diff --git "a/logs.txt" "b/logs.txt" new file mode 100644--- /dev/null +++ "b/logs.txt" @@ -0,0 +1,388 @@ +mlc_chat gen_mlc_chat_config --model /models/Llama-2-7b-chat-hf --quantization q4f32_1 --conv-template llama-2 --context-window-size 4096 --output /tmp/tmpp14fhh12 +/home/hongyi/.local/bin/mlc_chat:6: DeprecationWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html + from pkg_resources import load_entry_point +[2023-11-28 19:58:07] INFO auto_config.py:62: Found model configuration: /models/Llama-2-7b-chat-hf/config.json +[2023-11-28 19:58:07] INFO auto_config.py:99: Found model type: llama. Use `--model-type` to override. +[2023-11-28 19:58:07] INFO llama_model.py:42: context_window_size not found in config.json. Falling back to max_position_embeddings (4096) +[2023-11-28 19:58:07] INFO flags_model_config_override.py:24: Overriding context_window_size from 4096 to 4096 +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:77: [config.json] Setting bos_token_id: 1 +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:77: [config.json] Setting eos_token_id: 2 +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:81: Found generation_config.json: /models/Llama-2-7b-chat-hf/generation_config.json +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:87: [generation_config.json] Setting pad_token_id: 0 +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:87: [generation_config.json] Setting temperature: 0.6 +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:87: [generation_config.json] Setting top_p: 0.9 +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:97: Found tokenizer config: /models/Llama-2-7b-chat-hf/tokenizer.model. Copying to /tmp/tmpp14fhh12/tokenizer.model +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:97: Found tokenizer config: /models/Llama-2-7b-chat-hf/tokenizer.json. Copying to /tmp/tmpp14fhh12/tokenizer.json +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:99: Not found tokenizer config: /models/Llama-2-7b-chat-hf/vocab.json +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:99: Not found tokenizer config: /models/Llama-2-7b-chat-hf/merges.txt +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:99: Not found tokenizer config: /models/Llama-2-7b-chat-hf/added_tokens.json +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:97: Found tokenizer config: /models/Llama-2-7b-chat-hf/tokenizer_config.json. Copying to /tmp/tmpp14fhh12/tokenizer_config.json +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:104: [System default] Setting repetition_penalty: 1.0 +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:104: [System default] Setting mean_gen_len: 128 +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:104: [System default] Setting max_gen_len: 512 +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:104: [System default] Setting shift_fill_factor: 0.3 +[2023-11-28 19:58:07] INFO gen_mlc_chat_config.py:109: Dumping configuration file to: /tmp/tmpp14fhh12/mlc-chat-config.json +mlc_chat convert_weight --model /models/Llama-2-7b-chat-hf --quantization q4f32_1 --source-format auto --output /tmp/tmpp14fhh12 +/home/hongyi/.local/bin/mlc_chat:6: DeprecationWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html + from pkg_resources import load_entry_point +[2023-11-28 19:58:07] INFO auto_config.py:62: Found model configuration: /models/Llama-2-7b-chat-hf/config.json +[2023-11-28 19:58:07] INFO auto_device.py:37: Using device: cuda:0. Use `--device` to override. +[2023-11-28 19:58:07] INFO auto_weight.py:70: Finding weights in: /models/Llama-2-7b-chat-hf +[2023-11-28 19:58:07] INFO auto_weight.py:120: Found source weight format: huggingface-torch. Source configuration: /models/Llama-2-7b-chat-hf/pytorch_model.bin.index.json +[2023-11-28 19:58:07] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: /models/Llama-2-7b-chat-hf/model.safetensors.index.json +[2023-11-28 19:58:07] INFO auto_weight.py:106: Using source weight configuration: /models/Llama-2-7b-chat-hf/pytorch_model.bin.index.json. Use `--source` to override. +[2023-11-28 19:58:07] INFO auto_weight.py:110: Using source weight format: huggingface-torch. Use `--source-format` to override. +[2023-11-28 19:58:07] INFO auto_config.py:99: Found model type: llama. Use `--model-type` to override. +[2023-11-28 19:58:07] INFO llama_model.py:42: context_window_size not found in config.json. Falling back to max_position_embeddings (4096) +Weight conversion with arguments: + --config /models/Llama-2-7b-chat-hf/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 /models/Llama-2-7b-chat-hf/pytorch_model.bin.index.json + --source-format huggingface-torch + --output /tmp/tmpp14fhh12 + 0%| | 0/195 [00:00