diff --git "a/logs.txt" "b/logs.txt" new file mode 100644--- /dev/null +++ "b/logs.txt" @@ -0,0 +1,498 @@ +/home/junrushao/micromamba/envs/python311/bin/python -m mlc_chat gen_config /opt/scratch/assets/Mixtral-8x7B-Instruct-v0.1 --quantization q3f16_1 --conv-template LM --output /home/junrushao/tmp/tmpoazjl9lj --context-window-size 8192 +[2024-01-08 05:07:21] INFO auto_config.py:115: Found model configuration: /opt/scratch/assets/Mixtral-8x7B-Instruct-v0.1/config.json +[2024-01-08 05:07:21] INFO auto_config.py:151: Found model type: mixtral. Use `--model-type` to override. +[2024-01-08 05:07:21] INFO mistral_model.py:54: prefill_chunk_size defaults to sliding_window_size (4096) +[2024-01-08 05:07:21] WARNING compiler_flags.py:111: Warning: Cannot override context_window_size, because MixtralConfig does not have this field +[2024-01-08 05:07:21] INFO gen_config.py:117: [generation_config.json] Setting bos_token_id: 1 +[2024-01-08 05:07:21] INFO gen_config.py:117: [generation_config.json] Setting eos_token_id: 2 +[2024-01-08 05:07:21] INFO gen_config.py:129: Found tokenizer config: /opt/scratch/assets/Mixtral-8x7B-Instruct-v0.1/tokenizer.model. Copying to /home/junrushao/tmp/tmpoazjl9lj/tokenizer.model +[2024-01-08 05:07:21] INFO gen_config.py:129: Found tokenizer config: /opt/scratch/assets/Mixtral-8x7B-Instruct-v0.1/tokenizer.json. Copying to /home/junrushao/tmp/tmpoazjl9lj/tokenizer.json +[2024-01-08 05:07:21] INFO gen_config.py:131: Not found tokenizer config: /opt/scratch/assets/Mixtral-8x7B-Instruct-v0.1/vocab.json +[2024-01-08 05:07:21] INFO gen_config.py:131: Not found tokenizer config: /opt/scratch/assets/Mixtral-8x7B-Instruct-v0.1/merges.txt +[2024-01-08 05:07:21] INFO gen_config.py:131: Not found tokenizer config: /opt/scratch/assets/Mixtral-8x7B-Instruct-v0.1/added_tokens.json +[2024-01-08 05:07:21] INFO gen_config.py:129: Found tokenizer config: /opt/scratch/assets/Mixtral-8x7B-Instruct-v0.1/tokenizer_config.json. Copying to /home/junrushao/tmp/tmpoazjl9lj/tokenizer_config.json +[2024-01-08 05:07:21] INFO gen_config.py:70: [System default] Setting pad_token_id: 0 +[2024-01-08 05:07:21] INFO gen_config.py:70: [System default] Setting temperature: 0.7 +[2024-01-08 05:07:21] INFO gen_config.py:70: [System default] Setting repetition_penalty: 1.0 +[2024-01-08 05:07:21] INFO gen_config.py:70: [System default] Setting top_p: 0.95 +[2024-01-08 05:07:21] INFO gen_config.py:70: [System default] Setting mean_gen_len: 128 +[2024-01-08 05:07:21] INFO gen_config.py:70: [System default] Setting max_gen_len: 512 +[2024-01-08 05:07:21] INFO gen_config.py:70: [System default] Setting shift_fill_factor: 0.3 +[2024-01-08 05:07:21] INFO gen_config.py:159: Dumping configuration file to: /home/junrushao/tmp/tmpoazjl9lj/mlc-chat-config.json +/home/junrushao/micromamba/envs/python311/bin/python -m mlc_chat convert_weight /opt/scratch/assets/Mixtral-8x7B-Instruct-v0.1 --quantization q3f16_1 --source-format auto --output /home/junrushao/tmp/tmpoazjl9lj +[2024-01-08 05:07:22] INFO auto_config.py:115: Found model configuration: /opt/scratch/assets/Mixtral-8x7B-Instruct-v0.1/config.json +[2024-01-08 05:07:22] INFO auto_device.py:76: Found device: cuda:0 +[2024-01-08 05:07:22] INFO auto_device.py:76: Found device: cuda:1 +[2024-01-08 05:07:22] INFO auto_device.py:76: Found device: cuda:2 +[2024-01-08 05:07:22] INFO auto_device.py:76: Found device: cuda:3 +[2024-01-08 05:07:23] INFO auto_device.py:85: Not found device: rocm:0 +[2024-01-08 05:07:23] INFO auto_device.py:85: Not found device: metal:0 +[2024-01-08 05:07:23] INFO auto_device.py:85: Not found device: vulkan:0 +[2024-01-08 05:07:24] INFO auto_device.py:85: Not found device: opencl:0 +[2024-01-08 05:07:24] INFO auto_device.py:33: Using device: cuda:0 +[2024-01-08 05:07:24] INFO auto_weight.py:70: Finding weights in: /opt/scratch/assets/Mixtral-8x7B-Instruct-v0.1 +[2024-01-08 05:07:24] INFO auto_weight.py:136: Not found Huggingface PyTorch +[2024-01-08 05:07:24] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: /opt/scratch/assets/Mixtral-8x7B-Instruct-v0.1/model.safetensors.index.json +[2024-01-08 05:07:24] INFO auto_weight.py:106: Using source weight configuration: /opt/scratch/assets/Mixtral-8x7B-Instruct-v0.1/model.safetensors.index.json. Use `--source` to override. +[2024-01-08 05:07:24] INFO auto_weight.py:110: Using source weight format: huggingface-safetensor. Use `--source-format` to override. +[2024-01-08 05:07:24] INFO auto_config.py:151: Found model type: mixtral. Use `--model-type` to override. +[2024-01-08 05:07:24] INFO mistral_model.py:54: prefill_chunk_size defaults to sliding_window_size (4096) +Weight conversion with arguments: + --config /opt/scratch/assets/Mixtral-8x7B-Instruct-v0.1/config.json + --quantization GroupQuantize(name='q3f16_1', kind='group-quant', group_size=40, quantize_dtype='int3', storage_dtype='uint32', model_dtype='float16', num_elem_per_storage=10, num_storage_per_group=4, max_int_value=3) + --model-type mixtral + --device cuda:0 + --source /opt/scratch/assets/Mixtral-8x7B-Instruct-v0.1/model.safetensors.index.json + --source-format huggingface-safetensor + --output /home/junrushao/tmp/tmpoazjl9lj + 0%| | 0/227 [00:00