌ | 30875/569592 [40:00<320:36:00, 2.14s/it]
5%|▌ | 30876/569592 [40:01<266:49:12, 1.78s/it]
5%|▌ | 30876/569592 [40:01<266:49:12, 1.78s/it]
5%|▌ | 30877/569592 [40:07<485:05:17, 3.24s/it]
5%|▌ | 30877/569592 [40:07<485:05:17, 3.24s/it]
5%|▌ | 30878/569592 [40:08<383:18:58, 2.56s/it]
5%|▌ | 30878/569592 [40:08<383:18:58, 2.56s/it]
5%|▌ | 30879/569592 [40:10<345:29:41, 2.31s/it]
5%|▌ | 30879/569592 [40:10<345:29:41, 2.31s/it]
5%|▌ | 30880/569592 [40:11<301:09:04, 2.01s/it]
5%|▌ | 30880/569592 [40:11<301:09:04, 2.01s/it]
5%|▌ | 30881/569592 [40:16<419:08:17, 2.80s/it]
5%|▌ | 30881/569592 [40:16<419:08:17, 2.80s/it]
5%|▌ | 30882/569592 [40:18<405:00:28, 2.71s/it]
5%|▌ | 30882/569592 [40:18<405:00:28, 2.71s/it]
5%|▌ | 30883/569592 [40:19<332:09:37, 2.22s/it]
5%|▌ | 30883/569592 [40:20<332:09:37, 2.22s/it]
5%|▌ | 30884/569592 [40:21<312:13:23, 2.09s/it]
5%|▌ | 30884/569592 [40:21<312:13:23, 2.09s/it]
5%|▌ | 30885/569592 [40:26<442:58:24, 2.96s/it]
5%|▌ | 30885/569592 [40:26<442:58:24, 2.96s/it]
5%|▌ | 30886/569592 [40:30<467:38:35, 3.13s/it]
5%|▌ | 30886/569592 [40:30<467:38:35, 3.13s/it]
5%|▌ | 30887/569592 [40:31<368:36:52, 2.46s/it]
5%|▌ | 30887/569592 [40:31<368:36:52, 2.46s/it]
5%|▌ | 30888/569592 [40:32<300:29:18, 2.01s/it]
5%|▌ | 30888/569592 [40:32<300:29:18, 2.01s/it]
5%|▌ | 30889/569592 [40:36<406:19:17, 2.72s/it]
5%|▌ | 30889/569592 [40:36<406:19:17, 2.72s/it]
5%|▌ | 30890/569592 [40:41<487:55:19, 3.26s/it]
5%|▌ | 30890/569592 [40:41<487:55:19, 3.26s/it]
5%|▌ | 30891/569592 [40:42<386:29:48, 2.58s/it]
5%|▌ | 30891/569592 [40:42<386:29:48, 2.58s/it]
5%|▌ | 30892/569592 [40:43<326:30:52, 2.18s/it]
5%|▌ | 30892/569592 [40:43<326:30:52, 2.18s/it]
5%|▌ | 30893/569592 [40:46<389:15:55, 2.60s/it]
5%|▌ | 30893/569592 [40:46<389:15:55, 2.60s/it]
5%|▌ | 30894/569592 [40:51<461:51:42, 3.09s/it]
5%|▌ | 30894/569592 [40:51<461:51:42, 3.09s/it]
5%|▌ | 30895/569592 [40:52<366:20:58, 2.45s/it]
5%|▌ | 30895/569592 [40:52<366:20:58, 2.45s/it]
5%|▌ | 30896/569592 [40:52<298:25:58, 1.99s/it]
5%|▌ | 30896/569592 [40:52<298:25:58, 1.99s/it]
5%|▌ | 30897/569592 [40:56<380:48:21, 2.54s/it]
5%|▌ | 30897/569592 [40:56<380:48:21, 2.54s/it]
5%|▌ | 30898/569592 [41:01<486:27:14, 3.25s/it]
5%|▌ | 30898/569592 [41:01<486:27:14, 3.25s/it]
5%|▌ | 30899/569592 [41:02<388:25:34, 2.60s/it]
5%|▌ | 30899/569592 [41:02<388:25:34, 2.60s/it]
5%|▌ | 30900/569592 [41:06<418:07:19, 2.79s/it]
5%|▌ | 30900/569592 [41:06<418:07:19, 2.79s/it]
5%|▌ | 30901/569592 [41:07<336:21:42, 2.25s/it]
5%|▌ | 30901/569592 [41:07<336:21:42, 2.25s/it]
5%|▌ | 30902/569592 [41:12<484:57:51, 3.24s/it]
5%|▌ | 30902/569592 [41:12<484:57:51, 3.24s/it]
5%|▌ | 30903/569592 [41:17<564:07:01, 3.77s/it]
5%|▌ | 30903/569592 [41:17<564:07:01, 3.77s/it]
5%|▌ | 30904/569592 [41:21<589:06:28, 3.94s/it]
5%|▌ | 30904/569592 [41:21<589:06:28, 3.94s/it]
5%|▌ | 30905/569592 [41:26<625:59:22, 4.18s/it]
5%|▌ | 30905/569592 [41:26<625:59:22, 4.18s/it]
5%|▌ | 30906/569592 [41:27<477:10:49, 3.19s/it]
5%|▌ | 30906/569592 [41:27<477:10:49, 3.19s/it]
5%|▌ | 30907/569592 [41:31<501:59:15, 3.35s/it]
5%|▌ | 30907/569592 [41:31<501:59:15, 3.35s/it]
5%|▌ | 30908/569592 [41:36<573:04:38, 3.83s/it]
5%|▌ | 30908/569592 [41:36<573:04:38, 3.83s/it]
5%|▌ | 30909/569592 [41:41<623:50:21, 4.17s/it]
5%|▌ | 30909/569592 [41:41<623:50:21, 4.17s/it]
5%|▌ | 30910/569592 [41:44<582:09:42, 3.89s/it]
5%|▌ | 30910/569592 [41:44<582:09:42, 3.89s/it]
5%|▌ | 30911/569592 [41:47<552:35:24, 3.69s/it]
5%|▌ | 30911/569592 [41:47<552:35:24, 3.69s/it]
5%|▌ | 30912/569592 [41:52<594:06:40, 3.97s/it]
5%|▌ | 30912/569592 [41:52<594:06:40, 3.97s/it]
5%|▌ | 30913/569592 [41:55<575:56:34, 3.85s/it]
5%|▌ | 30913/569592 [41:55<575:56:34, 3.85s/it]
5%|▌ | 30914/569592 [42:00<629:59:01, 4.21s/it]
5%/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (100920000 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
|▌ | 30914/569592 [42:00<629:59:01, 4.21s/it]
5%|▌ | 30915/569592 [42:04<601:13:58, 4.02s/it]
5%|▌ | 30915/569592 [42:04<601:13:58, 4.02s/it]
5%|▌ | 30916/569592 [42:11<740:57:58, 4.95s/it]
5%|▌ | 30916/569592 [42:11<740:57:58, 4.95s/it]
5%|▌ | 30917/569592 [42:14<657:48:58, 4.40s/it]
5%|▌ | 30917/569592 [42:14<657:48:58, 4.40s/it]
5%|▌ | 30918/569592 [42:19<682:49:50, 4.56s/it]
5%|▌ | 30918/569592 [42:19<682:49:50, 4.56s/it]
5%|▌ | 30919/569592 [42:23<663:15:07, 4.43s/it]
5%|▌ | 30919/569592 [42:23<663:15:07, 4.43s/it]
5%|▌ | 30920/569592 [42:28<656:37:18, 4.39s/it]
5%|▌ | 30920/569592 [42:28<656:37:18, 4.39s/it]
5%|▌ | 30921/569592 [42:28<499:32:55, 3.34s/it]
5%|▌ | 30921/569592 [42:28<499:32:55, 3.34s/it]
5%|▌ | 30922/569592 [42:33<571:50:48, 3.82s/it]
5%|▌ | 30922/569592 [42:33<571:50:48, 3.82s/it]
5%|▌ | 30923/569592 [42:38<599:52:35, 4.01s/it]
5%|▌ | 30923/569592 [42:38<599:52:35, 4.01s/it]
5%|▌ | 30924/569592 [42:39<459:18:32, 3.07s/it]
5%|▌ | 30924/569592 [42:39<459:18:32, 3.07s/it]
5%|▌ | 30925/569592 [42:44<538:28:00, 3.60s/it]
5%|▌ | 30925/569592 [42:44<538:28:00, 3.60s/it]
5%|▌ | 30926/569592 [42:47<533:52:54, 3.57s/it]
5%|▌ | 30926/569592 [42:47<533:52:54, 3.57s/it]
5%|▌ | 30927/569592 [42:52<592:18:28, 3.96s/it]
5%|▌ | 30927/569592 [42:52<592:18:28, 3.96s/it]
5%|▌ | 30928/569592 [42:55<558:11:52, 3.73s/it]
5%|▌ | 30928/569592 [42:55<558:11:52, 3.73s/it]
5%|▌ | 30929/569592 [42:58<534:41:48, 3.57s/it]
5%|▌ | 30929/569592 [42:58<534:41:48, 3.57s/it]
5%|▌ | 30930/569592 [43:01<511:37:59, 3.42s/it]
5%|▌ | 30930/569592 [43:01<511:37:59, 3.42s/it]
5%|▌ | 30931/569592 [43:05<510:56:26, 3.41s/it]
5%|▌ | 30931/569592 [43:05<510:56:26, 3.41s/it]
5%|▌ | 30932/569592 [43:10<580:55:52, 3.88s/it]
5%|▌ | 30932/569592 [43:10<580:55:52, 3.88s/it]
5%|▌ | 30933/569592 [43:11<446:07:58, 2.98s/it]
5%|▌ | 30933/569592 [43:11<446:07:58, 2.98s/it]
5%|▌ | 30934/569592 [43:14<463:28:22, 3.10s/it]
5%|▌ | 30934/569592 [43:14<463:28:22, 3.10s/it]
5%|▌ | 30935/569592 [43:17<480:16:05, 3.21s/it]
5%|▌ | 30935/569592 [43:17<480:16:05, 3.21s/it]
5%|▌ | 30936/569592 [43:22<518:59:01, 3.47s/it]
5%|▌ | 30936/569592 [43:22<518:59:01, 3.47s/it]
5%|▌ | 30937/569592 [43:25<500:22:32, 3.34s/it]
5%|▌ | 30937/569592 [43:25<500:22:32, 3.34s/it]
5%|▌ | 30938/569592 [43:26<391:48:55, 2.62s/it]
5%|▌ | 30938/569592 [43:26<391:48:55, 2.62s/it]
5%|▌ | 30939/569592 [43:26<316:17:52, 2.11s/it]
5%|▌ | 30939/569592 [43:26<316:17:52, 2.11s/it]
5%|▌ | 30940/569592 [43:27<264:14:26, 1.77s/it]
5%|▌ | 30940/569592 [43:27<264:14:26, 1.77s/it]
5%|▌ | 30941/569592 [43:28<227:04:49, 1.52s/it]
5%|▌ | 30941/569592 [43:28<227:04:49, 1.52s/it]
5%|▌ | 30942/569592 [43:29<200:28:42, 1.34s/it]
5%|▌ | 30942/569592 [43:29<200:28:42, 1.34s/it]
5%|▌ | 30943/569592 [43:30<181:28:46, 1.21s/it]
5%|▌ | 30943/569592 [43:30<181:28:46, 1.21s/it]
5%|▌ | 30944/569592 [43:31<169:57:18, 1.14s/it]
5%|▌ | 30944/569592 [43:31<169:57:18, 1.14s/it]
5%|▌ | 30945/569592 [43:35<272:28:59, 1.82s/it]
5%|▌ | 30945/569592 [43:35<272:28:59, 1.82s/it]
5%|▌ | 30946/569592 [43:38<358:59:54, 2.40s/it]
5%|▌ | 30946/569592 [43:38<358:59:54, 2.40s/it]
5%|▌ | 30947/569592 [43:39<297:55:38, 1.99s/it]
5%|▌ | 30947/569592 [43:39<297:55:38, 1.99s/it]
5%|▌ | 30948/569592 [43:40<252:59:29, 1.69s/it]
5%|▌ | 30948/569592 [43:40<252:59:29, 1.69s/it]
5%|▌ | 30949/569592 [43:45<368:49:04, 2.46s/it]
5%|▌ | 30949/569592 [43:45<368:49:04, 2.46s/it]
5%|▌ | 30950/569592 [43:49<448:43:42, 3.00s/it]
5%|▌ | 30950/569592 [43:49<448:43:42, 3.00s/it]
5%|▌ | 30951/569592 [43:50<362:58:27, 2.43s/it]
5%|▌ | 30951/569592 [43:50<362:58:27, 2.43s/it]
5%|▌ | 30952/569592 [43:51<296:50:53, 1.98s/it]
5%|▌ | 30952/569592 [43:51<296:50:53, 1.98s/it]
5%|▌ | 30953/569592 [43:56<434:40:50, 2.91s/it]
5%|▌ | 30953/569592 [43:56<434:40:50, 2.91s/it]
5%|▌ | 30954/569592 [43:59<440:27:43, 2.94s/it]
5%|▌ | 30954/569592 [43:59<440:27:43, 2.94s/it]
5%|▌ | 30955/569592 [44:00<354:18:43, 2.37s/it]
5%|▌ | 30955/569592 [44:00<354:18:43, 2.37s/it]
5%|▌ | 30956/569592 [44:01<291:19:36, 1.95s/it]
5%|▌ | 30956/569592 [44:01<291:19:36, 1.95s/it]
5%|▌ | 30957/569592 [44:07<478:35:11, 3.20s/it]
5%|▌ | 30957/569592 [44:07<478:35:11, 3.20s/it]
5%|▌ | 30958/569592 [44:09<429:10:08, 2.87s/it]
5%|▌ | 30958/569592 [44:09<429:10:08, 2.87s/it]
5%|▌ | 30959/569592 [44:10<344:04:10, 2.30s/it]
5%|▌ | 30959/569592 [44:10<344:04:10, 2.30s/it]
5%|▌ | 30960/569592 [44:12<325:30:22, 2.18s/it]
5%|▌ | 30960/569592 [44:12<325:30:22, 2.18s/it]
5%|▌ | 30961/569592 [44:18<478:35:55, 3.20s/it]
5%|▌ | 30961/569592 [44:18<478:35:55, 3.20s/it]
5%|▌ | 30962/569592 [44:19<406:52:55, 2.72s/it]
5%|▌ | 30962/569592 [44:19<406:52:55, 2.72s/it]
5%|▌ | 30963/569592 [44:20<328:14:37, 2.19s/it]
5%|▌ | 30963/569592 [44:20<328:14:37, 2.19s/it]
5%|▌ | 30964/569592 [44:21<279:46:27, 1.87s/it]
5%|▌ | 30964/569592 [44:21<279:46:27, 1.87s/it]
5%|▌ | 30965/569592 [44:28<483:59:36, 3.23s/it]
5%|▌ | 30965/569592 [44:28<483:59:36, 3.23s/it]
5%|▌ | 30966/569592 [44:30<439:08:46, 2.94s/it]
5%|▌ | 30966/569592 [44:30<439:08:46, 2.94s/it]
5%|▌ | 30967/569592 [44:31<349:49:46, 2.34s/it]
5%|▌ | 30967/569592 [44:31<349:49:46, 2.34s/it]
5%|▌ | 30968/569592 [44:32<287:49:25, 1.92s/it]
5%|▌ | 30968/569592 [44:32<287:49:25, 1.92s/it]
5%|▌ | 30969/569592 [44:38<471:57:16, 3.15s/it]
5%|▌ | 30969/569592 [44:38<471:57:16, 3.15s/it]
5%|▌ | 30970/569592 [44:39<386:40:10, 2.58s/it]
5%|▌ | 30970/569592 [44:39<386:40:10, 2.58s/it]
5%|▌ | 30971/569592 [44:40<313:51:32, 2.10s/it]
5%|▌ | 30971/569592 [44:40<313:51:32, 2.10s/it]
5%|▌ | 30972/569592 [44:42<307:46:21, 2.06s/it]
5%|▌ | 30972/569592 [44:42<307:46:21, 2.06s/it]
5%|▌ | 30973/569592 [44:47<457:12:04, 3.06s/it]
5%|▌ | 30973/569592 [44:47<457:12:04, 3.06s/it]
5%|▌ | 30974/569592 [44:51<459:39:56, 3.07s/it]
5%|▌ | 30974/569592 [44:51<459:39:56, 3.07s/it]
5%|▌ | 30975/569592 [44:52<365:33:33, 2.44s/it]
5%|▌ | 30975/569592 [44:52<365:33:33, 2.44s/it]
5%|▌ | 30976/569592 [44:53<304:27:04, 2.03s/it]
5%|▌ | 30976/569592 [44:53<304:27:04, 2.03s/it]
5%|▌ | 30977/569592 [44:59<507:38:01, 3.39s/it]
5%|▌ | 30977/569592 [44:59<507:38:01, 3.39s/it]
5%|▌ | 30978/569592 [45:00<398:02:52, 2.66s/it]
5%|▌ | 30978/569592 [45:00<398:02:52, 2.66s/it]
5%|▌ | 30979/569592 [45:01<335:10:31, 2.24s/it]
5%|▌ | 30979/569592 [45:01<335:10:31, 2.24s/it]
5%|▌ | 30980/569592 [45:03<299:28:51, 2.00s/it]
5%|▌ | 30980/569592 [45:03<299:28:51, 2.00s/it]
5%|▌ | 30981/569592 [45:10<518:54:21, 3.47s/it]
5%|▌ | 30981/569592 [45:10<518:54:21, 3.47s/it]
5%|▌ | 30982/569592 [45:11<405:34:08, 2.71s/it]
5%|▌ | 30982/569592 [45:11<405:34:08, 2.71s/it]
5%|▌ | 30983/569592 [45:12<325:38:12, 2.18s/it]
5%|▌ | 30983/569592 [45:12<325:38:12, 2.18s/it]
5%|▌ | 30984/569592 [45:13<299:49:48, 2.00s/it]
5%|▌ | 30984/569592 [45:13<299:49:48, 2.00s/it]
5%|▌ | 30985/569592 [45:20<515:09:06, 3.44s/it]
5%|▌ | 30985/569592 [45:20<515:09:06, 3.44s/it]
5%|▌ | 30986/569592 [45:21<405:29:27, 2.71s/it]
5%|▌ | 30986/569592 [45:21<405:29:27, 2.71s/it]
5%|▌ | 30987/569592 [45:22<324:45:03, 2.17s/it]
5%|▌ | 30987/569592 [45:22<324:45:03, 2.17s/it]
5%|▌ | 30988/569592 [45:23<292:51:16, 1.96s/it]
5%|▌ | 30988/569592 [45:23<292:51:16, 1.96s/it]
5%|▌ | 30989/569592 [45:30<503:28:31, 3.37s/it]
5%|▌ | 30989/569592 [45:30<503:28:31, 3.37s/it]
5%|▌ | 30990/569592 [45:31<398:49:19, 2.67s/it]
5%|▌ | 30990/569592 [45:31<398:49:19, 2.67s/it]
5%|▌ | 30991/569592 [45:32<324:16:51, 2.17s/it]
5%|▌ | 30991/569592 [45:32<324:16:51, 2.17s/it]
5%|▌ | 30992/569592 [45:33<277:26:01, 1.85s/it]
5%|▌ | 30992/569592 [45:33<277:26:01, 1.85s/it]
5%|▌ | 30993/569592 [45:40<514:44:01, 3.44s/it]
5%|▌ | 30993/569592 [45:40<514:44:01, 3.44s/it]
5%|▌ | 30994/569592 [45:41<404:14:04, 2.70s/it]
5%|▌ | 30994/569592 [45:41<404:14:04, 2.70s/it]
5%|▌ | 30995/569592 [45:42<325:35:10, 2.18s/it]
5%|▌ | 30995/569592 [45:42<325:35:10, 2.18s/it]
5%|▌ | 30996/569592 [45:44<294:35:10, 1.97s/it]
5%|▌ | 30996/569592 [45:44<294:35:10, 1.97s/it]
5%|▌ | 30997/569592 [45:49<459:24:24, 3.07s/it]
5%|▌ | 30997/569592 [45:49<459:24:24, 3.07s/it]
5%|▌ | 30998/569592 [45:50<363:45:26, 2.43s/it]
5%|▌ | 30998/569592 [45:50<363:45:26, 2.43s/it]
5%|▌ | 30999/569592 [45:51<297:21:55, 1.99s/it]
5%|▌ | 30999/569592 [45:51<297:21:55, 1.99s/it]
5%|▌ | 31000/569592 [45:54<349:11:49, 2.33s/it]
5%|▌ | 31000/569592 [45:54<349:11:49, 2.33s/it]Saving model checkpoint to /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-31000
Configuration saved in /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-31000/config.json
Configuration saved in /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-31000/generation_config.json
The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 6 checkpoint shards. You can find where each parameters has been saved in the index located at /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-31000/model.safetensors.index.json.
tokenizer config file saved in /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-31000/tokenizer_config.json
Special tokens file saved in /fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-31000/special_tokens_map.json
Deleting older checkpoint [/fsx_0/user/zhaojiang/models/qwen-vl-gen/checkpoint-30000] due to args.save_total_limit
model-00001-of-00006.safetensors: 0%| | 0.00/4.97G [00:00, ?B/s][A
model-00004-of-00006.safetensors: 0%| | 0.00/5.00G [00:00, ?B/s][A[A
rng_state_0.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_1.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
Upload 133 LFS files: 0%| | 0/133 [00:00, ?it/s][A[A[A[A[A
rng_state_10.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A[A[A
model-00001-of-00006.safetensors: 0%| | 4.44M/4.97G [00:00<01:51, 44.3MB/s][A
rng_state_10.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 309kB/s]
model-00004-of-00006.safetensors: 0%| | 5.34M/5.00G [00:00<01:33, 53.2MB/s][A[A
rng_state_0.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 107kB/s]
rng_state_1.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 95.4kB/s]
rng_state_100.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_101.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_102.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A[A[A
model-00001-of-00006.safetensors: 0%| | 16.0M/4.97G [00:00<01:37, 50.8MB/s][A
rng_state_100.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 347kB/s]
model-00004-of-00006.safetensors: 0%| | 16.0M/5.00G [00:00<01:47, 46.5MB/s][A[A
rng_state_101.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 222kB/s]
rng_state_102.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 171kB/s]
rng_state_103.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_103.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 276kB/s]
rng_state_104.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_105.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_105.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 399kB/s]
rng_state_104.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 212kB/s]
rng_state_106.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_106.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 448kB/s]
rng_state_107.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_108.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_107.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 164kB/s]
rng_state_108.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 232kB/s]
rng_state_109.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_109.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 227kB/s]
rng_state_11.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_110.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_11.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 328kB/s]
rng_state_110.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 392kB/s]
model-00001-of-00006.safetensors: 1%| | 32.0M/4.97G [00:01<03:03, 26.9MB/s][A
rng_state_111.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_111.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 418kB/s]
rng_state_112.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
model-00004-of-00006.safetensors: 1%| | 32.0M/5.00G [00:01<03:23, 24.5MB/s][A[A
rng_state_113.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_113.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 243kB/s]
rng_state_112.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 107kB/s]
rng_state_114.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_115.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_114.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 300kB/s]
model-00001-of-00006.safetensors: 1%| | 48.0M/4.97G [00:01<02:32, 32.3MB/s][A
model-00004-of-00006.safetensors: 1%| | 48.0M/5.00G [00:01<02:27, 33.5MB/s][A[A
rng_state_116.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_115.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 194kB/s]
rng_state_116.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 378kB/s]
rng_state_117.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_118.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_117.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 292kB/s]
rng_state_119.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_118.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 395kB/s]
model-00001-of-00006.safetensors: 1%|▏ | 64.0M/4.97G [00:01<01:57, 41.8MB/s][A
rng_state_119.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 203kB/s]
rng_state_12.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_120.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
model-00004-of-00006.safetensors: 1%|▏ | 64.0M/5.00G [00:01<02:06, 39.2MB/s][A[A
rng_state_12.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 239kB/s]
rng_state_120.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 135kB/s]
rng_state_121.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_121.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 279kB/s]
model-00001-of-00006.safetensors: 2%|▏ | 80.0M/4.97G [00:02<01:50, 44.4MB/s][A
rng_state_122.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_123.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
model-00004-of-00006.safetensors: 2%|▏ | 80.0M/5.00G [00:02<01:56, 42.2MB/s][A[A
rng_state_123.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 392kB/s]
rng_state_122.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 135kB/s]
rng_state_124.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_124.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 234kB/s]
rng_state_125.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_126.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
model-00004-of-00006.safetensors: 2%|▏ | 96.0M/5.00G [00:02<01:45, 46.5MB/s][A[A
rng_state_125.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 244kB/s]
model-00001-of-00006.safetensors: 2%|▏ | 96.0M/4.97G [00:02<01:54, 42.7MB/s][A
rng_state_126.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 158kB/s]
rng_state_127.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_13.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_127.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 308kB/s]
rng_state_14.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_13.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 214kB/s]
rng_state_14.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 264kB/s]
model-00001-of-00006.safetensors: 2%|▏ | 112M/4.97G [00:02<01:41, 48.0MB/s] [A
rng_state_15.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_16.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
model-00004-of-00006.safetensors: 2%|▏ | 112M/5.00G [00:02<01:40, 48.7MB/s] [A[A
rng_state_15.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 247kB/s]
rng_state_16.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 231kB/s]
rng_state_17.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_17.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 173kB/s]
model-00001-of-00006.safetensors: 3%|▎ | 128M/4.97G [00:02<01:27, 55.3MB/s][A
rng_state_18.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_19.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
model-00004-of-00006.safetensors: 3%|▎ | 128M/5.00G [00:02<01:30, 53.6MB/s][A[A
rng_state_18.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 213kB/s]
rng_state_2.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_19.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 222kB/s]
rng_state_2.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 180kB/s]
rng_state_20.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_21.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_20.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 234kB/s]
rng_state_21.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 254kB/s]
model-00004-of-00006.safetensors: 3%|▎ | 144M/5.00G [00:03<01:26, 56.0MB/s][A[A
rng_state_22.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
model-00001-of-00006.safetensors: 3%|▎ | 144M/4.97G [00:03<01:36, 50.1MB/s][A
rng_state_23.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_22.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 238kB/s]
rng_state_24.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_23.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 298kB/s]
rng_state_24.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 294kB/s]
rng_state_25.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_26.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_26.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 463kB/s]
rng_state_27.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
model-00001-of-00006.safetensors: 3%|▎ | 160M/4.97G [00:03<01:28, 54.5MB/s][A
model-00004-of-00006.safetensors: 3%|▎ | 160M/5.00G [00:03<01:27, 55.2MB/s][A[A
rng_state_25.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 193kB/s]
rng_state_27.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 275kB/s]
rng_state_28.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_28.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 377kB/s]
rng_state_29.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_3.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_3.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 286kB/s]
model-00001-of-00006.safetensors: 4%|▎ | 176M/4.97G [00:03<01:23, 57.5MB/s][A
rng_state_30.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_29.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 167kB/s]
rng_state_31.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_30.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 214kB/s]
rng_state_32.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_31.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 239kB/s]
rng_state_32.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 210kB/s]
rng_state_33.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_33.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 299kB/s]
rng_state_34.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
model-00001-of-00006.safetensors: 4%|▍ | 192M/4.97G [00:04<01:26, 55.0MB/s][A
rng_state_34.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 366kB/s]
rng_state_35.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_36.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_35.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 217kB/s]
rng_state_36.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 198kB/s]
rng_state_37.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_38.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_37.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 206kB/s]
model-00001-of-00006.safetensors: 4%|▍ | 208M/4.97G [00:04<01:23, 56.9MB/s][A
rng_state_38.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 172kB/s]
rng_state_39.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_4.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_39.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 302kB/s]
rng_state_4.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 369kB/s]
rng_state_40.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_40.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 337kB/s]
rng_state_41.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_42.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_43.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A[A[A
rng_state_42.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 276kB/s]
rng_state_41.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 253kB/s]
model-00001-of-00006.safetensors: 5%|▍ | 224M/4.97G [00:04<01:32, 51.3MB/s][A
rng_state_44.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_45.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_43.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 120kB/s]
rng_state_44.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 337kB/s]
rng_state_46.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_45.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 130kB/s]
rng_state_47.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
model-00001-of-00006.safetensors: 5%|▍ | 240M/4.97G [00:04<01:25, 55.3MB/s][A
rng_state_46.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 138kB/s]
rng_state_47.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 322kB/s]
rng_state_48.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
model-00004-of-00006.safetensors: 4%|▎ | 176M/5.00G [00:05<03:22, 23.8MB/s][A[A
rng_state_48.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 220kB/s]
rng_state_49.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_5.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_49.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 181kB/s]
rng_state_50.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_5.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 370kB/s]
model-00001-of-00006.safetensors: 5%|▌ | 256M/4.97G [00:05<01:23, 56.6MB/s][A
model-00004-of-00006.safetensors: 4%|▍ | 192M/5.00G [00:05<02:42, 29.7MB/s][A[A
rng_state_50.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 162kB/s]
rng_state_51.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_52.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_51.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 176kB/s]
rng_state_52.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 167kB/s]
rng_state_53.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
model-00001-of-00006.safetensors: 5%|▌ | 272M/4.97G [00:05<01:17, 60.4MB/s][A
rng_state_53.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 200kB/s]
rng_state_54.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_55.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_54.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 360kB/s]
rng_state_55.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 236kB/s]
rng_state_56.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
model-00004-of-00006.safetensors: 4%|▍ | 208M/5.00G [00:05<02:24, 33.1MB/s][A[A
rng_state_57.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_56.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 252kB/s]
rng_state_58.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
model-00001-of-00006.safetensors: 6%|▌ | 288M/4.97G [00:05<01:17, 60.6MB/s][A
rng_state_57.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 235kB/s]
rng_state_58.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 284kB/s]
rng_state_59.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_6.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_59.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 332kB/s]
rng_state_60.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_6.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 288kB/s]
model-00004-of-00006.safetensors: 4%|▍ | 224M/5.00G [00:05<02:03, 38.7MB/s][A[A
model-00001-of-00006.safetensors: 6%|▌ | 304M/4.97G [00:05<01:14, 62.7MB/s][A
rng_state_60.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 262kB/s]
rng_state_61.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_62.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_63.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A[A[A
rng_state_61.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 288kB/s]
rng_state_62.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 277kB/s]
rng_state_63.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 448kB/s]
rng_state_64.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_65.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
model-00001-of-00006.safetensors: 6%|▋ | 320M/4.97G [00:06<01:15, 61.3MB/s][A
rng_state_66.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A[A[A
rng_state_64.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 200kB/s]
rng_state_66.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 312kB/s]
rng_state_65.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 157kB/s]
rng_state_67.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_68.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_69.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A[A[A
rng_state_67.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 341kB/s]
rng_state_68.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 326kB/s]
rng_state_69.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 292kB/s]
rng_state_7.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_70.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_71.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A[A[A
model-00001-of-00006.safetensors: 7%|▋ | 336M/4.97G [00:06<01:23, 55.4MB/s][A
rng_state_70.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 320kB/s]
rng_state_7.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 229kB/s]
rng_state_71.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 143kB/s]
rng_state_72.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_73.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
model-00001-of-00006.safetensors: 7%|▋ | 352M/4.97G [00:06<01:18, 59.1MB/s][A
rng_state_73.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 281kB/s]
rng_state_74.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_72.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 166kB/s]
rng_state_74.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 290kB/s]
rng_state_75.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_76.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_76.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 367kB/s]
rng_state_75.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 226kB/s]
model-00001-of-00006.safetensors: 7%|▋ | 368M/4.97G [00:07<01:15, 61.3MB/s][A
rng_state_77.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_78.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
model-00004-of-00006.safetensors: 5%|▍ | 240M/5.00G [00:07<03:16, 24.2MB/s][A[A
rng_state_77.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 206kB/s]
rng_state_78.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 323kB/s]
rng_state_79.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
model-00001-of-00006.safetensors: 8%|▊ | 384M/4.97G [00:07<01:08, 67.1MB/s][A
rng_state_79.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 244kB/s]
rng_state_8.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_80.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_81.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A[A[A
rng_state_80.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 295kB/s]
rng_state_8.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 173kB/s]
model-00004-of-00006.safetensors: 5%|▌ | 256M/5.00G [00:07<02:40, 29.5MB/s][A[A
rng_state_81.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 259kB/s]
rng_state_82.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_83.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
model-00001-of-00006.safetensors: 8%|▊ | 400M/4.97G [00:07<01:10, 65.1MB/s][A
rng_state_84.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A[A[A
rng_state_83.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 194kB/s]
rng_state_82.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 124kB/s]
model-00004-of-00006.safetensors: 5%|▌ | 272M/5.00G [00:07<02:09, 36.5MB/s][A[A
rng_state_84.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 137kB/s]
rng_state_85.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_85.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 330kB/s]
rng_state_86.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
model-00001-of-00006.safetensors: 8%|▊ | 416M/4.97G [00:07<01:10, 64.8MB/s][A
rng_state_87.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_86.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 262kB/s]
rng_state_88.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
model-00004-of-00006.safetensors: 6%|▌ | 288M/5.00G [00:07<01:47, 43.7MB/s][A[A
rng_state_87.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 253kB/s]
rng_state_88.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 219kB/s]
rng_state_89.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_9.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
model-00001-of-00006.safetensors: 9%|▊ | 432M/4.97G [00:07<01:09, 65.6MB/s][A
rng_state_90.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A[A[A
rng_state_89.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 175kB/s]
rng_state_9.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 181kB/s]
rng_state_90.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 172kB/s]
rng_state_91.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
model-00004-of-00006.safetensors: 6%|▌ | 304M/5.00G [00:08<01:43, 45.5MB/s][A[A
rng_state_91.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 450kB/s]
rng_state_92.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_93.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_94.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A[A[A
rng_state_93.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 422kB/s]
rng_state_92.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 183kB/s]
rng_state_94.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 335kB/s]
model-00001-of-00006.safetensors: 9%|▉ | 448M/4.97G [00:08<01:14, 60.8MB/s][A
rng_state_95.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_96.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
model-00004-of-00006.safetensors: 6%|▋ | 320M/5.00G [00:08<01:34, 49.5MB/s][A[A
rng_state_97.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A[A[A
rng_state_95.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 234kB/s]
rng_state_96.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 289kB/s]
rng_state_97.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 292kB/s]
rng_state_98.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A
rng_state_99.pth: 0%| | 0.00/16.0k [00:00, ?B/s][A[A[A[A
rng_state_98.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 383kB/s]
scheduler.pt: 0%| | 0.00/1.06k [00:00, ?B/s][A[A[A
rng_state_99.pth: 100%|██████████| 16.0k/16.0k [00:00<00:00, 363kB/s]
scheduler.pt: 100%|██████████| 1.06k/1.06k [00:00<00:00, 28.5kB/s]
training_args.bin: 0%| | 0.00/7.29k [00:00, ?B/s][A[A[A
336337.out: 0%| | 0.00/81.4M [00:00, ?B/s][A[A[A[A
training_args.bin: 100%|██████████| 7.29k/7.29k [00:00<00:00, 173kB/s]
model-00004-of-00006.safetensors: 7%|▋ | 336M/5.00G [00:08<01:48, 43.0MB/s][A[A
336337.out: 20%|█▉ | 16.0M/81.4M [00:00<00:01, 53.4MB/s][A[A[A[A
model-00004-of-00006.safetensors: 7%|▋ | 352M/5.00G [00:09<01:34, 49.3MB/s][A[A
336337.out: 39%|███▉ | 32.0M/81.4M [00:00<00:00, 53.9MB/s][A[A[A[A
model-00001-of-00006.safetensors: 9%|▉ | 464M/4.97G [00:09<02:36, 28.8MB/s][A
336337.out: 59%|█████▉ | 48.0M/81.4M [00:00<00:00, 55.8MB/s][A[A[A[A
model-00001-of-00006.safetensors: 10%|▉ | 480M/4.97G [00:09<02:09, 34.6MB/s][A
336337.out: 79%|███████▊ | 64.0M/81.4M [00:01<00:00, 53.7MB/s][A[A[A[A
model-00001-of-00006.safetensors: 10%|▉ | 496M/4.97G [00:09<01:48, 41.4MB/s][A
model-00001-of-00006.safetensors: 10%|█ | 512M/4.97G [00:10<01:38, 45.1MB/s][A
336337.out: 98%|█████████▊| 80.0M/81.4M [00:01<00:00, 50.5MB/s][A[A[A[A
336337.out: 100%|██████████| 81.4M/81.4M [00:01<00:00, 48.3MB/s]
model-00001-of-00006.safetensors: 11%|█ | 528M/4.97G [00:10<01:28, 50.4MB/s][A
model-00004-of-00006.safetensors: 7%|▋ | 368M/5.00G [00:10<03:24, 22.7MB/s][A[A
model-00001-of-00006.safetensors: 11%|█ | 544M/4.97G [00:10<01:22, 53.5MB/s][A
model-00004-of-00006.safetensors: 8%|▊ | 384M/5.00G [00:10<02:45, 28.0MB/s][A[A
model-00001-of-00006.safetensors: 11%|█▏ | 560M/4.97G [00:10<01:17, 56.8MB/s][A
model-00001-of-00006.safetensors: 12%|█▏ | 576M/4.97G [00:11<01:11, 61.6MB/s][A
model-00004-of-00006.safetensors: 8%|▊ | 400M/5.00G [00:11<02:18, 33.3MB/s][A[A
model-00004-of-00006.safetensors: 8%|▊ | 416M/5.00G [00:11<01:57, 39.1MB/s][A[A
model-00001-of-00006.safetensors: 12%|█▏ | 592M/4.97G [00:11<01:12, 60.2MB/s][A
model-00004-of-00006.safetensors: 9%|▊ | 430M/5.00G [00:11<02:15, 33.8MB/s][A[A
model-00001-of-00006.safetensors: 12%|█▏ | 598M/4.97G [00:11<01:54, 38.0MB/s][A
model-00004-of-00006.safetensors: 9%|▊ | 435M/5.00G [00:12<02:07, 35.9MB/s][A[A
model-00001-of-00006.safetensors: 12%|█▏ | 608M/4.97G [00:12<01:53, 38.5MB/s][A
model-00004-of-00006.safetensors: 9%|▉ | 448M/5.00G [00:12<01:52, 40.3MB/s][A[A
model-00001-of-00006.safetensors: 13%|█▎ | 624M/4.97G [00:12<01:34, 45.8MB/s][A
model-00004-of-00006.safetensors: 9%|▉ | 464M/5.00G [00:12<01:35, 47.4MB/s][A[A
model-00004-of-00006.safetensors: 10%|▉ | 480M/5.00G [00:12<01:28, 51.2MB/s][A[A
model-00001-of-00006.safetensors: 13%|█▎ | 640M/4.97G [00:12<01:36, 44.8MB/s][A
model-00004-of-00006.safetensors: 10%|▉ | 496M/5.00G [00:12<01:20, 56.0MB/s][A[A
model-00001-of-00006.safetensors: 13%|█▎ | 656M/4.97G [00:13<01:23, 51.4MB/s][A
model-00004-of-00006.safetensors: 10%|█ | 512M/5.00G [00:13<01:16, 58.4MB/s][A[A
model-00001-of-00006.safetensors: 14%|█▎ | 672M/4.97G [00:13<01:21, 52.5MB/s][A
model-00004-of-00006.safetensors: 11%|█ | 528M/5.00G [00:13<01:11, 62.6MB/s][A[A
model-00001-of-00006.safetensors: 14%|█▍ | 688M/4.97G [00:13<01:16, 55.9MB/s][A
model-00004-of-00006.safetensors: 11%|█ | 544M/5.00G [00:13<01:07, 66.2MB/s][A[A
model-00001-of-00006.safetensors: 14%|█▍ | 704M/4.97G [00:13<01:11, 59.4MB/s][A
model-00001-of-00006.safetensors: 14%|█▍ | 720M/4.97G [00:14<01:10, 60.1MB/s][A
model-00004-of-00006.safetensors: 11%|█ | 560M/5.00G [00:14<01:19, 56.2MB/s][A[A
model-00004-of-00006.safetensors: 12%|█▏ | 576M/5.00G [00:14<01:13, 60.3MB/s][A[A
model-00001-of-00006.safetensors: 15%|█▍ | 736M/4.97G [00:14<01:09, 61.0MB/s][A
model-00004-of-00006.safetensors: 12%|█▏ | 592M/5.00G [00:14<01:07, 65.8MB/s][A[A
model-00001-of-00006.safetensors: 15%|█▌ | 752M/4.97G [00:14<01:05, 64.6MB/s][A
model-00004-of-00006.safetensors: 12%|█▏ | 608M/5.00G [00:14<01:04, 68.0MB/s][A[A
model-00001-of-00006.safetensors: 15%|█▌ | 768M/4.97G [00:14<01:04, 65.4MB/s][A
model-00004-of-00006.safetensors: 12%|█▏ | 624M/5.00G [00:14<01:06, 65.6MB/s][A[A
model-00001-of-00006.safetensors: 16%|█▌ | 784M/4.97G [00:15<01:04, 64.4MB/s][A
model-00004-of-00006.safetensors: 13%|█▎ | 640M/5.00G [00:15<01:05, 66.2MB/s][A[A
model-00001-of-00006.safetensors: 16%|█▌ | 800M/4.97G [00:15<01:02, 66.7MB/s][A
model-00004-of-00006.safetensors: 13%|█▎ | 656M/5.00G [00:15<01:04, 66.9MB/s][A[A
model-00001-of-00006.safetensors: 16%|█▋ | 816M/4.97G [00:15<01:02, 66.9MB/s][A
model-00004-of-00006.safetensors: 13%|█▎ | 672M/5.00G [00:15<01:04, 66.7MB/s][A[A
model-00001-of-00006.safetensors: 17%|█▋ | 832M/4.97G [00:15<01:01, 66.9MB/s][A
model-00004-of-00006.safetensors: 14%|█▍ | 688M/5.00G [00:15<01:04, 67.3MB/s][A[A
model-00001-of-00006.safetensors: 17%|█▋ | 848M/4.97G [00:15<00:58, 70.5MB/s][A
model-00004-of-00006.safetensors: 14%|█▍ | 704M/5.00G [00:16<01:04, 66.5MB/s][A[A
model-00001-of-00006.safetensors: 17%|█▋ | 864M/4.97G [00:16<01:00, 68.3MB/s][A
model-00004-of-00006.safetensors: 14%|█▍ | 720M/5.00G [00:16<01:04, 65.9MB/s][A[A
model-00001-of-00006.safetensors: 18%|█▊ | 880M/4.97G [00:16<01:01, 66.8MB/s][A
model-00004-of-00006.safetensors: 15%|█▍ | 735M/5.00G [00:16<00:54, 78.6MB/s][A[A
model-00001-of-00006.safetensors: 18%|█▊ | 896M/4.97G [00:16<01:00, 67.3MB/s][A
model-00001-of-00006.safetensors: 18%|█▊ | 912M/4.97G [00:16<00:59, 67.6MB/s][A
model-00004-of-00006.safetensors: 15%|█▍ | 744M/5.00G [00:16<01:21, 52.2MB/s][A[A
model-00001-of-00006.safetensors: 19%|█▊ | 928M/4.97G [00:17<00:56, 71.2MB/s][A
model-00004-of-00006.safetensors: 15%|█▌ | 752M/5.00G [00:17<01:30, 46.8MB/s][A[A
model-00004-of-00006.safetensors: 15%|█▌ | 768M/5.00G [00:17<01:21, 52.2MB/s][A[A
model-00001-of-00006.safetensors: 19%|█▉ | 944M/4.97G [00:17<01:06, 60.4MB/s][A
model-00004-of-00006.safetensors: 16%|█▌ | 784M/5.00G [00:17<01:15, 56.0MB/s][A[A
model-00001-of-00006.safetensors: 19%|█▉ | 960M/4.97G [00:17<01:03, 63.3MB/s][A
model-00004-of-00006.safetensors: 16%|█▌ | 800M/5.00G [00:17<01:12, 58.1MB/s][A[A
model-00001-of-00006.safetensors: 20%|█▉ | 976M/4.97G [00:17<01:03, 63.0MB/s][A
model-00004-of-00006.safetensors: 16%|█▋ | 816M/5.00G [00:18<01:05, 63.8MB/s][A[A
model-00001-of-00006.safetensors: 20%|█▉ | 992M/4.97G [00:18<01:03, 62.7MB/s][A
model-00004-of-00006.safetensors: 17%|█▋ | 832M/5.00G [00:18<01:05, 63.4MB/s][A[A
model-00001-of-00006.safetensors: 20%|██ | 1.01G/4.97G [00:18<01:00, 65.9MB/s][A
model-00004-of-00006.safetensors: 17%|█▋ | 848M/5.00G [00:18<01:09, 60.1MB/s][A[A
model-00001-of-00006.safetensors: 21%|██ | 1.02G/4.97G [00:18<00:59, 65.8MB/s][A
model-00004-of-00006.safetensors: 17%|█▋ | 864M/5.00G [00:18<01:05, 63.1MB/s][A[A
model-00001-of-00006.safetensors: 21%|██ | 1.04G/4.97G [00:18<01:00, 64.6MB/s][A
model-00004-of-00006.safetensors: 18%|█▊ | 880M/5.00G [00:19<01:04, 63.7MB/s][A[A
model-00001-of-00006.safetensors: 21%|██▏ | 1.06G/4.97G [00:19<00:58, 67.3MB/s][A
model-00004-of-00006.safetensors: 18%|█▊ | 896M/5.00G [00:19<01:04, 64.0MB/s][A[A
model-00001-of-00006.safetensors: 22%|██▏ | 1.07G/4.97G [00:19<01:01, 63.5MB/s][A
model-00004-of-00006.safetensors: 18%|█▊ | 912M/5.00G [00:19<01:02, 65.3MB/s][A[A
model-00001-of-00006.safetensors: 22%|██▏ | 1.09G/4.97G [00:19<01:00, 64.6MB/s][A
model-00004-of-00006.safetensors: 19%|█▊ | 928M/5.00G [00:19<01:03, 64.6MB/s][A[A
model-00001-of-00006.safetensors: 22%|██▏ | 1.10G/4.97G [00:19<00:59, 65.4MB/s][A
model-00004-of-00006.safetensors: 19%|█▉ | 944M/5.00G [00:20<01:03, 64.0MB/s][A[A
model-00001-of-00006.safetensors: 23%|██▎ | 1.12G/4.97G [00:20<00:59, 65.0MB/s][A
model-00004-of-00006.safetensors: 19%|█▉ | 960M/5.00G [00:20<01:01, 65.7MB/s][A[A
model-00001-of-00006.safetensors: 23%|██▎ | 1.14G/4.97G [00:20<00:56, 67.3MB/s][A
model-00004-of-00006.safetensors: 20%|█▉ | 976M/5.00G [00:20<01:15, 53.3MB/s][A[A
model-00001-of-00006.safetensors: 23%|██▎ | 1.15G/4.97G [00:20<01:15, 50.5MB/s][A
model-00004-of-00006.safetensors: 20%|█▉ | 992M/5.00G [00:20<01:11, 56.2MB/s][A[A
model-00001-of-00006.safetensors: 24%|██▎ | 1.17G/4.97G [00:21<01:14, 50.7MB/s][A
model-00004-of-00006.safetensors: 20%|██ | 1.01G/5.00G [00:21<01:06, 60.2MB/s][A[A
model-00001-of-00006.safetensors: 24%|██▍ | 1.18G/4.97G [00:21<01:12, 52.2MB/s][A
model-00001-of-00006.safetensors: 24%|██▍ | 1.20G/4.97G [00:21<01:06, 56.8MB/s][A
model-00004-of-00006.safetensors: 20%|██ | 1.02G/5.00G [00:21<01:32, 43.0MB/s][A[A
model-00001-of-00006.safetensors: 24%|██▍ | 1.22G/4.97G [00:21<01:05, 57.1MB/s][A
model-00004-of-00006.safetensors: 21%|██ | 1.04G/5.00G [00:22<01:21, 48.6MB/s][A[A
model-00001-of-00006.safetensors: 25%|██▍ | 1.23G/4.97G [00:22<01:01, 60.3MB/s][A
model-00004-of-00006.safetensors: 21%|██ | 1.06G/5.00G [00:22<01:15, 52.3MB/s][A[A
model-00001-of-00006.safetensors: 25%|██▌ | 1.25G/4.97G [00:22<00:59, 62.3MB/s][A
model-00004-of-00006.safetensors: 21%|██▏ | 1.07G/5.00G [00:22<01:09, 56.8MB/s][A[A
model-00004-of-00006.safetensors: 22%|██▏ | 1.09G/5.00G [00:22<01:03, 61.5MB/s][A[A
model-00001-of-00006.safetensors: 25%|██▌ | 1.26G/4.97G [00:22<01:13, 50.5MB/s][A
model-00001-of-00006.safetensors: 26%|██▌ | 1.28G/4.97G [00:23<01:08, 53.9MB/s][A
model-00001-of-00006.safetensors: 26%|██▌ | 1.30G/4.97G [00:23<01:03, 57.4MB/s][A
model-00001-of-00006.safetensors: 26%|██▋ | 1.31G/4.97G [00:23<01:03, 57.4MB/s][A
model-00001-of-00006.safetensors: 27%|██▋ | 1.33G/4.97G [00:23<00:59, 61.3MB/s][A
model-00001-of-00006.safetensors: 27%|██▋ | 1.34G/4.97G [00:24<01:02, 57.8MB/s][A
model-00004-of-00006.safetensors: 22%|██▏ | 1.10G/5.00G [00:24<02:26, 26.6MB/s][A[A
model-00004-of-00006.safetensors: 22%|██▏ | 1.12G/5.00G [00:24<01:59, 32.3MB/s][A[A
model-00001-of-00006.safetensors: 27%|██▋ | 1.36G/4.97G [00:24<01:02, 57.9MB/s][A
model-00004-of-00006.safetensors: 23%|██▎ | 1.14G/5.00G [00:24<01:41, 38.0MB/s][A[A
model-00001-of-00006.safetensors: 28%|██▊ | 1.38G/4.97G [00:24<00:59, 59.9MB/s][A
model-00001-of-00006.safetensors: 28%|██▊ | 1.39G/4.97G [00:24<00:59, 60.2MB/s][A
model-00004-of-00006.safetensors: 23%|██▎ | 1.15G/5.00G [00:24<01:35, 40.2MB/s][A[A
model-00004-of-00006.safetensors: 23%|██▎ | 1.17G/5.00G [00:25<01:21, 46.8MB/s][A[A
model-00001-of-00006.safetensors: 28%|██▊ | 1.41G/4.97G [00:25<01:12, 49.4MB/s][A
model-00004-of-00006.safetensors: 24%|██▎ | 1.18G/5.00G [00:25<01:13, 51.9MB/s][A[A
model-00001-of-00006.safetensors: 29%|██▊ | 1.42G/4.97G [00:25<01:03, 55.6MB/s][A
model-00004-of-00006.safetensors: 24%|██▍ | 1.20G/5.00G [00:25<01:08, 55.4MB/s][A[A
model-00001-of-00006.safetensors: 29%|██▉ | 1.44G/4.97G [00:25<01:01, 57.7MB/s][A
model-00004-of-00006.safetensors: 24%|██▍ | 1.22G/5.00G [00:25<01:04, 58.5MB/s][A[A
model-00001-of-00006.safetensors: 29%|██▉ | 1.46G/4.97G [00:26<00:57, 60.9MB/s][A
model-00004-of-00006.safetensors: 25%|██▍ | 1.23G/5.00G [00:26<01:02, 60.4MB/s][A[A
model-00001-of-00006.safetensors: 30%|██▉ | 1.47G/4.97G [00:26<00:54, 64.3MB/s][A
model-00004-of-00006.safetensors: 25%|██▍ | 1.25G/5.00G [00:26<00:59, 62.8MB/s][A[A
model-00001-of-00006.safetensors: 30%|██▉ | 1.49G/4.97G [00:26<00:51, 67.9MB/s][A
model-00004-of-00006.safetensors: 25%|██▌ | 1.26G/5.00G [00:26<00:58, 63.5MB/s][A[A
model-00001-of-00006.safetensors: 30%|███ | 1.50G/4.97G [00:26<00:50, 68.0MB/s][A
model-00004-of-00006.safetensors: 26%|██▌ | 1.28G/5.00G [00:26<00:54, 68.9MB/s][A[A
model-00001-of-00006.safetensors: 31%|███ | 1.52G/4.97G [00:27<00:52, 65.6MB/s][A
model-00004-of-00006.safetensors: 26%|██▌ | 1.30G/5.00G [00:27<00:52, 69.9MB/s][A[A
model-00001-of-00006.safetensors: 31%|███ | 1.54G/4.97G [00:27<00:54, 62.5MB/s][A
model-00004-of-00006.safetensors: 26%|██▌ | 1.31G/5.00G [00:27<00:55, 66.0MB/s][A[A
model-00001-of-00006.safetensors: 31%|███▏ | 1.55G/4.97G [00:27<00:53, 63.8MB/s][A
model-00004-of-00006.safetensors: 27%|██▋ | 1.33G/5.00G [00:27<00:55, 65.8MB/s][A[A
model-00004-of-00006.safetensors: 27%|██▋ | 1.34G/5.00G [00:27<01:07, 53.9MB/s][A[A
model-00001-of-00006.safetensors: 32%|███▏ | 1.57G/4.97G [00:28<01:08, 49.4MB/s][A
model-00004-of-00006.safetensors: 27%|██▋ | 1.36G/5.00G [00:28<01:03, 57.4MB/s][A[A
model-00001-of-00006.safetensors: 32%|███▏ | 1.58G/4.97G [00:28<01:02, 53.9MB/s][A
model-00004-of-00006.safetensors: 28%|██▊ | 1.38G/5.00G [00:28<01:00, 59.4MB/s][A[A
model-00001-of-00006.safetensors: 32%|███▏ | 1.60G/4.97G [00:28<00:59, 56.7MB/s][A
model-00004-of-00006.safetensors: 28%|██▊ | 1.39G/5.00G [00:28<00:59, 60.9MB/s][A[A
model-00001-of-00006.safetensors: 33%|███▎ | 1.62G/4.97G [00:28<00:59, 56.1MB/s][A
model-00004-of-00006.safetensors: 28%|██▊ | 1.41G/5.00G [00:28<00:58, 61.4MB/s][A[A
model-00001-of-00006.safetensors: 33%|███▎ | 1.63G/4.97G [00:29<00:57, 58.5MB/s][A
model-00004-of-00006.safetensors: 28%|██▊ | 1.42G/5.00G [00:29<00:57, 61.7MB/s][A[A
model-00001-of-00006.safetensors: 33%|███▎ | 1.65G/4.97G [00:29<00:54, 61.3MB/s][A
model-00004-of-00006.safetensors: 29%|██▉ | 1.44G/5.00G [00:29<00:56, 63.2MB/s][A[A
model-00001-of-00006.safetensors: 34%|███▎ | 1.66G/4.97G [00:29<00:51, 63.8MB/s][A
model-00004-of-00006.safetensors: 29%|██▉ | 1.46G/5.00G [00:29<00:54, 65.0MB/s][A[A
model-00001-of-00006.safetensors: 34%|███▍ | 1.68G/4.97G [00:29<00:53, 61.8MB/s][A
model-00004-of-00006.safetensors: 29%|██▉ | 1.47G/5.00G [00:29<00:56, 62.3MB/s][A[A
model-00001-of-00006.safetensors: 34%|███▍ | 1.70G/4.97G [00:30<00:51, 63.4MB/s][A
model-00004-of-00006.safetensors: 30%|██▉ | 1.49G/5.00G [00:30<00:55, 63.2MB/s][A[A
model-00001-of-00006.safetensors: 34%|███▍ | 1.71G/4.97G [00:30<00:51, 63.6MB/s][A
model-00004-of-00006.safetensors: 30%|███ | 1.50G/5.00G [00:30<00:54, 64.5MB/s][A[A
model-00001-of-00006.safetensors: 35%|███▍ | 1.73G/4.97G [00:30<00:50, 64.0MB/s][A
model-00001-of-00006.safetensors: 35%|███▌ | 1.74G/4.97G [00:30<00:50, 63.7MB/s][A
model-00004-of-00006.safetensors: 30%|███ | 1.52G/5.00G [00:31<01:13, 47.1MB/s][A[A
model-00001-of-00006.safetensors: 35%|███▌ | 1.76G/4.97G [00:31<00:53, 59.6MB/s][A
model-00004-of-00006.safetensors: 31%|███ | 1.54G/5.00G [00:31<01:06, 51.8MB/s][A[A
model-00001-of-00006.safetensors: 36%|███▌ | 1.78G/4.97G [00:31<00:52, 60.3MB/s][A
model-00004-of-00006.safetensors: 31%|███ | 1.55G/5.00G [00:31<01:01, 56.3MB/s][A[A
model-00001-of-00006.safetensors: 36%|███▌ | 1.79G/4.97G [00:31<00:51, 61.7MB/s][A
model-00004-of-00006.safetensors: 31%|███▏ | 1.57G/5.00G [00:31<00:56, 60.8MB/s][A[A
model-00001-of-00006.safetensors: 36%|███▋ | 1.81G/4.97G [00:31<00:46, 67.5MB/s][A
model-00004-of-00006.safetensors: 32%|███▏ | 1.58G/5.00G [00:31<00:54, 62.9MB/s][A[A
model-00001-of-00006.safetensors: 37%|███▋ | 1.82G/4.97G [00:32<00:51, 60.6MB/s][A
model-00004-of-00006.safetensors: 32%|███▏ | 1.60G/5.00G [00:32<00:51, 66.4MB/s][A[A
model-00001-of-00006.safetensors: 37%|███▋ | 1.84G/4.97G [00:32<00:48, 64.2MB/s][A
model-00004-of-00006.safetensors: 32%|███▏ | 1.62G/5.00G [00:32<00:49, 68.5MB/s][A[A
model-00004-of-00006.safetensors: 33%|███▎ | 1.63G/5.00G [00:32<00:53, 62.6MB/s][A[A
model-00004-of-00006.safetensors: 33%|███▎ | 1.65G/5.00G [00:32<00:52, 63.3MB/s][A[A
model-00001-of-00006.safetensors: 37%|███▋ | 1.86G/4.97G [00:33<01:14, 41.7MB/s][A
model-00004-of-00006.safetensors: 33%|███▎ | 1.66G/5.00G [00:33<00:50, 65.7MB/s][A[A
model-00001-of-00006.safetensors: 38%|███▊ | 1.87G/4.97G [00:33<01:10, 43.9MB/s][A
model-00004-of-00006.safetensors: 34%|███▎ | 1.68G/5.00G [00:33<00:54, 61.4MB/s][A[A
model-00001-of-00006.safetensors: 38%|███▊ | 1.89G/4.97G [00:33<01:04, 47.8MB/s][A
model-00004-of-00006.safetensors: 34%|███▍ | 1.70G/5.00G [00:33<00:55, 59.9MB/s][A[A
model-00001-of-00006.safetensors: 38%|███▊ | 1.90G/4.97G [00:33<00:55, 54.9MB/s][A
model-00004-of-00006.safetensors: 34%|███▍ | 1.71G/5.00G [00:33<00:51, 64.2MB/s][A[A
model-00001-of-00006.safetensors: 39%|███▊ | 1.92G/4.97G [00:34<00:51, 59.0MB/s][A
model-00004-of-00006.safetensors: 35%|███▍ | 1.73G/5.00G [00:34<00:50, 64.9MB/s][A[A
model-00001-of-00006.safetensors: 39%|███▉ | 1.94G/4.97G [00:34<00:51, 59.1MB/s][A
model-00004-of-00006.safetensors: 35%|███▍ | 1.74G/5.00G [00:34<00:49, 65.3MB/s][A[A
model-00001-of-00006.safetensors: 39%|███▉ | 1.95G/4.97G [00:34<00:47, 62.8MB/s][A
model-00004-of-00006.safetensors: 35%|███▌ | 1.76G/5.00G [00:34<00:46, 70.1MB/s][A[A
model-00004-of-00006.safetensors: 36%|███▌ | 1.78G/5.00G [00:34<00:46, 68.9MB/s][A[A
model-00001-of-00006.safetensors: 40%|███▉ | 1.97G/4.97G [00:34<00:53, 56.4MB/s][A
model-00001-of-00006.safetensors: 40%|███▉ | 1.98G/4.97G [00:35<00:52, 56.3MB/s][A
model-00001-of-00006.safetensors: 40%|████ | 2.00G/4.97G [00:35<00:48, 61.6MB/s][A
model-00004-of-00006.safetensors: 36%|███▌ | 1.79G/5.00G [00:35<01:05, 49.3MB/s][A[A
model-00001-of-00006.safetensors: 41%|████ | 2.02G/4.97G [00:35<00:47, 62.7MB/s][A
model-00004-of-00006.safetensors: 36%|███▌ | 1.81G/5.00G [00:35<01:00, 52.4MB/s][A[A
model-00001-of-00006.safetensors: 41%|████ | 2.03G/4.97G [00:35<00:42, 68.4MB/s][A
model-00004-of-00006.safetensors: 36%|███▋ | 1.82G/5.00G [00:35<01:04, 49.6MB/s][A[A
model-00001-of-00006.safetensors: 41%|████ | 2.05G/4.97G [00:36<00:43, 67.1MB/s][A
model-00001-of-00006.safetensors: 42%|████▏ | 2.06G/4.97G [00:36<00:43, 66.5MB/s][A
model-00004-of-00006.safetensors: 37%|███▋ | 1.84G/5.00G [00:36<01:07, 47.0MB/s][A[A
model-00001-of-00006.safetensors: 42%|████▏ | 2.08G/4.97G [00:36<00:42, 68.2MB/s][A
model-00004-of-00006.safetensors: 37%|███▋ | 1.86G/5.00G [00:36<01:01, 51.2MB/s][A[A
model-00001-of-00006.safetensors: 42%|████▏ | 2.10G/4.97G [00:36<00:49, 58.6MB/s][A
model-00004-of-00006.safetensors: 37%|███▋ | 1.87G/5.00G [00:36<00:57, 54.0MB/s][A[A
model-00001-of-00006.safetensors: 43%|████▎ | 2.11G/4.97G [00:37<00:43, 65.6MB/s][A
model-00004-of-00006.safetensors: 38%|███▊ | 1.89G/5.00G [00:37<00:52, 58.9MB/s][A[A
model-00001-of-00006.safetensors: 43%|████▎ | 2.13G/4.97G [00:37<00:41, 68.9MB/s][A
model-00004-of-00006.safetensors: 38%|███▊ | 1.90G/5.00G [00:37<00:49, 62.1MB/s][A[A
model-00001-of-00006.safetensors: 43%|████▎ | 2.14G/4.97G [00:37<00:41, 68.6MB/s][A
model-00004-of-00006.safetensors: 38%|███▊ | 1.92G/5.00G [00:37<00:50, 60.8MB/s][A[A
model-00001-of-00006.safetensors: 43%|████▎ | 2.16G/4.97G [00:37<00:41, 67.6MB/s][A
model-00004-of-00006.safetensors: 39%|███▊ | 1.94G/5.00G [00:37<00:49, 62.3MB/s][A[A
model-00001-of-00006.safetensors: 44%|████▍ | 2.18G/4.97G [00:37<00:41, 67.2MB/s][A
model-00004-of-00006.safetensors: 39%|███▉ | 1.95G/5.00G [00:38<00:49, 61.7MB/s][A[A
model-00001-of-00006.safetensors: 44%|████▍ | 2.19G/4.97G [00:38<00:45, 60.6MB/s][A
model-00004-of-00006.safetensors: 39%|███▉ | 1.97G/5.00G [00:38<00:46, 65.6MB/s][A[A
model-00001-of-00006.safetensors: 44%|████▍ | 2.21G/4.97G [00:38<01:02, 44.0MB/s][A
model-00001-of-00006.safetensors: 45%|████▍ | 2.22G/4.97G [00:39<00:53, 50.8MB/s][A
model-00001-of-00006.safetensors: 45%|████▌ | 2.24G/4.97G [00:39<00:50, 54.3MB/s][A
model-00001-of-00006.safetensors: 45%|████▌ | 2.26G/4.97G [00:39<00:45, 60.0MB/s][A
model-00001-of-00006.safetensors: 46%|████▌ | 2.27G/4.97G [00:39<00:43, 62.4MB/s][A
model-00001-of-00006.safetensors: 46%|████▌ | 2.29G/4.97G [00:39<00:41, 64.7MB/s][A
model-00004-of-00006.safetensors: 40%|███▉ | 1.98G/5.00G [00:40<02:17, 21.9MB/s][A[A
model-00001-of-00006.safetensors: 46%|████▋ | 2.30G/4.97G [00:40<00:40, 65.3MB/s][A
model-00004-of-00006.safetensors: 40%|████ | 2.00G/5.00G [00:40<01:49, 27.5MB/s][A[A
model-00001-of-00006.safetensors: 47%|████▋ | 2.32G/4.97G [00:40<00:39, 66.9MB/s][A
model-00004-of-00006.safetensors: 40%|████ | 2.02G/5.00G [00:40<01:28, 33.7MB/s][A[A
model-00001-of-00006.safetensors: 47%|████▋ | 2.34G/4.97G [00:40<00:39, 67.1MB/s][A
model-00004-of-00006.safetensors: 41%|████ | 2.03G/5.00G [00:40<01:15, 39.1MB/s][A[A
model-00001-of-00006.safetensors: 47%|████▋ | 2.35G/4.97G [00:40<00:39, 66.5MB/s][A
model-00001-of-00006.safetensors: 48%|████▊ | 2.37G/4.97G [00:41<00:44, 59.0MB/s][A
model-00004-of-00006.safetensors: 41%|████ | 2.05G/5.00G [00:41<01:13, 40.0MB/s][A[A
model-00001-of-00006.safetensors: 48%|████▊ | 2.38G/4.97G [00:41<00:41, 61.6MB/s][A
model-00004-of-00006.safetensors: 41%|████▏ | 2.06G/5.00G [00:41<01:06, 44.1MB/s][A[A
model-00001-of-00006.safetensors: 48%|████▊ | 2.40G/4.97G [00:41<00:42, 59.7MB/s][A
model-00004-of-00006.safetensors: 42%|████▏ | 2.08G/5.00G [00:41<01:04, 45.5MB/s][A[A
model-00001-of-00006.safetensors: 49%|████▊ | 2.42G/4.97G [00:41<00:38, 65.6MB/s][A
model-00004-of-00006.safetensors: 42%|████▏ | 2.10G/5.00G [00:42<00:55, 52.0MB/s][A[A
model-00001-of-00006.safetensors: 49%|████▉ | 2.43G/4.97G [00:42<00:35, 71.1MB/s][A
model-00004-of-00006.safetensors: 42%|████▏ | 2.11G/5.00G [00:42<00:52, 55.2MB/s][A[A
model-00001-of-00006.safetensors: 49%|████▉ | 2.45G/4.97G [00:42<00:36, 68.8MB/s][A
model-00004-of-00006.safetensors: 43%|████▎ | 2.13G/5.00G [00:42<00:49, 58.2MB/s][A[A
model-00001-of-00006.safetensors: 50%|████▉ | 2.46G/4.97G [00:42<00:35, 70.5MB/s][A
model-00001-of-00006.safetensors: 50%|████▉ | 2.48G/4.97G [00:42<00:34, 71.1MB/s][A
model-00004-of-00006.safetensors: 43%|████▎ | 2.14G/5.00G [00:42<00:50, 57.1MB/s][A[A
model-00004-of-00006.safetensors: 43%|████▎ | 2.16G/5.00G [00:43<00:43, 65.1MB/s][A[A
model-00001-of-00006.safetensors: 50%|█████ | 2.50G/4.97G [00:43<00:35, 70.3MB/s][A
model-00001-of-00006.safetensors: 51%|█████ | 2.51G/4.97G [00:43<00:34, 70.5MB/s][A
model-00001-of-00006.safetensors: 51%|█████ | 2.53G/4.97G [00:43<00:36, 67.5MB/s][A
model-00001-of-00006.safetensors: 51%|█████ | 2.54G/4.97G [00:43<00:41, 58.2MB/s][A
model-00001-of-00006.safetensors: 52%|█████▏ | 2.56G/4.97G [00:44<00:39, 60.5MB/s][A
model-00004-of-00006.safetensors: 44%|████▎ | 2.18G/5.00G [00:44<01:35, 29.4MB/s][A[A
model-00001-of-00006.safetensors: 52%|█████▏ | 2.58G/4.97G [00:44<00:40, 58.8MB/s][A
model-00004-of-00006.safetensors: 44%|████▍ | 2.19G/5.00G [00:44<01:19, 35.3MB/s][A[A
model-00004-of-00006.safetensors: 44%|████▍ | 2.21G/5.00G [00:44<01:07, 41.6MB/s][A[A
model-00004-of-00006.safetensors: 44%|████▍ | 2.22G/5.00G [00:44<00:59, 46.3MB/s][A[A
model-00004-of-00006.safetensors: 45%|████▍ | 2.24G/5.00G [00:45<00:54, 50.8MB/s][A[A
model-00004-of-00006.safetensors: 45%|████▌ | 2.26G/5.00G [00:45<00:50, 54.7MB/s][A[A
model-00004-of-00006.safetensors: 45%|████▌ | 2.27G/5.00G [00:45<00:46, 58.2MB/s][A[A
model-00001-of-00006.safetensors: 52%|█████▏ | 2.59G/4.97G [00:45<01:25, 27.8MB/s][A
model-00004-of-00006.safetensors: 46%|████▌ | 2.29G/5.00G [00:45<00:45, 59.6MB/s][A[A
model-00001-of-00006.safetensors: 53%|█████▎ | 2.61G/4.97G [00:45<01:10, 33.5MB/s][A
model-00004-of-00006.safetensors: 46%|████▌ | 2.30G/5.00G [00:46<00:42, 63.2MB/s][A[A
model-00001-of-00006.safetensors: 53%|█████▎ | 2.62G/4.97G [00:46<01:00, 38.5MB/s][A
model-00001-of-00006.safetensors: 53%|█████▎ | 2.64G/4.97G [00:46<00:53, 43.6MB/s][A
model-00004-of-00006.safetensors: 46%|████▋ | 2.32G/5.00G [00:46<00:49, 54.3MB/s][A[A
model-00001-of-00006.safetensors: 53%|█████▎ | 2.66G/4.97G [00:46<00:48, 47.3MB/s][A
model-00004-of-00006.safetensors: 47%|████▋ | 2.34G/5.00G [00:46<00:45, 58.4MB/s][A[A
model-00001-of-00006.safetensors: 54%|█████▍ | 2.67G/4.97G [00:47<00:44, 51.6MB/s][A
model-00004-of-00006.safetensors: 47%|████▋ | 2.35G/5.00G [00:47<00:50, 52.9MB/s][A[A
model-00001-of-00006.safetensors: 54%|█████▍ | 2.69G/4.97G [00:47<00:42, 53.8MB/s][A
model-00004-of-00006.safetensors: 47%|████▋ | 2.37G/5.00G [00:47<00:46, 56.9MB/s][A[A
model-00001-of-00006.safetensors: 54%|█████▍ | 2.70G/4.97G [00:47<00:39, 57.8MB/s][A
model-00004-of-00006.safetensors: 48%|████▊ | 2.38G/5.00G [00:47<00:43, 60.2MB/s][A[A
model-00001-of-00006.safetensors: 55%|█████▍ | 2.72G/4.97G [00:47<00:36, 60.9MB/s][A
model-00004-of-00006.safetensors: 48%|████▊ | 2.40G/5.00G [00:47<00:42, 61.6MB/s][A[A
model-00001-of-00006.safetensors: 55%|█████▌ | 2.74G/4.97G [00:47<00:35, 63.0MB/s][A
model-00004-of-00006.safetensors: 48%|████▊ | 2.42G/5.00G [00:48<00:41, 62.0MB/s][A[A
model-00001-of-00006.safetensors: 55%|█████▌ | 2.75G/4.97G [00:48<00:34, 63.8MB/s][A
model-00001-of-00006.safetensors: 56%|█████▌ | 2.77G/4.97G [00:48<00:34, 64.1MB/s][A
model-00004-of-00006.safetensors: 49%|████▊ | 2.43G/5.00G [00:48<00:46, 54.8MB/s][A[A
model-00001-of-00006.safetensors: 56%|█████▌ | 2.78G/4.97G [00:48<00:34, 63.6MB/s][A
model-00004-of-00006.safetensors: 49%|████▉ | 2.45G/5.00G [00:48<00:55, 45.7MB/s][A[A
model-00001-of-00006.safetensors: 56%|█████▋ | 2.80G/4.97G [00:48<00:35, 61.6MB/s][A
model-00001-of-00006.safetensors: 57%|█████▋ | 2.82G/4.97G [00:49<00:33, 64.5MB/s][A
model-00004-of-00006.safetensors: 49%|████▉ | 2.46G/5.00G [00:49<00:54, 46.9MB/s][A[A
model-00001-of-00006.safetensors: 57%|█████▋ | 2.83G/4.97G [00:49<00:33, 63.7MB/s][A
model-00004-of-00006.safetensors: 50%|████▉ | 2.48G/5.00G [00:49<00:48, 51.7MB/s][A[A
model-00001-of-00006.safetensors: 57%|█████▋ | 2.85G/4.97G [00:49<00:32, 64.5MB/s][A
model-00004-of-00006.safetensors: 50%|████▉ | 2.50G/5.00G [00:49<00:44, 56.1MB/s][A[A
model-00004-of-00006.safetensors: 50%|█████ | 2.51G/5.00G [00:49<00:41, 60.5MB/s][A[A
model-00001-of-00006.safetensors: 58%|█████▊ | 2.86G/4.97G [00:49<00:33, 63.4MB/s][A
model-00004-of-00006.safetensors: 51%|█████ | 2.53G/5.00G [00:50<00:38, 64.3MB/s][A[A
model-00001-of-00006.safetensors: 58%|█████▊ | 2.88G/4.97G [00:50<00:32, 63.2MB/s][A
model-00001-of-00006.safetensors: 58%|█████▊ | 2.90G/4.97G [00:50<00:31, 65.8MB/s][A
model-00001-of-00006.safetensors: 59%|█████▊ | 2.91G/4.97G [00:50<00:29, 70.7MB/s][A
model-00004-of-00006.safetensors: 51%|█████ | 2.54G/5.00G [00:50<00:47, 51.2MB/s][A[A
model-00001-of-00006.safetensors: 59%|█████▉ | 2.93G/4.97G [00:50<00:29, 69.6MB/s][A
model-00004-of-00006.safetensors: 51%|█████ | 2.56G/5.00G [00:50<00:44, 54.5MB/s][A[A
model-00004-of-00006.safetensors: 52%|█████▏ | 2.58G/5.00G [00:51<00:43, 56.0MB/s][A[A
model-00001-of-00006.safetensors: 59%|█████▉ | 2.94G/4.97G [00:51<00:39, 51.2MB/s][A
model-00004-of-00006.safetensors: 52%|█████▏ | 2.59G/5.00G [00:51<00:43, 55.8MB/s][A[A
model-00001-of-00006.safetensors: 60%|█████▉ | 2.96G/4.97G [00:51<00:36, 55.5MB/s][A
model-00004-of-00006.safetensors: 52%|█████▏ | 2.61G/5.00G [00:51<00:41, 57.6MB/s][A[A
model-00001-of-00006.safetensors: 60%|█████▉ | 2.98G/4.97G [00:51<00:35, 56.7MB/s][A
model-00001-of-00006.safetensors: 60%|██████ | 2.99G/4.97G [00:52<00:35, 55.7MB/s][A
model-00001-of-00006.safetensors: 61%|██████ | 3.01G/4.97G [00:52<00:32, 59.7MB/s][A
model-00004-of-00006.safetensors: 52%|█████▏ | 2.62G/5.00G [00:52<01:05, 36.1MB/s][A[A
model-00001-of-00006.safetensors: 61%|██████ | 3.02G/4.97G [00:52<00:31, 60.8MB/s][A
model-00004-of-00006.safetensors: 53%|█████▎ | 2.64G/5.00G [00:52<00:56, 42.0MB/s][A[A
model-00001-of-00006.safetensors: 61%|██████ | 3.04G/4.97G [00:52<00:30, 63.9MB/s][A
model-00004-of-00006.safetensors: 53%|█████▎ | 2.66G/5.00G [00:53<00:50, 46.7MB/s][A[A
model-00001-of-00006.safetensors: 62%|██████▏ | 3.06G/4.97G [00:53<00:28, 66.3MB/s][A
model-00004-of-00006.safetensors: 53%|█████▎ | 2.67G/5.00G [00:53<00:45, 51.1MB/s][A[A
model-00001-of-00006.safetensors: 62%|██████▏ | 3.07G/4.97G [00:53<00:27, 68.3MB/s][A
model-00004-of-00006.safetensors: 54%|█████▍ | 2.69G/5.00G [00:53<00:42, 54.2MB/s][A[A
model-00001-of-00006.safetensors: 62%|██████▏ | 3.09G/4.97G [00:53<00:28, 67.0MB/s][A
model-00004-of-00006.safetensors: 54%|█████▍ | 2.70G/5.00G [00:53<00:40, 57.0MB/s][A[A
model-00001-of-00006.safetensors: 63%|██████▎ | 3.10G/4.97G [00:53<00:29, 62.3MB/s][A
model-00004-of-00006.safetensors: 54%|█████▍ | 2.72G/5.00G [00:54<00:38, 59.1MB/s][A[A
model-00001-of-00006.safetensors: 63%|██████▎ | 3.12G/4.97G [00:54<00:29, 63.3MB/s][A
model-00001-of-00006.safetensors: 63%|██████▎ | 3.14G/4.97G [00:54<00:28, 64.1MB/s][A
model-00004-of-00006.safetensors: 55%|█████▍ | 2.74G/5.00G [00:54<00:41, 54.6MB/s][A[A
model-00001-of-00006.safetensors: 63%|██████▎ | 3.15G/4.97G [00:54<00:28, 64.5MB/s][A
model-00004-of-00006.safetensors: 55%|█████▌ | 2.75G/5.00G [00:54<00:39, 57.1MB/s][A[A
model-00001-of-00006.safetensors: 64%|██████▍ | 3.17G/4.97G [00:54<00:27, 65.9MB/s][A
model-00004-of-00006.safetensors: 55%|█████▌ | 2.77G/5.00G [00:54<00:36, 60.3MB/s][A[A
model-00001-of-00006.safetensors: 64%|██████▍ | 3.18G/4.97G [00:55<00:26, 66.4MB/s][A
model-00004-of-00006.safetensors: 56%|█████▌ | 2.78G/5.00G [00:55<00:35, 62.1MB/s][A[A
model-00004-of-00006.safetensors: 56%|█████▌ | 2.80G/5.00G [00:55<00:33, 66.6MB/s][A[A
model-00001-of-00006.safetensors: 64%|██████▍ | 3.20G/4.97G [00:55<00:27, 64.4MB/s][A
model-00004-of-00006.safetensors: 56%|█████▋ | 2.82G/5.00G [00:55<00:33, 65.6MB/s][A[A
model-00001-of-00006.safetensors: 65%|██████▍ | 3.22G/4.97G [00:55<00:28, 60.9MB/s][A
model-00004-of-00006.safetensors: 57%|█████▋ | 2.83G/5.00G [00:55<00:32, 66.0MB/s][A[A
model-00001-of-00006.safetensors: 65%|██████▌ | 3.23G/4.97G [00:55<00:26, 65.3MB/s][A
model-00004-of-00006.safetensors: 57%|█████▋ | 2.85G/5.00G [00:55<00:32, 67.0MB/s][A[A
model-00001-of-00006.safetensors: 65%|██████▌ | 3.25G/4.97G [00:56<00:26, 63.8MB/s][A
model-00004-of-00006.safetensors: 57%|█████▋ | 2.86G/5.00G [00:56<00:31, 66.8MB/s][A[A
model-00001-of-00006.safetensors: 66%|██████▌ | 3.26G/4.97G [00:56<00:25, 67.2MB/s][A
model-00004-of-00006.safetensors: 58%|█████▊ | 2.88G/5.00G [00:56<00:31, 67.6MB/s][A[A
model-00001-of-00006.safetensors: 66%|██████▌ | 3.28G/4.97G [00:56<00:23, 71.8MB/s][A
model-00001-of-00006.safetensors: 66%|██████▋ | 3.30G/4.97G [00:56<00:24, 69.1MB/s][A
model-00004-of-00006.safetensors: 58%|█████▊ | 2.90G/5.00G [00:56<00:32, 65.2MB/s][A[A
model-00004-of-00006.safetensors: 58%|█████▊ | 2.91G/5.00G [00:56<00:32, 64.9MB/s][A[A
model-00001-of-00006.safetensors: 67%|██████▋ | 3.31G/4.97G [00:57<00:27, 60.9MB/s][A
model-00004-of-00006.safetensors: 59%|█████▊ | 2.93G/5.00G [00:57<00:30, 67.4MB/s][A[A
model-00001-of-00006.safetensors: 67%|██████▋ | 3.33G/4.97G [00:57<00:26, 61.1MB/s][A
model-00001-of-00006.safetensors: 67%|██████▋ | 3.34G/4.97G [00:57<00:25, 62.9MB/s][A
model-00004-of-00006.safetensors: 59%|█████▉ | 2.94G/5.00G [00:57<00:36, 56.3MB/s][A[A
model-00001-of-00006.safetensors: 68%|██████▊ | 3.36G/4.97G [00:57<00:25, 62.3MB/s][A
model-00004-of-00006.safetensors: 59%|█████▉ | 2.96G/5.00G [00:57<00:34, 59.0MB/s][A[A
model-00001-of-00006.safetensors: 68%|██████▊ | 3.38G/4.97G [00:58<00:24, 64.5MB/s][A
model-00004-of-00006.safetensors: 60%|█████▉ | 2.98G/5.00G [00:58<00:32, 61.7MB/s][A[A
model-00004-of-00006.safetensors: 60%|█████▉ | 2.99G/5.00G [00:58<00:31, 62.8MB/s][A[A
model-00001-of-00006.safetensors: 68%|██████▊ | 3.39G/4.97G [00:58<00:24, 63.4MB/s][A
model-00004-of-00006.safetensors: 60%|██████ | 3.01G/5.00G [00:58<00:30, 64.7MB/s][A[A
model-00004-of-00006.safetensors: 60%|██████ | 3.01G/5.00G [00:58<00:37, 52.3MB/s][A[A
model-00004-of-00006.safetensors: 60%|██████ | 3.02G/5.00G [00:58<00:36, 53.9MB/s][A[A
model-00004-of-00006.safetensors: 61%|██████ | 3.04G/5.00G [00:59<00:48, 40.4MB/s][A[A
model-00004-of-00006.safetensors: 61%|██████ | 3.06G/5.00G [00:59<00:41, 47.4MB/s][A[A
model-00004-of-00006.safetensors: 61%|██████▏ | 3.07G/5.00G [00:59<00:36, 52.8MB/s][A[A
model-00004-of-00006.safetensors: 62%|██████▏ | 3.09G/5.00G [01:00<00:34, 54.8MB/s][A[A
model-00004-of-00006.safetensors: 62%|██████▏ | 3.10G/5.00G [01:00<00:33, 57.4MB/s][A[A
model-00004-of-00006.safetensors: 62%|██████▏ | 3.12G/5.00G [01:00<00:31, 60.3MB/s][A[A
model-00004-of-00006.safetensors: 63%|██████▎ | 3.14G/5.00G [01:00<00:27, 66.8MB/s][A[A
model-00001-of-00006.safetensors: 69%|██████▊ | 3.41G/4.97G [01:01<01:38, 15.8MB/s][A
model-00004-of-00006.safetensors: 63%|██████▎ | 3.15G/5.00G [01:01<00:26, 68.7MB/s][A[A
model-00001-of-00006.safetensors: 69%|██████▉ | 3.42G/4.97G [01:01<01:15, 20.5MB/s][A
model-00004-of-00006.safetensors: 63%|██████▎ | 3.17G/5.00G [01:01<00:27, 66.0MB/s][A[A
model-00001-of-00006.safetensors: 69%|██████▉ | 3.44G/4.97G [01:01<00:59, 25.7MB/s][A
model-00004-of-00006.safetensors: 64%|██████▎ | 3.18G/5.00G [01:01<00:27, 65.8MB/s][A[A
model-00004-of-00006.safetensors: 64%|██████▍ | 3.20G/5.00G [01:01<00:27, 65.7MB/s][A[A
model-00004-of-00006.safetensors: 64%|██████▍ | 3.22G/5.00G [01:02<00:26, 67.0MB/s][A[A
model-00001-of-00006.safetensors: 70%|██████▉ | 3.46G/4.97G [01:02<00:56, 26.5MB/s][A
model-00004-of-00006.safetensors: 65%|██████▍ | 3.23G/5.00G [01:02<00:27, 65.3MB/s][A[A
model-00001-of-00006.safetensors: 70%|██████▉ | 3.47G/4.97G [01:02<00:54, 27.5MB/s][A
model-00004-of-00006.safetensors: 65%|██████▍ | 3.25G/5.00G [01:02<00:29, 59.5MB/s][A[A
model-00001-of-00006.safetensors: 70%|███████ | 3.49G/4.97G [01:02<00:42, 34.6MB/s][A
model-00004-of-00006.safetensors: 65%|██████▌ | 3.26G/5.00G [01:02<00:29, 58.8MB/s][A[A
model-00001-of-00006.safetensors: 71%|███████ | 3.50G/4.97G [01:03<00:35, 41.4MB/s][A
model-00004-of-00006.safetensors: 66%|██████▌ | 3.28G/5.00G [01:03<00:28, 60.2MB/s][A[A
model-00001-of-00006.safetensors: 71%|███████ | 3.52G/4.97G [01:03<00:34, 41.4MB/s][A
model-00004-of-00006.safetensors: 66%|██████▌ | 3.30G/5.00G [01:03<00:27, 61.9MB/s][A[A
model-00004-of-00006.safetensors: 66%|██████▌ | 3.31G/5.00G [01:03<00:25, 66.9MB/s][A[A
model-00001-of-00006.safetensors: 71%|███████ | 3.54G/4.97G [01:03<00:30, 46.2MB/s][A
model-00004-of-00006.safetensors: 67%|██████▋ | 3.33G/5.00G [01:03<00:25, 66.0MB/s][A[A
model-00004-of-00006.safetensors: 67%|██████▋ | 3.34G/5.00G [01:04<00:24, 67.9MB/s][A[A
model-00004-of-00006.safetensors: 67%|██████▋ | 3.36G/5.00G [01:04<00:24, 65.6MB/s][A[A
model-00001-of-00006.safetensors: 72%|███████▏ | 3.55G/4.97G [01:04<00:41, 34.1MB/s][A
model-00004-of-00006.safetensors: 68%|██████▊ | 3.38G/5.00G [01:04<00:25, 64.7MB/s][A[A
model-00001-of-00006.safetensors: 72%|███████▏ | 3.57G/4.97G [01:04<00:35, 39.6MB/s][A
model-00004-of-00006.safetensors: 68%|██████▊ | 3.39G/5.00G [01:04<00:24, 65.8MB/s][A[A
model-00001-of-00006.safetensors: 72%|███████▏ | 3.58G/4.97G [01:04<00:31, 44.5MB/s][A
model-00004-of-00006.safetensors: 68%|██████▊ | 3.41G/5.00G [01:05<00:23, 67.4MB/s][A[A
model-00001-of-00006.safetensors: 72%|███████▏ | 3.60G/4.97G [01:05<00:28, 48.6MB/s][A
model-00004-of-00006.safetensors: 68%|██████▊ | 3.42G/5.00G [01:05<00:23, 66.9MB/s][A[A
model-00001-of-00006.safetensors: 73%|███████▎ | 3.62G/4.97G [01:05<00:25, 53.0MB/s][A
model-00004-of-00006.safetensors: 69%|██████▉ | 3.44G/5.00G [01:05<00:23, 67.4MB/s][A[A
model-00001-of-00006.safetensors: 73%|███████▎ | 3.63G/4.97G [01:05<00:23, 56.1MB/s][A
model-00004-of-00006.safetensors: 69%|██████▉ | 3.46G/5.00G [01:05<00:23, 66.0MB/s][A[A
model-00004-of-00006.safetensors: 69%|██████▉ | 3.47G/5.00G [01:06<00:23, 65.2MB/s][A[A
model-00004-of-00006.safetensors: 70%|██████▉ | 3.49G/5.00G [01:06<00:21, 69.9MB/s][A[A
model-00001-of-00006.safetensors: 73%|███████▎ | 3.65G/4.97G [01:06<00:35, 36.9MB/s][A
model-00004-of-00006.safetensors: 70%|███████ | 3.50G/5.00G [01:06<00:21, 69.8MB/s][A[A
model-00001-of-00006.safetensors: 74%|███████▍ | 3.66G/4.97G [01:06<00:31, 41.8MB/s][A
model-00004-of-00006.safetensors: 70%|███████ | 3.52G/5.00G [01:06<00:21, 68.3MB/s][A[A
model-00001-of-00006.safetensors: 74%|███████▍ | 3.68G/4.97G [01:06<00:26, 49.3MB/s][A
model-00004-of-00006.safetensors: 71%|███████ | 3.54G/5.00G [01:07<00:22, 66.5MB/s][A[A
model-00001-of-00006.safetensors: 74%|███████▍ | 3.70G/4.97G [01:07<00:24, 52.1MB/s][A
model-00004-of-00006.safetensors: 71%|███████ | 3.55G/5.00G [01:07<00:21, 66.7MB/s][A[A
model-00001-of-00006.safetensors: 75%|███████▍ | 3.71G/4.97G [01:07<00:22, 56.0MB/s][A
model-00004-of-00006.safetensors: 71%|███████▏ | 3.57G/5.00G [01:07<00:21, 67.1MB/s][A[A
model-00001-of-00006.safetensors: 75%|███████▌ | 3.73G/4.97G [01:07<00:22, 53.8MB/s][A
model-00004-of-00006.safetensors: 72%|███████▏ | 3.58G/5.00G [01:08<00:31, 45.0MB/s][A[A
model-00001-of-00006.safetensors: 75%|███████▌ | 3.74G/4.97G [01:08<00:27, 44.5MB/s][A
model-00004-of-00006.safetensors: 72%|███████▏ | 3.60G/5.00G [01:08<00:27, 51.4MB/s][A[A
model-00001-of-00006.safetensors: 76%|███████▌ | 3.76G/4.97G [01:08<00:24, 49.2MB/s][A
model-00004-of-00006.safetensors: 72%|███████▏ | 3.62G/5.00G [01:08<00:29, 46.9MB/s][A[A
model-00001-of-00006.safetensors: 76%|███████▌ | 3.78G/4.97G [01:08<00:22, 52.9MB/s][A
model-00004-of-00006.safetensors: 73%|███████▎ | 3.63G/5.00G [01:08<00:26, 51.6MB/s][A[A
model-00001-of-00006.safetensors: 76%|███████▋ | 3.79G/4.97G [01:09<00:20, 57.0MB/s][A
model-00004-of-00006.safetensors: 73%|███████▎ | 3.65G/5.00G [01:09<00:23, 57.0MB/s][A[A
model-00001-of-00006.safetensors: 77%|███████▋ | 3.81G/4.97G [01:09<00:19, 59.7MB/s][A
model-00001-of-00006.safetensors: 77%|███████▋ | 3.82G/4.97G [01:09<00:17, 64.9MB/s][A
model-00004-of-00006.safetensors: 73%|███████▎ | 3.66G/5.00G [01:09<00:23, 56.7MB/s][A[A
model-00004-of-00006.safetensors: 74%|███████▎ | 3.68G/5.00G [01:09<00:23, 57.2MB/s][A[A
model-00001-of-00006.safetensors: 77%|███████▋ | 3.84G/4.97G [01:09<00:19, 57.6MB/s][A
model-00004-of-00006.safetensors: 74%|███████▍ | 3.70G/5.00G [01:10<00:22, 58.3MB/s][A[A
model-00001-of-00006.safetensors: 78%|███████▊ | 3.86G/4.97G [01:10<00:18, 59.2MB/s][A
model-00004-of-00006.safetensors: 74%|███████▍ | 3.71G/5.00G [01:10<00:20, 62.6MB/s][A[A
model-00001-of-00006.safetensors: 78%|███████▊ | 3.87G/4.97G [01:10<00:17, 60.9MB/s][A
model-00004-of-00006.safetensors: 75%|███████▍ | 3.73G/5.00G [01:10<00:19, 64.1MB/s][A[A
model-00001-of-00006.safetensors: 78%|███████▊ | 3.89G/4.97G [01:10<00:17, 61.5MB/s][A
model-00004-of-00006.safetensors: 75%|███████▍ | 3.74G/5.00G [01:10<00:19, 63.7MB/s][A[A
model-00001-of-00006.safetensors: 79%|███████▊ | 3.90G/4.97G [01:10<00:16, 63.0MB/s][A
model-00004-of-00006.safetensors: 75%|███████▌ | 3.76G/5.00G [01:10<00:18, 65.9MB/s][A[A
model-00001-of-00006.safetensors: 79%|███████▉ | 3.92G/4.97G [01:11<00:17, 60.9MB/s][A
model-00004-of-00006.safetensors: 76%|███████▌ | 3.78G/5.00G [01:11<00:18, 67.8MB/s][A[A
model-00001-of-00006.safetensors: 79%|███████▉ | 3.94G/4.97G [01:11<00:16, 60.8MB/s][A
model-00004-of-00006.safetensors: 76%|███████▌ | 3.79G/5.00G [01:11<00:18, 66.4MB/s][A[A
model-00001-of-00006.safetensors: 80%|███████▉ | 3.95G/4.97G [01:11<00:15, 66.7MB/s][A
model-00004-of-00006.safetensors: 76%|███████▌ | 3.81G/5.00G [01:11<00:17, 68.8MB/s][A[A
model-00001-of-00006.safetensors: 80%|███████▉ | 3.97G/4.97G [01:11<00:14, 66.9MB/s][A
model-00004-of-00006.safetensors: 76%|███████▋ | 3.82G/5.00G [01:11<00:17, 65.5MB/s][A[A
model-00001-of-00006.safetensors: 80%|████████ | 3.98G/4.97G [01:12<00:14, 67.7MB/s][A
model-00004-of-00006.safetensors: 77%|███████▋ | 3.84G/5.00G [01:12<00:18, 62.1MB/s][A[A
model-00001-of-00006.safetensors: 81%|████████ | 4.00G/4.97G [01:12<00:13, 70.4MB/s][A
model-00004-of-00006.safetensors: 77%|███████▋ | 3.86G/5.00G [01:12<00:17, 64.0MB/s][A[A
model-00001-of-00006.safetensors: 81%|████████ | 4.02G/4.97G [01:12<00:13, 70.3MB/s][A
model-00001-of-00006.safetensors: 81%|████████ | 4.03G/4.97G [01:12<00:13, 70.2MB/s][A
model-00004-of-00006.safetensors: 77%|███████▋ | 3.87G/5.00G [01:12<00:21, 53.0MB/s][A[A
model-00001-of-00006.safetensors: 82%|████████▏ | 4.05G/4.97G [01:12<00:13, 66.6MB/s][A
model-00004-of-00006.safetensors: 78%|███████▊ | 3.89G/5.00G [01:13<00:19, 57.2MB/s][A[A
model-00001-of-00006.safetensors: 82%|████████▏ | 4.06G/4.97G [01:13<00:13, 65.7MB/s][A
model-00004-of-00006.safetensors: 78%|███████▊ | 3.90G/5.00G [01:13<00:17, 61.6MB/s][A[A
model-00001-of-00006.safetensors: 82%|████████▏ | 4.08G/4.97G [01:13<00:13, 66.7MB/s][A
model-00004-of-00006.safetensors: 78%|███████▊ | 3.92G/5.00G [01:13<00:17, 61.1MB/s][A[A
model-00001-of-00006.safetensors: 82%|████████▏ | 4.10G/4.97G [01:13<00:13, 64.6MB/s][A
model-00004-of-00006.safetensors: 79%|███████▊ | 3.94G/5.00G [01:13<00:17, 59.8MB/s][A[A
model-00001-of-00006.safetensors: 83%|████████▎ | 4.11G/4.97G [01:13<00:13, 61.7MB/s][A
model-00004-of-00006.safetensors: 79%|███████▉ | 3.95G/5.00G [01:14<00:18, 57.1MB/s][A[A
model-00001-of-00006.safetensors: 83%|████████▎ | 4.13G/4.97G [01:14<00:13, 63.8MB/s][A
model-00001-of-00006.safetensors: 83%|████████▎ | 4.14G/4.97G [01:14<00:12, 66.6MB/s][A
model-00004-of-00006.safetensors: 79%|███████▉ | 3.97G/5.00G [01:14<00:20, 50.0MB/s][A[A
model-00001-of-00006.safetensors: 84%|████████▍ | 4.16G/4.97G [01:14<00:12, 66.5MB/s][A
model-00004-of-00006.safetensors: 80%|███████▉ | 3.98G/5.00G [01:14<00:19, 52.9MB/s][A[A
model-00001-of-00006.safetensors: 84%|████████▍ | 4.18G/4.97G [01:14<00:11, 66.7MB/s][A
model-00004-of-00006.safetensors: 80%|████████ | 4.00G/5.00G [01:15<00:17, 55.9MB/s][A[A
model-00001-of-00006.safetensors: 84%|████████▍ | 4.19G/4.97G [01:15<00:11, 67.9MB/s][A
model-00004-of-00006.safetensors: 80%|████████ | 4.02G/5.00G [01:15<00:17, 55.8MB/s][A[A
model-00001-of-00006.safetensors: 85%|████████▍ | 4.21G/4.97G [01:15<00:11, 66.8MB/s][A
model-00004-of-00006.safetensors: 81%|████████ | 4.03G/5.00G [01:15<00:16, 58.7MB/s][A[A
model-00001-of-00006.safetensors: 85%|████████▌ | 4.22G/4.97G [01:15<00:11, 66.9MB/s][A
model-00004-of-00006.safetensors: 81%|████████ | 4.05G/5.00G [01:15<00:15, 61.6MB/s][A[A
model-00001-of-00006.safetensors: 85%|████████▌ | 4.24G/4.97G [01:15<00:10, 66.7MB/s][A
model-00004-of-00006.safetensors: 81%|████████▏ | 4.06G/5.00G [01:16<00:14, 63.0MB/s][A[A
model-00001-of-00006.safetensors: 86%|████████▌ | 4.26G/4.97G [01:16<00:11, 62.8MB/s][A
model-00004-of-00006.safetensors: 82%|████████▏ | 4.08G/5.00G [01:16<00:13, 69.2MB/s][A[A
model-00001-of-00006.safetensors: 86%|████████▌ | 4.27G/4.97G [01:16<00:11, 62.5MB/s][A
model-00004-of-00006.safetensors: 82%|████████▏ | 4.10G/5.00G [01:16<00:13, 66.7MB/s][A[A
model-00001-of-00006.safetensors: 86%|████████▋ | 4.29G/4.97G [01:16<00:11, 61.4MB/s][A
model-00004-of-00006.safetensors: 82%|████████▏ | 4.11G/5.00G [01:16<00:14, 62.1MB/s][A[A
model-00001-of-00006.safetensors: 87%|████████▋ | 4.30G/4.97G [01:16<00:10, 61.3MB/s][A
model-00004-of-00006.safetensors: 83%|████████▎ | 4.13G/5.00G [01:17<00:13, 62.5MB/s][A[A
model-00001-of-00006.safetensors: 87%|████████▋ | 4.32G/4.97G [01:17<00:10, 64.3MB/s][A
model-00004-of-00006.safetensors: 83%|████████▎ | 4.14G/5.00G [01:17<00:13, 63.9MB/s][A[A
model-00001-of-00006.safetensors: 87%|████████▋ | 4.34G/4.97G [01:17<00:09, 64.7MB/s][A
model-00004-of-00006.safetensors: 83%|████████▎ | 4.16G/5.00G [01:17<00:14, 59.8MB/s][A[A
model-00001-of-00006.safetensors: 88%|████████▊ | 4.35G/4.97G [01:17<00:09, 66.0MB/s][A
model-00004-of-00006.safetensors: 84%|████████▎ | 4.18G/5.00G [01:17<00:13, 61.7MB/s][A[A
model-00001-of-00006.safetensors: 88%|████████▊ | 4.37G/4.97G [01:17<00:08, 67.5MB/s][A
model-00001-of-00006.safetensors: 88%|████████▊ | 4.38G/4.97G [01:18<00:08, 68.8MB/s][A
model-00004-of-00006.safetensors: 84%|████████▍ | 4.19G/5.00G [01:18<00:14, 54.7MB/s][A[A
model-00001-of-00006.safetensors: 89%|████████▊ | 4.40G/4.97G [01:18<00:08, 67.8MB/s][A
model-00004-of-00006.safetensors: 84%|████████▍ | 4.21G/5.00G [01:18<00:13, 59.0MB/s][A[A
model-00001-of-00006.safetensors: 89%|████████▉ | 4.42G/4.97G [01:18<00:08, 62.7MB/s][A
model-00004-of-00006.safetensors: 84%|████████▍ | 4.22G/5.00G [01:18<00:12, 62.0MB/s][A[A
model-00001-of-00006.safetensors: 89%|████████▉ | 4.43G/4.97G [01:18<00:08, 60.8MB/s][A
model-00004-of-00006.safetensors: 85%|████████▍ | 4.24G/5.00G [01:18<00:12, 62.1MB/s][A[A
model-00004-of-00006.safetensors: 85%|████████▌ | 4.26G/5.00G [01:19<00:10, 67.8MB/s][A[A
model-00001-of-00006.safetensors: 90%|████████▉ | 4.45G/4.97G [01:19<00:08, 61.9MB/s][A
model-00004-of-00006.safetensors: 85%|████████▌ | 4.27G/5.00G [01:19<00:12, 59.2MB/s][A[A
model-00001-of-00006.safetensors: 90%|████████▉ | 4.46G/4.97G [01:19<00:09, 54.2MB/s][A
model-00004-of-00006.safetensors: 86%|████████▌ | 4.29G/5.00G [01:19<00:11, 61.0MB/s][A[A
model-00001-of-00006.safetensors: 90%|█████████ | 4.48G/4.97G [01:19<00:08, 55.3MB/s][A
model-00004-of-00006.safetensors: 86%|████████▌ | 4.30G/5.00G [01:19<00:11, 59.0MB/s][A[A
model-00001-of-00006.safetensors: 91%|█████████ | 4.50G/4.97G [01:20<00:07, 59.2MB/s][A
model-00004-of-00006.safetensors: 86%|████████▋ | 4.32G/5.00G [01:20<00:11, 60.5MB/s][A[A
model-00001-of-00006.safetensors: 91%|█████████ | 4.51G/4.97G [01:20<00:07, 60.7MB/s][A
model-00004-of-00006.safetensors: 87%|████████▋ | 4.34G/5.00G [01:20<00:10, 62.7MB/s][A[A
model-00001-of-00006.safetensors: 91%|█████████ | 4.53G/4.97G [01:20<00:07, 61.7MB/s][A
model-00004-of-00006.safetensors: 87%|████████▋ | 4.35G/5.00G [01:20<00:09, 65.6MB/s][A[A
model-00001-of-00006.safetensors: 92%|█████████▏| 4.54G/4.97G [01:20<00:06, 60.6MB/s][A
model-00004-of-00006.safetensors: 87%|████████▋ | 4.37G/5.00G [01:20<00:09, 69.6MB/s][A[A
model-00001-of-00006.safetensors: 92%|█████████▏| 4.56G/4.97G [01:21<00:06, 59.6MB/s][A
model-00004-of-00006.safetensors: 88%|████████▊ | 4.38G/5.00G [01:21<00:09, 65.7MB/s][A[A
model-00001-of-00006.safetensors: 92%|█████████▏| 4.58G/4.97G [01:21<00:06, 60.8MB/s][A
model-00004-of-00006.safetensors: 88%|████████▊ | 4.40G/5.00G [01:21<00:09, 64.2MB/s][A[A
model-00001-of-00006.safetensors: 92%|█████████▏| 4.59G/4.97G [01:21<00:05, 62.8MB/s][A
model-00004-of-00006.safetensors: 88%|████████▊ | 4.42G/5.00G [01:21<00:09, 60.2MB/s][A[A
model-00001-of-00006.safetensors: 93%|█████████▎| 4.61G/4.97G [01:21<00:05, 63.6MB/s][A
model-00004-of-00006.safetensors: 89%|████████▊ | 4.43G/5.00G [01:22<00:09, 57.9MB/s][A[A
model-00001-of-00006.safetensors: 93%|█████████▎| 4.62G/4.97G [01:22<00:05, 61.3MB/s][A
model-00001-of-00006.safetensors: 93%|█████████▎| 4.64G/4.97G [01:22<00:04, 67.8MB/s][A
model-00004-of-00006.safetensors: 89%|████████▉ | 4.45G/5.00G [01:22<00:09, 59.7MB/s][A[A
model-00004-of-00006.safetensors: 89%|████████▉ | 4.46G/5.00G [01:22<00:08, 62.8MB/s][A[A
model-00001-of-00006.safetensors: 94%|█████████▍| 4.66G/4.97G [01:22<00:04, 64.2MB/s][A
model-00001-of-00006.safetensors: 94%|█████████▍| 4.67G/4.97G [01:22<00:04, 67.1MB/s][A
model-00004-of-00006.safetensors: 90%|████████▉ | 4.48G/5.00G [01:22<00:08, 61.3MB/s][A[A
model-00004-of-00006.safetensors: 90%|████████▉ | 4.50G/5.00G [01:23<00:07, 63.1MB/s][A[A
model-00001-of-00006.safetensors: 94%|█████████▍| 4.69G/4.97G [01:23<00:04, 62.5MB/s][A
model-00004-of-00006.safetensors: 90%|█████████ | 4.51G/5.00G [01:23<00:07, 62.8MB/s][A[A
model-00001-of-00006.safetensors: 95%|█████████▍| 4.70G/4.97G [01:23<00:04, 63.5MB/s][A
model-00001-of-00006.safetensors: 95%|█████████▌| 4.72G/4.97G [01:23<00:03, 66.9MB/s][A
model-00004-of-00006.safetensors: 91%|█████████ | 4.53G/5.00G [01:23<00:07, 63.0MB/s][A[A
model-00004-of-00006.safetensors: 91%|█████████ | 4.54G/5.00G [01:23<00:07, 62.6MB/s][A[A
model-00001-of-00006.safetensors: 95%|█████████▌| 4.74G/4.97G [01:23<00:04, 55.1MB/s][A
model-00004-of-00006.safetensors: 91%|█████████ | 4.56G/5.00G [01:24<00:07, 56.0MB/s][A[A
model-00001-of-00006.safetensors: 96%|█████████▌| 4.75G/4.97G [01:24<00:03, 57.5MB/s][A
model-00004-of-00006.safetensors: 92%|█████████▏| 4.58G/5.00G [01:24<00:06, 61.7MB/s][A[A
model-00001-of-00006.safetensors: 96%|█████████▌| 4.77G/4.97G [01:24<00:03, 58.8MB/s][A
model-00004-of-00006.safetensors: 92%|█████████▏| 4.59G/5.00G [01:24<00:06, 63.6MB/s][A[A
model-00001-of-00006.safetensors: 96%|█████████▋| 4.78G/4.97G [01:24<00:02, 60.8MB/s][A
model-00004-of-00006.safetensors: 92%|█████████▏| 4.61G/5.00G [01:24<00:06, 63.0MB/s][A[A
model-00004-of-00006.safetensors: 92%|█████████▏| 4.62G/5.00G [01:25<00:05, 64.7MB/s][A[A
model-00001-of-00006.safetensors: 97%|█████████▋| 4.80G/4.97G [01:25<00:03, 45.9MB/s][A
model-00004-of-00006.safetensors: 93%|█████████▎| 4.64G/5.00G [01:25<00:05, 62.3MB/s][A[A
model-00001-of-00006.safetensors: 97%|█████████▋| 4.82G/4.97G [01:25<00:02, 51.3MB/s][A
model-00004-of-00006.safetensors: 93%|█████████▎| 4.66G/5.00G [01:25<00:05, 64.2MB/s][A[A
model-00001-of-00006.safetensors: 97%|█████████▋| 4.83G/4.97G [01:25<00:02, 55.9MB/s][A
model-00004-of-00006.safetensors: 93%|█████████▎| 4.67G/5.00G [01:25<00:04, 67.7MB/s][A[A
model-00001-of-00006.safetensors: 98%|█████████▊| 4.85G/4.97G [01:25<00:01, 59.2MB/s][A
model-00004-of-00006.safetensors: 94%|█████████▍| 4.69G/5.00G [01:26<00:04, 64.9MB/s][A[A
model-00001-of-00006.safetensors: 98%|█████████▊| 4.86G/4.97G [01:26<00:01, 59.1MB/s][A
model-00004-of-00006.safetensors: 94%|█████████▍| 4.70G/5.00G [01:26<00:04, 65.0MB/s][A[A
model-00001-of-00006.safetensors: 98%|█████████▊| 4.88G/4.97G [01:26<00:01, 62.2MB/s][A
model-00004-of-00006.safetensors: 94%|█████████▍| 4.72G/5.00G [01:26<00:04, 66.3MB/s][A[A
model-00001-of-00006.safetensors: 99%|█████████▊| 4.90G/4.97G [01:26<00:01, 65.4MB/s][A
model-00004-of-00006.safetensors: 95%|█████████▍| 4.74G/5.00G [01:26<00:03, 67.7MB/s][A[A
model-00001-of-00006.safetensors: 99%|█████████▉| 4.91G/4.97G [01:26<00:00, 69.3MB/s][A
model-00001-of-00006.safetensors: 99%|█████████▉| 4.93G/4.97G [01:27<00:00, 71.8MB/s][A
model-00004-of-00006.safetensors: 95%|█████████▌| 4.75G/5.00G [01:27<00:04, 58.3MB/s][A[A
model-00001-of-00006.safetensors: 100%|█████████▉| 4.94G/4.97G [01:27<00:00, 69.2MB/s][A
model-00004-of-00006.safetensors: 95%|█████████▌| 4.77G/5.00G [01:27<00:03, 66.4MB/s][A[A
model-00001-of-00006.safetensors: 100%|█████████▉| 4.96G/4.97G [01:27<00:00, 67.0MB/s][A
model-00004-of-00006.safetensors: 96%|█████████▌| 4.78G/5.00G [01:27<00:03, 65.7MB/s][A[A
model-00001-of-00006.safetensors: 100%|██████████| 4.97G/4.97G [01:27<00:00, 56.6MB/s]
model-00004-of-00006.safetensors: 96%|█████████▌| 4.80G/5.00G [01:27<00:03, 66.4MB/s][A[A
Upload 133 LFS files: 1%| | 1/133 [01:27<3:13:16, 87.86s/it][A[A[A[A[A
model-00004-of-00006.safetensors: 96%|█████████▋| 4.82G/5.00G [01:27<00:02, 65.8MB/s][A[A
model-00004-of-00006.safetensors: 97%|█████████▋| 4.83G/5.00G [01:28<00:02, 67.4MB/s][A[A
model-00004-of-00006.safetensors: 97%|█████████▋| 4.85G/5.00G [01:28<00:02, 66.3MB/s][A[A
model-00004-of-00006.safetensors: 97%|█████████▋| 4.86G/5.00G [01:28<00:02, 57.0MB/s][A[A
model-00004-of-00006.safetensors: 98%|█████████▊| 4.88G/5.00G [01:29<00:01, 62.7MB/s][A[A
model-00004-of-00006.safetensors: 98%|█████████▊| 4.90G/5.00G [01:29<00:01, 63.0MB/s][A[A
model-00004-of-00006.safetensors: 98%|█████████▊| 4.91G/5.00G [01:29<00:01, 58.1MB/s][A[A
model-00004-of-00006.safetensors: 99%|█████████▊| 4.93G/5.00G [01:29<00:01, 59.8MB/s][A[A
model-00004-of-00006.safetensors: 99%|█████████▉| 4.94G/5.00G [01:30<00:00, 61.2MB/s][A[A
model-00004-of-00006.safetensors: 99%|█████████▉| 4.96G/5.00G [01:30<00:00, 59.5MB/s][A[A
model-00004-of-00006.safetensors: 100%|█████████▉| 4.98G/5.00G [01:30<00:00, 63.1MB/s][A[A
model-00004-of-00006.safetensors: 100%|█████████▉| 4.99G/5.00G [01:30<00:00, 63.2MB/s][A[A
model-00004-of-00006.safetensors: 100%|██████████| 5.00G/5.00G [01:31<00:00, 54.9MB/s]
Upload 133 LFS files: 2%|▏ | 2/133 [01:31<1:23:17, 38.15s/it][A[A[A[A[A
Upload 133 LFS files: 100%|██████████| 133/133 [01:31<00:00, 1.46it/s]
5%|▌ | 31001/569592 [50:07<11566:19:39, 77.31s/it]
5%|▌ | 31001/569592 [50:07<11566:19:39, 77.31s/it]
5%|▌ | 31002/569592 [50:08<8142:48:56, 54.43s/it]
5%|▌ | 31002/569592 [50:08<8142:48:56, 54.43s/it]
5%|▌ | 31003/569592 [50:09<5739:32:11, 38.36s/it]
5%|▌ | 31003/569592 [50:09<5739:32:11, 38.36s/it]
5%|▌ | 31004/569592 [50:10<4058:51:13, 27.13s/it]
5%|▌ | 31004/569592 [50:10<4058:51:13, 27.13s/it]
5%|▌ | 31005/569592 [50:11<2886:42:18, 19.30s/it]
5%|▌ | 31005/569592 [50:11<2886:42:18, 19.30s/it]
5%|▌ | 31006/569592 [50:11<2063:08:41, 13.79s/it]
5%|▌ | 31006/569592 [50:11<2063:08:41, 13.79s/it]
5%|▌ | 31007/569592 [50:12<1485:52:11, 9.93s/it]
5%|▌ | 31007/569592 [50:12<1485:52:11, 9.93s/it]
5%|▌ | 31008/569592 [50:13<1081:57:13, 7.23s/it]
5%|▌ | 31008/569592 [50:13<1081:57:13, 7.23s/it]
5%|▌ | 31009/569592 [50:15<849:52:24, 5.68s/it]
5%|▌ | 31009/569592 [50:15<849:52:24, 5.68s/it]
5%|▌ | 31010/569592 [50:21<845:08:37, 5.65s/it]
5%|▌ | 31010/569592 [50:21<845:08:37, 5.65s/it]
5%|▌ | 31011/569592 [50:22<651:36:02, 4.36s/it]
5%|▌ | 31011/569592 [50:22<651:36:02, 4.36s/it]
5%|▌ | 31012/569592 [50:23<501:56:38, 3.36s/it]
5%|▌ | 31012/569592 [50:23<501:56:38, 3.36s/it]
5%|▌ | 31013/569592 [50:25<414:12:27, 2.77s/it]
5%|▌ | 31013/569592 [50:25<414:12:27, 2.77s/it]
5%|▌ | 31014/569592 [50:33<641:17:43, 4.29s/it]
5%|▌ | 31014/569592 [50:33<641:17:43, 4.29s/it]
5%|▌ | 31015/569592 [50:37<645:37:51, 4.32s/it]
5%|▌ | 31015/569592 [50:37<645:37:51, 4.32s/it]
5%|▌ | 31016/569592 [50:43<702:41:46, 4.70s/it]
5%|▌ | 31016/569592 [50:43<702:41:46, 4.70s/it]
5%|▌ | 31017/569592 [50:44<539:34:23, 3.61s/it]
5%|▌ /home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (92544000 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
| 31017/569592 [50:44<539:34:23, 3.61s/it]
5%|▌ | 31018/569592 [50:48<560:48:53, 3.75s/it]
5%|▌ | 31018/569592 [50:48<560:48:53, 3.75s/it]
5%|▌ | 31019/569592 [50:53<622:34:27, 4.16s/it]
5%|▌ | 31019/569592 [50:53<622:34:27, 4.16s/it]
5%|▌ | 31020/569592 [50:57<610:50:43, 4.08s/it]
5%|▌ | 31020/569592 [50:57<610:50:43, 4.08s/it]
5%|▌ | 31021/569592 [51:01<639:01:51, 4.27s/it]
5%|▌ | 31021/569592 [51:01<639:01:51, 4.27s/it]
5%|▌ | 31022/569592 [51:06<659:43:28, 4.41s/it]
5%|▌ | 31022/569592 [51:06<659:43:28, 4.41s/it]
5%|▌ | 31023/569592 [51:07<503:01:40, 3.36s/it]
5%|▌ | 31023/569592 [51:07<503:01:40, 3.36s/it]
5%|▌ | 31024/569592 [51:12<564:56:52, 3.78s/it]
5%|▌ | 31024/569592 [51:12<564:56:52, 3.78s/it]
5%|▌ | 31025/569592 [51:17<610:26:14, 4.08s/it]
5%|▌ | 31025/569592 [51:17<610:26:14, 4.08s/it]
5%|▌ | 31026/569592 [51:21<643:22:27, 4.30s/it]
5%|▌ | 31026/569592 [51:21<643:22:27, 4.30s/it]
5%|▌ | 31027/569592 [51:26<645:38:33, 4.32s/it]
5%|▌ | 31027/569592 [51:26<645:38:33, 4.32s/it]
5%|▌ | 31028/569592 [51:30<631:38:55, 4.22s/it]
5%|▌ | 31028/569592 [51:30<631:38:55, 4.22s/it]
5%|▌ | 31029/569592 [51:34<624:53:52, 4.18s/it]
5%|▌ | 31029/569592 [51:34<624:53:52, 4.18s/it]
5%|▌ | 31030/569592 [51:39<674:32:51, 4.51s/it]
5%|▌ | 31030/569592 [51:39<674:32:51, 4.51s/it]
5%|▌ | 31031/569592 [51:43<667:13:41, 4.46s/it]
5%|▌ | 31031/569592 [51:43<667:13:41, 4.46s/it]
5%|▌ | 31032/569592 [51:48<671:56:34, 4.49s/it]
5%|▌ | 31032/569592 [51:48<671:56:34, 4.49s/it]
5%|▌ | 31033/569592 [51:56<832:44:48, 5.57s/it]
5%|▌ | 31033/569592 [51:56<832:44:48, 5.57s/it]
5%|▌ | 31034/569592 [52:01<804:36:49, 5.38s/it]
5%|▌ | 31034/569592 [52:01<804:36:49, 5.38s/it]
5%|▌ | 31035/569592 [52:06<770:50:59, 5.15s/it]
5%|▌ | 31035/569592 [52:06<770:50:59, 5.15s/it]
5%|▌ | 31036/569592 [52:09<692:17:28, 4.63s/it]
5%|▌ | 31036/569592 [52:09<692:17:28, 4.63s/it]
5%|▌ | 31037/569592 [52:10<524:40:50, 3.51s/it]
5%|▌ | 31037/569592 [52:10<524:40:50, 3.51s/it]
5%|▌ | 31038/569592 [52:14<561:06:20, 3.75s/it]
5%|▌ | 31038/569592 [52:14<561:06:20, 3.75s/it]
5%|▌ | 31039/569592 [52:18<560:58:49, 3.75s/it]
5%|▌ | 31039/569592 [52:18<560:58:49, 3.75s/it]
5%|▌ | 31040/569592 [52:19<434:51:42, 2.91s/it]
5%|▌ | 31040/569592 [52:19<434:51:42, 2.91s/it]
5%|▌ | 31041/569592 [52:24<524:35:37, 3.51s/it]
5%|▌ | 31041/569592 [52:24<524:35:37, 3.51s/it]
5%|▌ | 31042/569592 [52:29<584:01:54, 3.90s/it]
5%|▌ | 31042/569592 [52:29<584:01:54, 3.90s/it]
5%|▌ | 31043/569592 [52:33<620:34:01, 4.15s/it]
5%|▌ | 31043/569592 [52:33<620:34:01, 4.15s/it]
5%|▌ | 31044/569592 [52:38<630:34:33, 4.22s/it]
5%|▌ | 31044/569592 [52:38<630:34:33, 4.22s/it]
5%|▌ | 31045/569592 [52:39<481:31:42, 3.22s/it]
5%|▌ | 31045/569592 [52:39<481:31:42, 3.22s/it]
5%|▌ | 31046/569592 [52:44<565:56:15, 3.78s/it]
5%|▌ | 31046/569592 [52:44<565:56:15, 3.78s/it]
5%|▌ | 31047/569592 [52:49<622:21:18, 4.16s/it]
5%|▌ | 31047/569592 [52:49<622:21:18, 4.16s/it]
5%|▌ | 31048/569592 [52:50<474:28:56, 3.17s/it]
5%|▌ | 31048/569592 [52:50<474:28:56, 3.17s/it]
5%|▌ | 31049/569592 [52:54<506:05:02, 3.38s/it]
5%|▌ | 31049/569592 [52:54<506:05:02, 3.38s/it]
5%|▌ | 31050/569592 [52:57<520:06:05, 3.48s/it]
5%|▌ | 31050/569592 [52:57<520:06:05, 3.48s/it]
5%|▌ | 31051/569592 [53:02<555:16:41, 3.71s/it]
5%|▌ | 31051/569592 [53:02<555:16:41, 3.71s/it]
5%|▌ | 31052/569592 [53:02<429:33:52, 2.87s/it]
5%|▌ | 31052/569592 [53:02<429:33:52, 2.87s/it]
5%|▌ | 31053/569592 [53:06<444:30:07, 2.97s/it]
5%|▌ | 31053/569592 [53:06<444:30:07, 2.97s/it]
5%|▌ | 31054/569592 [53:09<463:09:15, 3.10s/it]
5%|▌ | 31054/569592 [53:09<463:09:15, 3.10s/it]
5%|▌ | 31055/569592 [53:10<368:12:46, 2.46s/it]
5%|▌ | 31055/569592 [53:10<368:12:46, 2.46s/it]
5%|▌ | 31056/569592 [53:11<304:11:19, 2.03s/it]
5%|▌ | 31056/569592 [53:11<304:11:19, 2.03s/it]
5%|▌ | 31057/569592 [53:12<254:53:06, 1.70s/it]
5%|▌ | 31057/569592 [53:12<254:53:06, 1.70s/it]
5%|▌ | 31058/569592 [53:13<221:07:06, 1.48s/it]
5%|▌ | 31058/569592 [53:13<221:07:06, 1.48s/it]
5%|▌ | 31059/569592 [53:14<197:37:26, 1.32s/it]
5%|▌ | 31059/569592 [53:14<197:37:26, 1.32s/it]
5%|▌ | 31060/569592 [53:15<181:18:03, 1.21s/it]
5%|▌ | 31060/569592 [53:15<181:18:03, 1.21s/it]
5%|▌ | 31061/569592 [53:16<168:27:57, 1.13s/it]
5%|▌ | 31061/569592 [53:16<168:27:57, 1.13s/it]
5%|▌ | 31062/569592 [53:19<245:55:50, 1.64s/it]
5%|▌ | 31062/569592 [53:19<245:55:50, 1.64s/it]
5%|▌ | 31063/569592 [53:23<356:23:29, 2.38s/it]
5%|▌ | 31063/569592 [53:23<356:23:29, 2.38s/it]
5%|▌ | 31064/569592 [53:24<326:49:18, 2.18s/it]
5%|▌ | 31064/569592 [53:24<326:49:18, 2.18s/it]
5%|▌ | 31065/569592 [53:25<272:16:18, 1.82s/it]
5%|▌ | 31065/569592 [53:25<272:16:18, 1.82s/it]
5%|▌ | 31066/569592 [53:29<349:35:56, 2.34s/it]
5%|▌ | 31066/569592 [53:29<349:35:56, 2.34s/it]
5%|▌ | 31067/569592 [53:33<403:16:54, 2.70s/it]
5%|▌ | 31067/569592 [53:33<403:16:54, 2.70s/it]
5%|▌ | 31068/569592 [53:35<374:42:58, 2.50s/it]
5%|▌ | 31068/569592 [53:35<374:42:58, 2.50s/it]
5%|▌ | 31069/569592 [53:36<305:31:30, 2.04s/it]
5%|▌ | 31069/569592 [53:36<305:31:30, 2.04s/it]
5%|▌ | 31070/569592 [53:39<376:49:22, 2.52s/it]
5%|▌ | 31070/569592 [53:39<376:49:22, 2.52s/it]
5%|▌ | 31071/569592 [53:43<452:31:12, 3.03s/it]
5%|▌ | 31071/569592 [53:43<452:31:12, 3.03s/it]
5%|▌ | 31072/569592 [53:45<401:33:56, 2.68s/it]
5%|▌ | 31072/569592 [53:45<401:33:56, 2.68s/it]
5%|▌ | 31073/569592 [53:46<326:53:10, 2.19s/it]
5%|▌ | 31073/569592 [53:46<326:53:10, 2.19s/it]
5%|▌ | 31074/569592 [53:49<372:50:37, 2.49s/it]
5%|▌ | 31074/569592 [53:50<372:50:37, 2.49s/it]
5%|▌ | 31075/569592 [53:53<432:08:44, 2.89s/it]
5%|▌ | 31075/569592 [53:53<432:08:44, 2.89s/it]
5%|▌ | 31076/569592 [53:56<416:14:06, 2.78s/it]
5%|▌ | 31076/569592 [53:56<416:14:06, 2.78s/it]
5%|▌ | 31077/569592 [53:58<366:48:57, 2.45s/it]
5%|▌ | 31077/569592 [53:58<366:48:57, 2.45s/it]
5%|▌ | 31078/569592 [54:00<349:13:57, 2.33s/it]
5%|▌ | 31078/569592 [54:00<349:13:57, 2.33s/it]
5%|▌ | 31079/569592 [54:05<474:57:46, 3.18s/it]
5%|▌ | 31079/569592 [54:05<474:57:46, 3.18s/it]
5%|▌ | 31080/569592 [54:06<392:21:51, 2.62s/it]
5%|▌ | 31080/569592 [54:06<392:21:51, 2.62s/it]
5%|▌ | 31081/569592 [54:07<325:42:12, 2.18s/it]
5%|▌ | 31081/569592 [54:07<325:42:12, 2.18s/it]
5%|▌ | 31082/569592 [54:10<355:13:56, 2.37s/it]
5%|▌ | 31082/569592 [54:10<355:13:56, 2.37s/it]
5%|▌ | 31083/569592 [54:14<444:43:37, 2.97s/it]
5%|▌ | 31083/569592 [54:14<444:43:37, 2.97s/it]
5%|▌ | 31084/569592 [54:17<406:17:48, 2.72s/it]
5%|▌ | 31084/569592 [54:17<406:17:48, 2.72s/it]
5%|▌ | 31085/569592 [54:17<327:27:32, 2.19s/it]
5%|▌ | 31085/569592 [54:17<327:27:32, 2.19s/it]
5%|▌ | 31086/569592 [54:21<382:12:46, 2.56s/it]
5%|▌ | 31086/569592 [54:21<382:12:46, 2.56s/it]
5%|▌ | 31087/569592 [54:24<387:07:27, 2.59s/it]
5%|▌ | 31087/569592 [54:24<387:07:27, 2.59s/it]
5%|▌ | 31088/569592 [54:27<416:08:01, 2.78s/it]
5%|▌ | 31088/569592 [54:27<416:08:01, 2.78s/it]
5%|▌ | 31089/569592 [54:28<340:35:32, 2.28s/it]
5%|▌ | 31089/569592 [54:28<340:35:32, 2.28s/it]
5%|▌ | 31090/569592 [54:31<360:35:04, 2.41s/it]
5%|▌ | 31090/569592 [54:31<360:35:04, 2.41s/it]
5%|▌ | 31091/569592 [54:35<463:09:10, 3.10s/it]
5%|▌ | 31091/569592 [54:35<463:09:10, 3.10s/it]
5%|▌ | 31092/569592 [54:37<383:55:14, 2.57s/it]
5%|▌ | 31092/569592 [54:37<383:55:14, 2.57s/it]
5%|▌ | 31093/569592 [54:39<371:36:44, 2.48s/it]
5%|▌ | 31093/569592 [54:39<371:36:44, 2.48s/it]
5%|▌ | 31094/569592 [54:42<399:31:00, 2.67s/it]
5%|▌ | 31094/569592 [54:42<399:31:00, 2.67s/it]
5%|▌ | 31095/569592 [54:46<448:06:14, 3.00s/it]
5%|▌ | 31095/569592 [54:46<448:06:14, 3.00s/it]
5%|▌ | 31096/569592 [54:48<410:57:39, 2.75s/it]
5%|▌ | 31096/569592 [54:48<410:57:39, 2.75s/it]
5%|▌ | 31097/569592 [54:49<345:39:16, 2.31s/it]
5%|▌ | 31097/569592 [54:49<345:39:16, 2.31s/it]
5%|▌ | 31098/569592 [54:51<329:32:25, 2.20s/it]
5%|▌ | 31098/569592 [54:51<329:32:25, 2.20s/it]
5%|▌ | 31099/569592 [54:56<443:21:49, 2.96s/it]
5%|▌ | 31099/569592 [54:56<443:21:49, 2.96s/it]
5%|▌ | 31100/569592 [54:57<370:21:48, 2.48s/it]
5%|▌ | 31100/569592 [54:57<370:21:48, 2.48s/it]
5%|▌ | 31101/569592 [55:00<384:36:38, 2.57s/it]
5%|▌ | 31101/569592 [55:00<384:36:38, 2.57s/it]
5%|▌ | 31102/569592 [55:03<397:12:20, 2.66s/it]
5%|▌ | 31102/569592 [55:03<397:12:20, 2.66s/it]
5%|▌ | 31103/569592 [55:06<422:10:59, 2.82s/it]
5%|▌ | 31103/569592 [55:06<422:10:59, 2.82s/it]
5%|▌ | 31104/569592 [55:08<399:32:26, 2.67s/it]
5%|▌ | 31104/569592 [55:08<399:32:26, 2.67s/it]
5%|▌ | 31105/569592 [55:10<359:13:48, 2.40s/it]
5%|▌ | 31105/569592 [55:10<359:13:48, 2.40s/it]
5%|▌ | 31106/569592 [55:13<357:20:43, 2.39s/it]
5%|▌ | 31106/569592 [55:13<357:20:43, 2.39s/it]
5%|▌ | 31107/569592 [55:17<434:56:54, 2.91s/it]
5%|▌ | 31107/569592 [55:17<434:56:54, 2.91s/it]
5%|▌ | 31108/569592 [55:18<374:56:01, 2.51s/it]
5%|▌ | 31108/569592 [55:18<374:56:01, 2.51s/it]
5%|▌ | 31109/569592 [55:20<357:30:05, 2.39s/it]
5%|▌ | 31109/569592 [55:20<357:30:05, 2.39s/it]
5%|▌ | 31110/569592 [55:22<329:44:47, 2.20s/it]
5%|▌ | 31110/569592 [55:22<329:44:47, 2.20s/it]
5%|▌ | 31111/569592 [55:25<379:48:55, 2.54s/it]
5%|▌ | 31111/569592 [55:26<379:48:55, 2.54s/it]
5%|▌ | 31112/569592 [55:28<397:29:39, 2.66s/it]
5%|▌ | 31112/569592 [55:28<397:29:39, 2.66s/it]
5%|▌ | 31113/569592 [55:31<406:29:09, 2.72s/it]
5%|▌ | 31113/569592 [55:31<406:29:09, 2.72s/it]
5%|▌ | 31114/569592 [55:33<369:18:26, 2.47s/it]
5%|▌ | 31114/569592 [55:33<369:18:26, 2.47s/it]
5%|▌ | 31115/569592 [55:37<410:15:07, 2.74s/it]
5%|▌ | 31115/569592 [55:37<410:15:07, 2.74s/it]
5%|▌ | 31116/569592 [55:39<380:06:30, 2.54s/it]
5%|▌ | 31116/569592 [55:39<380:06:30, 2.54s/it]
5%|▌ | 31117/569592 [55:40<311:29:41, 2.08s/it]
5%|▌ | 31117/569592 [55:40<311:29:41, 2.08s/it]
5%|▌ | 31118/569592 [55:43<366:12:28, 2.45s/it]
5%|▌ | 31118/569592 [55:43<366:12:28, 2.45s/it]
5%|▌ | 31119/569592 [55:46<401:38:25, 2.69s/it]
5%|▌ | 31119/569592 [55:46<401:38:25, 2.69s/it]
5%|▌ | 31120/569592 [55:48<380:16:26, 2.54s/it]
5%|▌ | 31120/569592 [55:48<380:16:26, 2.54s/it]
5%|▌ | 31121/569592 [55:51<380:54:56, 2.55s/it]
5%|▌ | 31121/569592 [55:51<380:54:56, 2.55s/it]
5%|▌ | 31122/569592 [55:53<359:06:40, 2.40s/it]
5%|▌ | 31122/569592 [55:53<359:06:40, 2.40s/it]
5%|▌ | 31123/569592 [55:57<434:16:48, 2.90s/it]
5%|▌ | 31123/569592 [55:57<434:16:48, 2.90s/it]
5%|▌ | 31124/569592 [55:58<346:24:58, 2.32s/it]
5%|▌ | 31124/569592 [55:58<346:24:58, 2.32s/it]
5%|▌ | 31125/569592 [56:01<368:20:03, 2.46s/it]
5%|▌ | 31125/569592 [56:01<368:20:03, 2.46s/it]
5%|▌ | 31126/569592 [56:02<327:08:58, 2.19s/it]
5%|▌ | 31126/569592 [56:02<327:08:58, 2.19s/it]
5%|▌ | 31127/569592 [56:07<445:31:42, 2.98s/it]
5%|▌ | 31127/569592 [56:07<445:31:42, 2.98s/it]
5%|▌ | 31128/569592 [56:08<353:17:13, 2.36s/it]
5%|▌ | 31128/569592 [56:08<353:17:13, 2.36s/it]
5%|▌ | 31129/569592 [56:11<367:08:14, 2.45s/it]
5%|▌ | 31129/569592 [56:11<367:08:14, 2.45s/it]
5%|▌ | 31130/569592 [56:15<456:5/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (100920000 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
0:41, 3.05s/it]
5%|▌ | 31130/569592 [56:15<456:50:41, 3.05s/it]
5%|▌ | 31131/569592 [56:16<367:08:40, 2.45s/it]
5%|▌ | 31131/569592 [56:16<367:08:40, 2.45s/it]
5%|▌ | 31132/569592 [56:20<439:47:09, 2.94s/it]
5%|▌ | 31132/569592 [56:20<439:47:09, 2.94s/it]
5%|▌ | 31133/569592 [56:24<490:37:38, 3.28s/it]
5%|▌ | 31133/569592 [56:24<490:37:38, 3.28s/it]
5%|▌ | 31134/569592 [56:25<383:28:41, 2.56s/it]
5%|▌ | 31134/569592 [56:25<383:28:41, 2.56s/it]
5%|▌ | 31135/569592 [56:30<482:43:49, 3.23s/it]
5%|▌ | 31135/569592 [56:30<482:43:49, 3.23s/it]
5%|▌ | 31136/569592 [56:35<547:57:42, 3.66s/it]
5%|▌ | 31136/569592 [56:35<547:57:42, 3.66s/it]
5%|▌ | 31137/569592 [56:39<584:03:41, 3.90s/it]
5%|▌ | 31137/569592 [56:39<584:03:41, 3.90s/it]
5%|▌ | 31138/569592 [56:44<615:01:53, 4.11s/it]
5%|▌ | 31138/569592 [56:44<615:01:53, 4.11s/it]
5%|▌ | 31139/569592 [56:49<651:25:20, 4.36s/it]
5%|▌ | 31139/569592 [56:49<651:25:20, 4.36s/it]
5%|▌ | 31140/569592 [56:53<634:42:54, 4.24s/it]
5%|▌ | 31140/569592 [56:53<634:42:54, 4.24s/it]
5%|▌ | 31141/569592 [56:54<483:45:43, 3.23s/it]
5%|▌ | 31141/569592 [56:54<483:45:43, 3.23s/it]
5%|▌ | 31142/569592 [56:57<493:56:48, 3.30s/it]
5%|▌ | 31142/569592 [56:57<493:56:48, 3.30s/it]
5%|▌ | 31143/569592 [57:02<575:15:18, 3.85s/it]
5%|▌ | 31143/569592 [57:02<575:15:18, 3.85s/it]
5%|▌ | 31144/569592 [57:05<538:31:56, 3.60s/it]
5%|▌ | 31144/569592 [57:05<538:31:56, 3.60s/it]
5%|▌ | 31145/569592 [57:10<594:12:43, 3.97s/it]
5%|▌ | 31145/569592 [57:10<594:12:43, 3.97s/it]
5%|▌ | 31146/569592 [57:17<725:52:42, 4.85s/it]
5%|▌ | 31146/569592 [57:17<725:52:42, 4.85s/it]
5%|▌ | 31147/569592 [57:20<666:22:45, 4.46s/it]
5%|▌ | 31147/569592 [57:21<666:22:45, 4.46s/it]
5%|▌ | 31148/569592 [57:25<674:29:06, 4.51s/it]
5%|▌ | 31148/569592 [57:25<674:29:06, 4.51s/it]
5%|▌ | 31149/569592 [57:30<676:01:16, 4.52s/it]
5%|▌ | 31149/569592 [57:30<676:01:16, 4.52s/it]
5%|▌ | 31150/569592 [57:33<641:50:02, 4.29s/it]
5%|▌ | 31150/569592 [57:33<641:50:02, 4.29s/it]
5%|▌ | 31151/569592 [57:38<637:57:26, 4.27s/it]
5%|▌ | 31151/569592 [57:38<637:57:26, 4.27s/it]
5%|▌ | 31152/569592 [57:41<591:34:49, 3.96s/it]
5%|▌ | 31152/569592 [57:41<591:34:49, 3.96s/it]
5%|▌ | 31153/569592 [57:46<623:17:45, 4.17s/it]
5%|▌ | 31153/569592 [57:46<623:17:45, 4.17s/it]
5%|▌ | 31154/569592 [57:50<646:07:24, 4.32s/it]
5%|▌ | 31154/569592 [57:50<646:07:24, 4.32s/it]
5%|▌ | 31155/569592 [57:54<610:52:36, 4.08s/it]
5%|▌ | 31155/569592 [57:54<610:52:36, 4.08s/it]
5%|▌ | 31156/569592 [57:57<594:54:55, 3.98s/it]
5%|▌ | 31156/569592 [57:57<594:54:55, 3.98s/it]
5%|▌ | 31157/569592 [58:01<552:58:33, 3.70s/it]
5%|▌ | 31157/569592 [58:01<552:58:33, 3.70s/it]
5%|▌ | 31158/569592 [58:01<427:43:57, 2.86s/it]
/home/zhaojiang/.local/lib/python3.10/site-packages/PIL/Image.py:3368: DecompressionBombWarning: Image size (103329614 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
warnings.warn(
5%|▌ | 31158/569592 [58:01<427:43:57, 2.86s/it]
5%|▌ | 31159/569592 [58:05<454:53:14, 3.04s/it]
5%|▌ | 31159/569592 [58:05<454:53:14, 3.04s/it]
5%|▌ | 31160/569592 [58:08<475:20:14, 3.18s/it]
5%|▌ | 31160/569592 [58:08<475:20:14, 3.18s/it]
5%|▌ | 31161/569592 [58:13<559:06:56, 3.74s/it]
5%|▌ | 31161/569592 [58:13<559:06:56, 3.74s/it]
5%|▌ | 31162/569592 [58:14<431:54:14, 2.89s/it]
5%|▌ | 31162/569592 [58:14<431:54:14, 2.89s/it]
5%|▌ | 31163/569592 [58:19<519:14:08, 3.47s/it]
5%|▌ | 31163/569592 [58:19<519:14:08, 3.47s/it]
5%|▌ | 31164/569592 [58:24<593:32:51, 3.97s/it]
5%|▌ | 31164/569592 [58:24<593:32:51, 3.97s/it]
5%|▌ | 31165/569592 [58:25<454:56:23, 3.04s/it]
5%|▌ | 31165/569592 [58:25<454:56:23, 3.04s/it]
5%|▌ | 31166/569592 [58:29<510:05:07, 3.41s/it]
5%|▌ | 31166/569592 [58:29<510:05:07, 3.41s/it]
5%|▌ | 31167/569592 [58:30<398:08:13, 2.66s/it]
5%|▌ | 31167/569592 [58:30<398:08:13, 2.66s/it]
5%|▌ | 31168/569592 [58:31<320:49:02, 2.15s/it]
5%|▌ | 31168/569592 [58:31<320:49:02, 2.15s/it]
5%|▌ | 31169/569592 [58:32<267:24:56, 1.79s/it]
5%|▌ | 31169/569592 [58:32<267:24:56, 1.79s/it]
5%|▌ | 31170/569592 [58:33<229:55:16, 1.54s/it]
5%|▌ | 31170/569592 [58:33<229:55:16, 1.54s/it]
5%|▌ | 31171/569592 [58:37<315:50:04, 2.11s/it]
5%|▌ | 31171/569592 [58:37<315:50:04, 2.11s/it]
5%|▌ | 31172/569592 [58:41<404:10:56, 2.70s/it]
5%|▌ | 31172/569592 [58:41<404:10:56, 2.70s/it]
5%|▌ | 31173/569592 [58:42<330:02:58, 2.21s/it]
5%|▌ | 31173/569592 [58:42<330:02:58, 2.21s/it]
5%|▌ | 31174/569592 [58:43<272:57:10, 1.83s/it]
5%|▌ | 31174/569592 [58:43<272:57:10, 1.83s/it]
5%|▌ | 31175/569592 [58:44<234:22:54, 1.57s/it]
5%|▌ | 31175/569592 [58:44<234:22:54, 1.57s/it]
5%|▌ | 31176/569592 [58:45<209:24:18, 1.40s/it]
5%|▌ | 31176/569592 [58:45<209:24:18, 1.40s/it]
5%|▌ | 31177/569592 [58:48<275:35:40, 1.84s/it]
5%|▌ | 31177/569592 [58:48<275:35:40, 1.84s/it]
5%|▌ | 31178/569592 [58:49<239:18:35, 1.60s/it]
5%|▌ | 31178/569592 [58:49<239:18:35, 1.60s/it]
5%|▌ | 31179/569592 [58:54<389:08:12, 2.60s/it]
5%|▌ | 31179/569592 [58:54<389:08:12, 2.60s/it]
5%|▌ | 31180/569592 [58:55<316:57:09, 2.12s/it]
5%|▌ | 31180/569592 [58:55
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 661040 got signal: 15
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 2033589 got signal: 15
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 651329 got signal: 15
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 673195 got signal: 15
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
torch.distributed.elastic.multiprocessing.api.SignalException: Process 2110507 got signal: 15
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 1986959 got signal: 15
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 1987087 got signal: 15
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 1986836 got signal: 15
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
Traceback (most recent call last):
File "/home/zhaojiang/.local/bin/torchrun", line 8, in
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 1983947 got signal: 15
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 1990262 got signal: 15
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
sys.exit(main())
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 1987887 got signal: 15
return f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 919, in main
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
run(args)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/run.py", line 910, in run
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
elastic_launch(
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 1988962 got signal: 15
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 260, in launch_agent
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 1982123 got signal: 15
result = agent.run()
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 137, in wrapper
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
result = f(*args, **kwargs)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 696, in run
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 1985442 got signal: 15
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
result = self._invoke_run(role)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 855, in _invoke_run
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
time.sleep(monitor_interval)
File "/home/zhaojiang/.local/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 1983838 got signal: 15
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
torch.distributed.elastic.multiprocessing.api.SignalException: Process 1985034 got signal: 15