/home/junrushao/micromamba/envs/python311/bin/python -m mlc_chat gen_config /home/junrushao/tmp/tmpc5liwyrs/repo --quantization q4f32_1 --conv-template dolly --output /home/junrushao/tmp/tmpq5kh4k7j --context-window-size 2048 [2023-12-29 19:25:55] INFO auto_config.py:115: Found model configuration: /home/junrushao/tmp/tmpc5liwyrs/repo/config.json [2023-12-29 19:25:55] INFO auto_config.py:151: Found model type: gpt_neox. Use `--model-type` to override. [2023-12-29 19:25:55] INFO gpt_neox_model.py:46: context_window_size not found in config.json. Falling back to max_position_embeddings (2048) [2023-12-29 19:25:55] INFO flags_model_config_override.py:63: Default prefill_chunk_size to context_window_size (2048) because it is not provided [2023-12-29 19:25:55] INFO flags_model_config_override.py:112: Overriding context_window_size from 2048 to 2048 [2023-12-29 19:25:55] INFO flags_model_config_override.py:112: Overriding prefill_chunk_size from 2048 to 2048 [2023-12-29 19:25:55] INFO gen_config.py:117: Not found generation_config.json: /home/junrushao/tmp/tmpc5liwyrs/repo/generation_config.json [2023-12-29 19:25:55] INFO gen_config.py:115: [config.json] Setting bos_token_id: 0 [2023-12-29 19:25:55] INFO gen_config.py:115: [config.json] Setting eos_token_id: 0 [2023-12-29 19:25:55] INFO gen_config.py:129: Not found tokenizer config: /home/junrushao/tmp/tmpc5liwyrs/repo/tokenizer.model [2023-12-29 19:25:55] INFO gen_config.py:127: Found tokenizer config: /home/junrushao/tmp/tmpc5liwyrs/repo/tokenizer.json. Copying to /home/junrushao/tmp/tmpq5kh4k7j/tokenizer.json [2023-12-29 19:25:55] INFO gen_config.py:129: Not found tokenizer config: /home/junrushao/tmp/tmpc5liwyrs/repo/vocab.json [2023-12-29 19:25:55] INFO gen_config.py:129: Not found tokenizer config: /home/junrushao/tmp/tmpc5liwyrs/repo/merges.txt [2023-12-29 19:25:55] INFO gen_config.py:129: Not found tokenizer config: /home/junrushao/tmp/tmpc5liwyrs/repo/added_tokens.json [2023-12-29 19:25:55] INFO gen_config.py:127: Found tokenizer config: /home/junrushao/tmp/tmpc5liwyrs/repo/tokenizer_config.json. Copying to /home/junrushao/tmp/tmpq5kh4k7j/tokenizer_config.json [2023-12-29 19:25:55] INFO gen_config.py:69: [System default] Setting pad_token_id: 0 [2023-12-29 19:25:55] INFO gen_config.py:69: [System default] Setting temperature: 0.7 [2023-12-29 19:25:55] INFO gen_config.py:69: [System default] Setting repetition_penalty: 1.0 [2023-12-29 19:25:55] INFO gen_config.py:69: [System default] Setting top_p: 0.95 [2023-12-29 19:25:55] INFO gen_config.py:69: [System default] Setting mean_gen_len: 128 [2023-12-29 19:25:55] INFO gen_config.py:69: [System default] Setting max_gen_len: 512 [2023-12-29 19:25:55] INFO gen_config.py:69: [System default] Setting shift_fill_factor: 0.3 [2023-12-29 19:25:55] INFO gen_config.py:157: Dumping configuration file to: /home/junrushao/tmp/tmpq5kh4k7j/mlc-chat-config.json /home/junrushao/micromamba/envs/python311/bin/python -m mlc_chat convert_weight /home/junrushao/tmp/tmpc5liwyrs/repo --quantization q4f32_1 --source-format auto --output /home/junrushao/tmp/tmpq5kh4k7j [2023-12-29 19:25:56] INFO auto_config.py:115: Found model configuration: /home/junrushao/tmp/tmpc5liwyrs/repo/config.json [2023-12-29 19:25:56] INFO auto_device.py:76: Found device: cuda:0 [2023-12-29 19:25:56] INFO auto_device.py:76: Found device: cuda:1 [2023-12-29 19:25:56] INFO auto_device.py:76: Found device: cuda:2 [2023-12-29 19:25:56] INFO auto_device.py:76: Found device: cuda:3 [2023-12-29 19:25:57] INFO auto_device.py:85: Not found device: rocm:0 [2023-12-29 19:25:57] INFO auto_device.py:85: Not found device: metal:0 [2023-12-29 19:25:57] INFO auto_device.py:85: Not found device: vulkan:0 [2023-12-29 19:25:58] INFO auto_device.py:85: Not found device: opencl:0 [2023-12-29 19:25:58] INFO auto_device.py:33: Using device: cuda:0 [2023-12-29 19:25:58] INFO auto_weight.py:70: Finding weights in: /home/junrushao/tmp/tmpc5liwyrs/repo [2023-12-29 19:25:58] INFO auto_weight.py:129: Found source weight format: huggingface-torch. Source configuration: /home/junrushao/tmp/tmpc5liwyrs/repo/pytorch_model.bin [2023-12-29 19:25:58] INFO auto_weight.py:149: Not found Huggingface Safetensor [2023-12-29 19:25:58] INFO auto_weight.py:106: Using source weight configuration: /home/junrushao/tmp/tmpc5liwyrs/repo/pytorch_model.bin. Use `--source` to override. [2023-12-29 19:25:58] INFO auto_weight.py:110: Using source weight format: huggingface-torch. Use `--source-format` to override. [2023-12-29 19:25:58] INFO auto_config.py:151: Found model type: gpt_neox. Use `--model-type` to override. [2023-12-29 19:25:58] INFO gpt_neox_model.py:46: context_window_size not found in config.json. Falling back to max_position_embeddings (2048) [2023-12-29 19:26:03] INFO huggingface_loader.py:169: Loading HF parameters from: /home/junrushao/tmp/tmpc5liwyrs/repo/pytorch_model.bin Weight conversion with arguments: --config /home/junrushao/tmp/tmpc5liwyrs/repo/config.json --quantization GroupQuantize(name='q4f32_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float32', num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7) --model-type gpt_neox --device cuda:0 --source /home/junrushao/tmp/tmpc5liwyrs/repo/pytorch_model.bin --source-format huggingface-torch --output /home/junrushao/tmp/tmpq5kh4k7j 0%| | 0/436 [00:00