diff --git "a/logs.txt" "b/logs.txt" new file mode 100644--- /dev/null +++ "b/logs.txt" @@ -0,0 +1,357 @@ +/home/cfruan/.conda/envs/mlc-source-311/bin/python -m mlc_chat gen_config /models/gemma-7b-it --quantization q4f16_2 --conv-template gemma_instruction --output /tmp/tmpqbj3qggh --context-window-size 8192 --prefill-chunk-size 1024 +[2024-02-22 18:06:28] INFO auto_config.py:115: Found model configuration: /models/gemma-7b-it/config.json +[2024-02-22 18:06:28] INFO auto_config.py:153: Found model type: gemma. Use `--model-type` to override. +[2024-02-22 18:06:28] INFO gemma_model.py:55: context_window_size not found in config.json. Falling back to max_position_embeddings (8192) +[2024-02-22 18:06:28] INFO gemma_model.py:70: prefill_chunk_size defaults to context_window_size (8192) +[2024-02-22 18:06:28] INFO config.py:106: Overriding context_window_size from 8192 to 8192 +[2024-02-22 18:06:28] INFO config.py:106: Overriding prefill_chunk_size from 8192 to 1024 +[2024-02-22 18:06:28] INFO config.py:106: Overriding max_batch_size from 1 to 80 +[2024-02-22 18:06:28] INFO gen_config.py:121: [generation_config.json] Setting bos_token_id: 2 +[2024-02-22 18:06:28] INFO gen_config.py:121: [generation_config.json] Setting eos_token_id: 1 +[2024-02-22 18:06:28] INFO gen_config.py:121: [generation_config.json] Setting pad_token_id: 0 +[2024-02-22 18:06:28] INFO gen_config.py:133: Found tokenizer config: /models/gemma-7b-it/tokenizer.model. Copying to /tmp/tmpqbj3qggh/tokenizer.model +[2024-02-22 18:06:28] INFO gen_config.py:133: Found tokenizer config: /models/gemma-7b-it/tokenizer.json. Copying to /tmp/tmpqbj3qggh/tokenizer.json +[2024-02-22 18:06:28] INFO gen_config.py:135: Not found tokenizer config: /models/gemma-7b-it/vocab.json +[2024-02-22 18:06:28] INFO gen_config.py:135: Not found tokenizer config: /models/gemma-7b-it/merges.txt +[2024-02-22 18:06:28] INFO gen_config.py:135: Not found tokenizer config: /models/gemma-7b-it/added_tokens.json +[2024-02-22 18:06:28] INFO gen_config.py:133: Found tokenizer config: /models/gemma-7b-it/tokenizer_config.json. Copying to /tmp/tmpqbj3qggh/tokenizer_config.json +[2024-02-22 18:06:28] INFO gen_config.py:74: [System default] Setting temperature: 0.7 +[2024-02-22 18:06:28] INFO gen_config.py:74: [System default] Setting presence_penalty: 0.0 +[2024-02-22 18:06:28] INFO gen_config.py:74: [System default] Setting frequency_penalty: 0.0 +[2024-02-22 18:06:28] INFO gen_config.py:74: [System default] Setting repetition_penalty: 1.0 +[2024-02-22 18:06:28] INFO gen_config.py:74: [System default] Setting top_p: 0.95 +[2024-02-22 18:06:28] INFO gen_config.py:74: [System default] Setting mean_gen_len: 128 +[2024-02-22 18:06:28] INFO gen_config.py:74: [System default] Setting max_gen_len: 512 +[2024-02-22 18:06:28] INFO gen_config.py:74: [System default] Setting shift_fill_factor: 0.3 +[2024-02-22 18:06:28] INFO gen_config.py:186: Dumping configuration file to: /tmp/tmpqbj3qggh/mlc-chat-config.json +/home/cfruan/.conda/envs/mlc-source-311/bin/python -m mlc_chat convert_weight /models/gemma-7b-it --quantization q4f16_2 --source-format auto --output /tmp/tmpqbj3qggh +[2024-02-22 18:06:31] INFO auto_config.py:115: Found model configuration: /models/gemma-7b-it/config.json +[2024-02-22 18:06:32] INFO auto_device.py:76: Found device: cuda:0 +[2024-02-22 18:06:32] INFO auto_device.py:76: Found device: cuda:1 +[2024-02-22 18:06:34] INFO auto_device.py:85: Not found device: rocm:0 +[2024-02-22 18:06:36] INFO auto_device.py:85: Not found device: metal:0 +[2024-02-22 18:06:47] INFO auto_device.py:76: Found device: vulkan:0 +[2024-02-22 18:06:47] INFO auto_device.py:76: Found device: vulkan:1 +[2024-02-22 18:06:47] INFO auto_device.py:76: Found device: vulkan:2 +[2024-02-22 18:06:48] INFO auto_device.py:85: Not found device: opencl:0 +[2024-02-22 18:06:48] INFO auto_device.py:33: Using device: cuda:0 +[2024-02-22 18:06:48] INFO auto_weight.py:70: Finding weights in: /models/gemma-7b-it +[2024-02-22 18:06:48] INFO auto_weight.py:136: Not found Huggingface PyTorch +[2024-02-22 18:06:48] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: /models/gemma-7b-it/model.safetensors.index.json +[2024-02-22 18:06:48] INFO auto_weight.py:106: Using source weight configuration: /models/gemma-7b-it/model.safetensors.index.json. Use `--source` to override. +[2024-02-22 18:06:48] INFO auto_weight.py:110: Using source weight format: huggingface-safetensor. Use `--source-format` to override. +[2024-02-22 18:06:48] INFO auto_config.py:153: Found model type: gemma. Use `--model-type` to override. +[2024-02-22 18:06:48] INFO gemma_model.py:55: context_window_size not found in config.json. Falling back to max_position_embeddings (8192) +[2024-02-22 18:06:48] INFO gemma_model.py:70: prefill_chunk_size defaults to context_window_size (8192) +Weight conversion with arguments: + --config /models/gemma-7b-it/config.json + --quantization GroupQuantize(name='q4f16_2', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float16', linear_weight_layout='NK', quantize_embedding=False, quantize_final_fc=False, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7) + --model-type gemma + --device cuda:0 + --source /models/gemma-7b-it/model.safetensors.index.json + --source-format huggingface-safetensor + --output /tmp/tmpqbj3qggh + 0%| | 0/170 [00:00