/home/junrushao/micromamba/envs/python311/bin/python -m mlc_chat gen_config /home/junrushao/tmp/tmps_wsupkk/repo --quantization q4f32_1 --conv-template wizard_coder_or_math --output /home/junrushao/tmp/tmpcnfmgk1d --context-window-size 16384 [2023-12-29 18:11:27] INFO auto_config.py:115: Found model configuration: /home/junrushao/tmp/tmps_wsupkk/repo/config.json [2023-12-29 18:11:27] INFO auto_config.py:151: Found model type: llama. Use `--model-type` to override. [2023-12-29 18:11:27] INFO llama_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (16384) [2023-12-29 18:11:27] INFO flags_model_config_override.py:63: Default prefill_chunk_size to context_window_size (16384) because it is not provided [2023-12-29 18:11:27] INFO flags_model_config_override.py:112: Overriding context_window_size from 16384 to 16384 [2023-12-29 18:11:27] INFO flags_model_config_override.py:112: Overriding prefill_chunk_size from 16384 to 16384 [2023-12-29 18:11:27] INFO gen_config.py:115: [generation_config.json] Setting bos_token_id: 1 [2023-12-29 18:11:27] INFO gen_config.py:115: [generation_config.json] Setting eos_token_id: 2 [2023-12-29 18:11:27] INFO gen_config.py:115: [config.json] Setting pad_token_id: 0 [2023-12-29 18:11:27] INFO gen_config.py:127: Found tokenizer config: /home/junrushao/tmp/tmps_wsupkk/repo/tokenizer.model. Copying to /home/junrushao/tmp/tmpcnfmgk1d/tokenizer.model [2023-12-29 18:11:27] INFO gen_config.py:127: Found tokenizer config: /home/junrushao/tmp/tmps_wsupkk/repo/tokenizer.json. Copying to /home/junrushao/tmp/tmpcnfmgk1d/tokenizer.json [2023-12-29 18:11:27] INFO gen_config.py:129: Not found tokenizer config: /home/junrushao/tmp/tmps_wsupkk/repo/vocab.json [2023-12-29 18:11:27] INFO gen_config.py:129: Not found tokenizer config: /home/junrushao/tmp/tmps_wsupkk/repo/merges.txt [2023-12-29 18:11:27] INFO gen_config.py:127: Found tokenizer config: /home/junrushao/tmp/tmps_wsupkk/repo/added_tokens.json. Copying to /home/junrushao/tmp/tmpcnfmgk1d/added_tokens.json [2023-12-29 18:11:27] INFO gen_config.py:127: Found tokenizer config: /home/junrushao/tmp/tmps_wsupkk/repo/tokenizer_config.json. Copying to /home/junrushao/tmp/tmpcnfmgk1d/tokenizer_config.json [2023-12-29 18:11:27] INFO gen_config.py:69: [System default] Setting temperature: 0.7 [2023-12-29 18:11:27] INFO gen_config.py:69: [System default] Setting repetition_penalty: 1.0 [2023-12-29 18:11:27] INFO gen_config.py:69: [System default] Setting top_p: 0.95 [2023-12-29 18:11:27] INFO gen_config.py:69: [System default] Setting mean_gen_len: 128 [2023-12-29 18:11:27] INFO gen_config.py:69: [System default] Setting max_gen_len: 512 [2023-12-29 18:11:27] INFO gen_config.py:69: [System default] Setting shift_fill_factor: 0.3 [2023-12-29 18:11:27] INFO gen_config.py:157: Dumping configuration file to: /home/junrushao/tmp/tmpcnfmgk1d/mlc-chat-config.json /home/junrushao/micromamba/envs/python311/bin/python -m mlc_chat convert_weight /home/junrushao/tmp/tmps_wsupkk/repo --quantization q4f32_1 --source-format auto --output /home/junrushao/tmp/tmpcnfmgk1d [2023-12-29 18:11:28] INFO auto_config.py:115: Found model configuration: /home/junrushao/tmp/tmps_wsupkk/repo/config.json [2023-12-29 18:11:29] INFO auto_device.py:76: Found device: cuda:0 [2023-12-29 18:11:29] INFO auto_device.py:76: Found device: cuda:1 [2023-12-29 18:11:29] INFO auto_device.py:76: Found device: cuda:2 [2023-12-29 18:11:29] INFO auto_device.py:76: Found device: cuda:3 [2023-12-29 18:11:29] INFO auto_device.py:85: Not found device: rocm:0 [2023-12-29 18:11:30] INFO auto_device.py:85: Not found device: metal:0 [2023-12-29 18:11:30] INFO auto_device.py:85: Not found device: vulkan:0 [2023-12-29 18:11:30] INFO auto_device.py:85: Not found device: opencl:0 [2023-12-29 18:11:30] INFO auto_device.py:33: Using device: cuda:0 [2023-12-29 18:11:30] INFO auto_weight.py:70: Finding weights in: /home/junrushao/tmp/tmps_wsupkk/repo [2023-12-29 18:11:30] INFO auto_weight.py:120: Found source weight format: huggingface-torch. Source configuration: /home/junrushao/tmp/tmps_wsupkk/repo/pytorch_model.bin.index.json [2023-12-29 18:11:30] INFO auto_weight.py:149: Not found Huggingface Safetensor [2023-12-29 18:11:30] INFO auto_weight.py:106: Using source weight configuration: /home/junrushao/tmp/tmps_wsupkk/repo/pytorch_model.bin.index.json. Use `--source` to override. [2023-12-29 18:11:30] INFO auto_weight.py:110: Using source weight format: huggingface-torch. Use `--source-format` to override. [2023-12-29 18:11:30] INFO auto_config.py:151: Found model type: llama. Use `--model-type` to override. [2023-12-29 18:11:30] INFO llama_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (16384) Weight conversion with arguments: --config /home/junrushao/tmp/tmps_wsupkk/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 llama --device cuda:0 --source /home/junrushao/tmp/tmps_wsupkk/repo/pytorch_model.bin.index.json --source-format huggingface-torch --output /home/junrushao/tmp/tmpcnfmgk1d 0%| | 0/291 [00:00