Upload folder using huggingface_hub

decoder/caption/adapter_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a8d290b571379f77f4ee2fc69c83fa161c11779748273cdb698fb77432dc68b
+size 88263290

decoder/caption/adapter_config.json

@@ -0,0 +1 @@
+{"r": 16, "lora_alpha": 32, "target_modules": ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "down_proj", "up_proj", "lm_head"], "peft_type": "LORA"}

decoder/caption/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a508581cf5c3eb39bfbce3e5671562a5c21c0f03f5d087ba61f440b645affc
+size 88277586

decoder/config.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.42.3", "use_cache": true, "vocab_size": 128256}

decoder/reasoning/adapter_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b23142725f51ca423b232e64ca429da25a6848b037c9ed085f4debe2dd0dad0
+size 88263290

decoder/reasoning/adapter_config.json

@@ -0,0 +1 @@
+{"r": 16, "lora_alpha": 32, "target_modules": ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "down_proj", "up_proj", "lm_head"], "peft_type": "LORA"}

decoder/reasoning/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b8b7962aad70993ef0e8e2764df12ac1b861b533a480e858940cb71173b181
+size 88277586

decoder/summary/adapter_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9ea1b11113670bbe2ef0ba41b88ad60ff5613cad62731ca8a3b07860414530
+size 88263290

decoder/summary/adapter_config.json

@@ -0,0 +1 @@
+{"r": 16, "lora_alpha": 32, "target_modules": ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "down_proj", "up_proj", "lm_head"], "peft_type": "LORA"}

decoder/summary/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb74389dea7679d578b75aed8d2a20302e493fd9d6599c585a8dab68f48e3a3
+size 88277586

encoder/main/adapter_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c05c1355097b621960fbbb756eeba2afa877c298ac02907ddfb1ef3d17f6a200
+size 115583738

encoder/main/config.json

@@ -0,0 +1 @@
+{"_name_or_path": "Xkev/Llama-3.2V-11B-cot", "architectures": ["MllamaForConditionalGeneration"], "image_token_index": 128256, "model_type": "mllama", "text_config": {"_name_or_path": "", "add_cross_attention": false, "architectures": null, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 128000, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "cross_attention_layers": [3, 8, 13, 18, 23, 28, 33, 38], "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": [128001, 128008, 128009], "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 4096, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "initializer_range": 0.02, "intermediate_size": 14336, "is_decoder": false, "is_encoder_decoder": false, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 131072, "min_length": 0, "model_type": "mllama_text_model", "no_repeat_ngram_size": 0, "num_attention_heads": 32, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 40, "num_key_value_heads": 8, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 128004, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 128256}, "torch_dtype": "float32", "transformers_version": "4.45.2", "vision_config": {"_name_or_path": "", "add_cross_attention": false, "architectures": null, "attention_heads": 16, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_size": 1280, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "image_size": 560, "initializer_range": 0.02, "intermediate_layers_indices": [3, 7, 15, 23, 30], "intermediate_size": 5120, "is_decoder": false, "is_encoder_decoder": false, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "length_penalty": 1.0, "max_length": 20, "max_num_tiles": 4, "min_length": 0, "model_type": "mllama_vision_model", "no_repeat_ngram_size": 0, "norm_eps": 1e-05, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_global_layers": 8, "num_hidden_layers": 32, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "supported_aspect_ratios": [[1, 1], [1, 2], [1, 3], [1, 4], [2, 1], [2, 2], [3, 1], [4, 1]], "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "vision_output_dim": 7680}}