/home/junrushao/micromamba/envs/python311/bin/python -m mlc_chat gen_config /opt/scratch/assets/gpt_bigcode-santacoder --quantization q4f32_1 --conv-template LM --output /home/junrushao/tmp/tmph17zk__o --context-window-size 2048 [2024-01-08 19:19:02] INFO auto_config.py:115: Found model configuration: /opt/scratch/assets/gpt_bigcode-santacoder/config.json [2024-01-08 19:19:02] INFO auto_config.py:151: Found model type: gpt_bigcode. Use `--model-type` to override. [2024-01-08 19:19:02] INFO gpt_bigcode_model.py:41: context_window_size not found in config.json. Falling back to n_positions (2048) [2024-01-08 19:19:02] INFO gpt_bigcode_model.py:54: prefill_chunk_size defaults to context_window_size (2048) [2024-01-08 19:19:02] INFO compiler_flags.py:118: Overriding context_window_size from 2048 to 2048 [2024-01-08 19:19:02] INFO gen_config.py:119: Not found generation_config.json: /opt/scratch/assets/gpt_bigcode-santacoder/generation_config.json [2024-01-08 19:19:02] INFO gen_config.py:117: [config.json] Setting bos_token_id: 49152 [2024-01-08 19:19:02] INFO gen_config.py:117: [config.json] Setting eos_token_id: 49152 [2024-01-08 19:19:02] INFO gen_config.py:131: Not found tokenizer config: /opt/scratch/assets/gpt_bigcode-santacoder/tokenizer.model [2024-01-08 19:19:02] INFO gen_config.py:129: Found tokenizer config: /opt/scratch/assets/gpt_bigcode-santacoder/tokenizer.json. Copying to /home/junrushao/tmp/tmph17zk__o/tokenizer.json [2024-01-08 19:19:02] INFO gen_config.py:131: Not found tokenizer config: /opt/scratch/assets/gpt_bigcode-santacoder/vocab.json [2024-01-08 19:19:02] INFO gen_config.py:131: Not found tokenizer config: /opt/scratch/assets/gpt_bigcode-santacoder/merges.txt [2024-01-08 19:19:02] INFO gen_config.py:131: Not found tokenizer config: /opt/scratch/assets/gpt_bigcode-santacoder/added_tokens.json [2024-01-08 19:19:02] INFO gen_config.py:129: Found tokenizer config: /opt/scratch/assets/gpt_bigcode-santacoder/tokenizer_config.json. Copying to /home/junrushao/tmp/tmph17zk__o/tokenizer_config.json [2024-01-08 19:19:02] INFO gen_config.py:70: [System default] Setting pad_token_id: 0 [2024-01-08 19:19:02] INFO gen_config.py:70: [System default] Setting temperature: 0.7 [2024-01-08 19:19:02] INFO gen_config.py:70: [System default] Setting repetition_penalty: 1.0 [2024-01-08 19:19:02] INFO gen_config.py:70: [System default] Setting top_p: 0.95 [2024-01-08 19:19:02] INFO gen_config.py:70: [System default] Setting mean_gen_len: 128 [2024-01-08 19:19:02] INFO gen_config.py:70: [System default] Setting max_gen_len: 512 [2024-01-08 19:19:02] INFO gen_config.py:70: [System default] Setting shift_fill_factor: 0.3 [2024-01-08 19:19:02] INFO gen_config.py:159: Dumping configuration file to: /home/junrushao/tmp/tmph17zk__o/mlc-chat-config.json /home/junrushao/micromamba/envs/python311/bin/python -m mlc_chat convert_weight /opt/scratch/assets/gpt_bigcode-santacoder --quantization q4f32_1 --source-format auto --output /home/junrushao/tmp/tmph17zk__o [2024-01-08 19:19:03] INFO auto_config.py:115: Found model configuration: /opt/scratch/assets/gpt_bigcode-santacoder/config.json [2024-01-08 19:19:04] INFO auto_device.py:76: Found device: cuda:0 [2024-01-08 19:19:04] INFO auto_device.py:76: Found device: cuda:1 [2024-01-08 19:19:04] INFO auto_device.py:76: Found device: cuda:2 [2024-01-08 19:19:04] INFO auto_device.py:76: Found device: cuda:3 [2024-01-08 19:19:04] INFO auto_device.py:85: Not found device: rocm:0 [2024-01-08 19:19:04] INFO auto_device.py:85: Not found device: metal:0 [2024-01-08 19:19:05] INFO auto_device.py:85: Not found device: vulkan:0 [2024-01-08 19:19:05] INFO auto_device.py:85: Not found device: opencl:0 [2024-01-08 19:19:05] INFO auto_device.py:33: Using device: cuda:0 [2024-01-08 19:19:05] INFO auto_weight.py:70: Finding weights in: /opt/scratch/assets/gpt_bigcode-santacoder [2024-01-08 19:19:05] INFO auto_weight.py:129: Found source weight format: huggingface-torch. Source configuration: /opt/scratch/assets/gpt_bigcode-santacoder/pytorch_model.bin [2024-01-08 19:19:05] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: /opt/scratch/assets/gpt_bigcode-santacoder/model.safetensors.index.json [2024-01-08 19:19:05] INFO auto_weight.py:106: Using source weight configuration: /opt/scratch/assets/gpt_bigcode-santacoder/pytorch_model.bin. Use `--source` to override. [2024-01-08 19:19:05] INFO auto_weight.py:110: Using source weight format: huggingface-torch. Use `--source-format` to override. [2024-01-08 19:19:05] INFO auto_config.py:151: Found model type: gpt_bigcode. Use `--model-type` to override. [2024-01-08 19:19:05] INFO gpt_bigcode_model.py:41: context_window_size not found in config.json. Falling back to n_positions (2048) [2024-01-08 19:19:05] INFO gpt_bigcode_model.py:54: prefill_chunk_size defaults to context_window_size (2048) [2024-01-08 19:19:08] INFO huggingface_loader.py:169: Loading HF parameters from: /opt/scratch/assets/gpt_bigcode-santacoder/pytorch_model.bin Weight conversion with arguments: --config /opt/scratch/assets/gpt_bigcode-santacoder/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_bigcode --device cuda:0 --source /opt/scratch/assets/gpt_bigcode-santacoder/pytorch_model.bin --source-format huggingface-torch --output /home/junrushao/tmp/tmph17zk__o 0%| | 0/293 [00:00