diff --git "a/logs.txt" "b/logs.txt" new file mode 100644--- /dev/null +++ "b/logs.txt" @@ -0,0 +1,547 @@ +/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Qwen2-0.5B-Instruct --quantization q0f32 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC +[2024-06-06 23:38:30] INFO auto_config.py:116: Found model configuration: /models/Qwen2-0.5B-Instruct/config.json +[2024-06-06 23:38:30] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override. +[2024-06-06 23:38:30] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768) +[2024-06-06 23:38:30] INFO qwen2_model.py:66: prefill_chunk_size defaults to 2048 +[2024-06-06 23:38:30] INFO config.py:107: Overriding max_batch_size from 1 to 80 +[2024-06-06 23:38:30] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 151643 +[2024-06-06 23:38:30] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 151643 +[2024-06-06 23:38:30] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [151645, 151643] +[2024-06-06 23:38:30] INFO gen_config.py:143: [generation_config.json] Setting repetition_penalty: 1.1 +[2024-06-06 23:38:30] INFO gen_config.py:143: [generation_config.json] Setting temperature: 0.7 +[2024-06-06 23:38:30] INFO gen_config.py:143: [generation_config.json] Setting top_p: 0.8 +[2024-06-06 23:38:30] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen2-0.5B-Instruct/tokenizer.model +[2024-06-06 23:38:30] INFO gen_config.py:155: Found tokenizer config: /models/Qwen2-0.5B-Instruct/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/tokenizer.json +[2024-06-06 23:38:30] INFO gen_config.py:155: Found tokenizer config: /models/Qwen2-0.5B-Instruct/vocab.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/vocab.json +[2024-06-06 23:38:30] INFO gen_config.py:155: Found tokenizer config: /models/Qwen2-0.5B-Instruct/merges.txt. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/merges.txt +[2024-06-06 23:38:30] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen2-0.5B-Instruct/added_tokens.json +[2024-06-06 23:38:30] INFO gen_config.py:155: Found tokenizer config: /models/Qwen2-0.5B-Instruct/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/tokenizer_config.json +[2024-06-06 23:38:30] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_level', 'prepend_space_in_encode': False, 'strip_space_in_decode': False} +[2024-06-06 23:38:30] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0 +[2024-06-06 23:38:30] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0 +[2024-06-06 23:38:30] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/mlc-chat-config.json +/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Qwen2-0.5B-Instruct --quantization q0f32 --output /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC +[2024-06-06 23:38:32] INFO auto_config.py:116: Found model configuration: /models/Qwen2-0.5B-Instruct/config.json +[2024-06-06 23:38:33] INFO auto_device.py:79: Found device: cuda:0 +[2024-06-06 23:38:35] INFO auto_device.py:88: Not found device: rocm:0 +[2024-06-06 23:38:36] INFO auto_device.py:88: Not found device: metal:0 +[2024-06-06 23:38:38] INFO auto_device.py:79: Found device: vulkan:0 +[2024-06-06 23:38:38] INFO auto_device.py:79: Found device: vulkan:1 +[2024-06-06 23:38:38] INFO auto_device.py:79: Found device: vulkan:2 +[2024-06-06 23:38:38] INFO auto_device.py:79: Found device: vulkan:3 +[2024-06-06 23:38:39] INFO auto_device.py:88: Not found device: opencl:0 +[2024-06-06 23:38:39] INFO auto_device.py:35: Using device: cuda:0 +[2024-06-06 23:38:39] INFO auto_weight.py:71: Finding weights in: /models/Qwen2-0.5B-Instruct +[2024-06-06 23:38:39] INFO auto_weight.py:137: Not found Huggingface PyTorch +[2024-06-06 23:38:39] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /models/Qwen2-0.5B-Instruct/model.safetensors.index.json +[2024-06-06 23:38:39] INFO auto_weight.py:107: Using source weight configuration: /models/Qwen2-0.5B-Instruct/model.safetensors.index.json. Use `--source` to override. +[2024-06-06 23:38:39] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override. +[2024-06-06 23:38:39] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override. +[2024-06-06 23:38:39] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768) +[2024-06-06 23:38:39] INFO qwen2_model.py:66: prefill_chunk_size defaults to 2048 +Traceback (most recent call last): + File "/opt/conda/envs/py310/lib/python3.10/runpy.py", line 196, in _run_module_as_main + return _run_code(code, main_globals, None, + File "/opt/conda/envs/py310/lib/python3.10/runpy.py", line 86, in _run_code + exec(code, run_globals) + File "/opt/conda/envs/py310/lib/python3.10/site-packages/mlc_llm/__main__.py", line 64, in + main() + File "/opt/conda/envs/py310/lib/python3.10/site-packages/mlc_llm/__main__.py", line 37, in main + cli.main(sys.argv[2:]) + File "/opt/conda/envs/py310/lib/python3.10/site-packages/mlc_llm/cli/convert_weight.py", line 88, in main + convert_weight( + File "/opt/conda/envs/py310/lib/python3.10/site-packages/mlc_llm/interface/convert_weight.py", line 181, in convert_weight + _convert_args(args) + File "/opt/conda/envs/py310/lib/python3.10/site-packages/mlc_llm/interface/convert_weight.py", line 145, in _convert_args + tvmjs.dump_ndarray_cache( + File "/opt/conda/envs/py310/lib/python3.10/site-packages/tvm/contrib/tvmjs.py", line 272, in dump_ndarray_cache + for k, origin_v in param_generator: + File "/opt/conda/envs/py310/lib/python3.10/site-packages/mlc_llm/interface/convert_weight.py", line 122, in _param_generator + loader = LOADER[args.source_format]( + File "/opt/conda/envs/py310/lib/python3.10/site-packages/mlc_llm/loader/huggingface_loader.py", line 99, in __init__ + check_parameter_usage(extern_param_map, set(self.torch_to_path.keys())) + File "/opt/conda/envs/py310/lib/python3.10/site-packages/mlc_llm/loader/utils.py", line 33, in check_parameter_usage + raise ValueError( +ValueError: The following extern parameters do not exist in the weight files: + lm_head.weight +Weight conversion with arguments: + --config /models/Qwen2-0.5B-Instruct/config.json + --quantization NoQuantize(name='q0f32', kind='no-quant', model_dtype='float32') + --model-type qwen2 + --device cuda:0 + --source /models/Qwen2-0.5B-Instruct/model.safetensors.index.json + --source-format huggingface-safetensor + --output /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC +Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC +/home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm gen_config /ssd2/models/Qwen2-0.5B-Instruct --quantization q0f32 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC +[2024-06-06 22:32:41] INFO auto_config.py:116: Found model configuration: /ssd2/models/Qwen2-0.5B-Instruct/config.json +[2024-06-06 22:32:41] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override. +[2024-06-06 22:32:41] INFO qwen2_model.py:50: context_window_size not found in config.json. Falling back to max_position_embeddings (32768) +[2024-06-06 22:32:41] INFO qwen2_model.py:67: prefill_chunk_size defaults to 2048 +[2024-06-06 22:32:41] INFO config.py:107: Overriding max_batch_size from 1 to 80 +[2024-06-06 22:32:41] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 151643 +[2024-06-06 22:32:41] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 151643 +[2024-06-06 22:32:41] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [151645, 151643] +[2024-06-06 22:32:41] INFO gen_config.py:143: [generation_config.json] Setting repetition_penalty: 1.1 +[2024-06-06 22:32:41] INFO gen_config.py:143: [generation_config.json] Setting temperature: 0.7 +[2024-06-06 22:32:41] INFO gen_config.py:143: [generation_config.json] Setting top_p: 0.8 +[2024-06-06 22:32:41] INFO gen_config.py:157: Not found tokenizer config: /ssd2/models/Qwen2-0.5B-Instruct/tokenizer.model +[2024-06-06 22:32:41] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Qwen2-0.5B-Instruct/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/tokenizer.json +[2024-06-06 22:32:41] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Qwen2-0.5B-Instruct/vocab.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/vocab.json +[2024-06-06 22:32:41] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Qwen2-0.5B-Instruct/merges.txt. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/merges.txt +[2024-06-06 22:32:41] INFO gen_config.py:157: Not found tokenizer config: /ssd2/models/Qwen2-0.5B-Instruct/added_tokens.json +[2024-06-06 22:32:41] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Qwen2-0.5B-Instruct/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/tokenizer_config.json +[2024-06-06 22:32:41] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_level', 'prepend_space_in_encode': False, 'strip_space_in_decode': False} +[2024-06-06 22:32:41] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0 +[2024-06-06 22:32:41] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0 +[2024-06-06 22:32:41] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/mlc-chat-config.json +/home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm convert_weight /ssd2/models/Qwen2-0.5B-Instruct --quantization q0f32 --output /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC +[2024-06-06 22:32:42] INFO auto_config.py:116: Found model configuration: /ssd2/models/Qwen2-0.5B-Instruct/config.json +[2024-06-06 22:32:43] INFO auto_device.py:79: Found device: cuda:0 +[2024-06-06 22:32:43] INFO auto_device.py:79: Found device: cuda:1 +[2024-06-06 22:32:44] INFO auto_device.py:88: Not found device: rocm:0 +[2024-06-06 22:32:45] INFO auto_device.py:88: Not found device: metal:0 +[2024-06-06 22:32:47] INFO auto_device.py:79: Found device: vulkan:0 +[2024-06-06 22:32:47] INFO auto_device.py:79: Found device: vulkan:1 +[2024-06-06 22:32:47] INFO auto_device.py:79: Found device: vulkan:2 +[2024-06-06 22:32:48] INFO auto_device.py:88: Not found device: opencl:0 +[2024-06-06 22:32:48] INFO auto_device.py:35: Using device: cuda:0 +[2024-06-06 22:32:48] INFO auto_weight.py:71: Finding weights in: /ssd2/models/Qwen2-0.5B-Instruct +[2024-06-06 22:32:48] INFO auto_weight.py:137: Not found Huggingface PyTorch +[2024-06-06 22:32:48] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /ssd2/models/Qwen2-0.5B-Instruct/model.safetensors.index.json +[2024-06-06 22:32:48] INFO auto_weight.py:107: Using source weight configuration: /ssd2/models/Qwen2-0.5B-Instruct/model.safetensors.index.json. Use `--source` to override. +[2024-06-06 22:32:48] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override. +[2024-06-06 22:32:48] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override. +[2024-06-06 22:32:48] INFO qwen2_model.py:50: context_window_size not found in config.json. Falling back to max_position_embeddings (32768) +[2024-06-06 22:32:48] INFO qwen2_model.py:67: prefill_chunk_size defaults to 2048 +Weight conversion with arguments: + --config /ssd2/models/Qwen2-0.5B-Instruct/config.json + --quantization NoQuantize(name='q0f32', kind='no-quant', model_dtype='float32') + --model-type qwen2 + --device cuda:0 + --source /ssd2/models/Qwen2-0.5B-Instruct/model.safetensors.index.json + --source-format huggingface-safetensor + --output /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC +Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC + 0%| | 0/170 [00:00 type is zero. + setattr(self, word, getattr(machar, word).flat[0]) +/home/rickzhou/miniconda3/envs/mlc/lib/python3.11/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. + return self._float_to_str(self.smallest_subnormal) + 1%| | 1/170 [00:05<15:51, 5.63s/it] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (896,), dtype: float32 + 1%| | 1/170 [00:05<15:51, 5.63s/it] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 1%| | 1/170 [00:05<15:51, 5.63s/it] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 1%| | 1/170 [00:05<15:51, 5.63s/it] 2%|▏ | 4/170 [00:05<03:02, 1.10s/it] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 2%|▏ | 4/170 [00:05<03:02, 1.10s/it] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 2%|▏ | 4/170 [00:05<03:02, 1.10s/it] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 2%|▏ | 4/170 [00:05<03:02, 1.10s/it] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 2%|▏ | 4/170 [00:05<03:02, 1.10s/it] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (896,), dtype: float32 + 2%|▏ | 4/170 [00:05<03:02, 1.10s/it] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 2%|▏ | 4/170 [00:05<03:02, 1.10s/it] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 2%|▏ | 4/170 [00:05<03:02, 1.10s/it] 6%|▋ | 11/170 [00:05<00:49, 3.20it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 6%|▋ | 11/170 [00:05<00:49, 3.20it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 6%|▋ | 11/170 [00:05<00:49, 3.20it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 6%|▋ | 11/170 [00:05<00:49, 3.20it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 6%|▋ | 11/170 [00:05<00:49, 3.20it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (896,), dtype: float32 + 6%|▋ | 11/170 [00:05<00:49, 3.20it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 6%|▋ | 11/170 [00:05<00:49, 3.20it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 6%|▋ | 11/170 [00:06<00:49, 3.20it/s] 11%|█ | 18/170 [00:06<00:25, 6.08it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 11%|█ | 18/170 [00:06<00:25, 6.08it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 11%|█ | 18/170 [00:06<00:25, 6.08it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 11%|█ | 18/170 [00:06<00:25, 6.08it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 11%|█ | 18/170 [00:06<00:25, 6.08it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (896,), dtype: float32 + 11%|█ | 18/170 [00:06<00:25, 6.08it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 11%|█ | 18/170 [00:06<00:25, 6.08it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 11%|█ | 18/170 [00:06<00:25, 6.08it/s] 15%|█▍ | 25/170 [00:06<00:15, 9.63it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 15%|█▍ | 25/170 [00:06<00:15, 9.63it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 15%|█▍ | 25/170 [00:06<00:15, 9.63it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 15%|█▍ | 25/170 [00:06<00:15, 9.63it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 15%|█▍ | 25/170 [00:06<00:15, 9.63it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (896,), dtype: float32 + 15%|█▍ | 25/170 [00:06<00:15, 9.63it/s] [2024-06-06 22:32:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 15%|█▍ | 25/170 [00:06<00:15, 9.63it/s] 18%|█▊ | 31/170 [00:06<00:10, 13.45it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 18%|█▊ | 31/170 [00:06<00:10, 13.45it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 18%|█▊ | 31/170 [00:06<00:10, 13.45it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 18%|█▊ | 31/170 [00:06<00:10, 13.45it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 18%|█▊ | 31/170 [00:06<00:10, 13.45it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 18%|█▊ | 31/170 [00:06<00:10, 13.45it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (896,), dtype: float32 + 18%|█▊ | 31/170 [00:06<00:10, 13.45it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 18%|█▊ | 31/170 [00:06<00:10, 13.45it/s] 22%|██▏ | 38/170 [00:06<00:07, 17.95it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 22%|██▏ | 38/170 [00:06<00:07, 17.95it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 22%|██▏ | 38/170 [00:06<00:07, 17.95it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 22%|██▏ | 38/170 [00:06<00:07, 17.95it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 22%|██▏ | 38/170 [00:06<00:07, 17.95it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 22%|██▏ | 38/170 [00:06<00:07, 17.95it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (896,), dtype: float32 + 22%|██▏ | 38/170 [00:06<00:07, 17.95it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 22%|██▏ | 38/170 [00:06<00:07, 17.95it/s] 26%|██▋ | 45/170 [00:06<00:05, 22.72it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 26%|██▋ | 45/170 [00:06<00:05, 22.72it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 26%|██▋ | 45/170 [00:06<00:05, 22.72it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 26%|██▋ | 45/170 [00:06<00:05, 22.72it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 26%|██▋ | 45/170 [00:06<00:05, 22.72it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 26%|██▋ | 45/170 [00:06<00:05, 22.72it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (896,), dtype: float32 + 26%|██▋ | 45/170 [00:06<00:05, 22.72it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 26%|██▋ | 45/170 [00:06<00:05, 22.72it/s] 31%|███ | 52/170 [00:06<00:04, 27.25it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 31%|███ | 52/170 [00:06<00:04, 27.25it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 31%|███ | 52/170 [00:06<00:04, 27.25it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 31%|███ | 52/170 [00:06<00:04, 27.25it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 31%|███ | 52/170 [00:06<00:04, 27.25it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 31%|███ | 52/170 [00:06<00:04, 27.25it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (896,), dtype: float32 + 31%|███ | 52/170 [00:06<00:04, 27.25it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 31%|███ | 52/170 [00:06<00:04, 27.25it/s] 35%|███▍ | 59/170 [00:06<00:03, 31.17it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 35%|███▍ | 59/170 [00:06<00:03, 31.17it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 35%|███▍ | 59/170 [00:06<00:03, 31.17it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 35%|███▍ | 59/170 [00:06<00:03, 31.17it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 35%|███▍ | 59/170 [00:06<00:03, 31.17it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 35%|███▍ | 59/170 [00:06<00:03, 31.17it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (896,), dtype: float32 + 35%|███▍ | 59/170 [00:07<00:03, 31.17it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 35%|███▍ | 59/170 [00:07<00:03, 31.17it/s] 39%|███▉ | 66/170 [00:07<00:02, 34.84it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 39%|███▉ | 66/170 [00:07<00:02, 34.84it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 39%|███▉ | 66/170 [00:07<00:02, 34.84it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 39%|███▉ | 66/170 [00:07<00:02, 34.84it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 39%|███▉ | 66/170 [00:07<00:02, 34.84it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 39%|███▉ | 66/170 [00:07<00:02, 34.84it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (896,), dtype: float32 + 39%|███▉ | 66/170 [00:07<00:02, 34.84it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 39%|███▉ | 66/170 [00:07<00:02, 34.84it/s] 43%|████▎ | 73/170 [00:07<00:02, 37.81it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 43%|████▎ | 73/170 [00:07<00:02, 37.81it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 43%|████▎ | 73/170 [00:07<00:02, 37.81it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 43%|████▎ | 73/170 [00:07<00:02, 37.81it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 43%|████▎ | 73/170 [00:07<00:02, 37.81it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 43%|████▎ | 73/170 [00:07<00:02, 37.81it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (896,), dtype: float32 + 43%|████▎ | 73/170 [00:07<00:02, 37.81it/s] [2024-06-06 22:32:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 43%|████▎ | 73/170 [00:07<00:02, 37.81it/s] 47%|████▋ | 80/170 [00:07<00:02, 39.89it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 47%|████▋ | 80/170 [00:07<00:02, 39.89it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 47%|████▋ | 80/170 [00:07<00:02, 39.89it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 47%|████▋ | 80/170 [00:07<00:02, 39.89it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 47%|████▋ | 80/170 [00:07<00:02, 39.89it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 47%|████▋ | 80/170 [00:07<00:02, 39.89it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (896,), dtype: float32 + 47%|████▋ | 80/170 [00:07<00:02, 39.89it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 47%|████▋ | 80/170 [00:07<00:02, 39.89it/s] 51%|█████ | 87/170 [00:07<00:01, 41.67it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 51%|█████ | 87/170 [00:07<00:01, 41.67it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 51%|█████ | 87/170 [00:07<00:01, 41.67it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 51%|█████ | 87/170 [00:07<00:01, 41.67it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 51%|█████ | 87/170 [00:07<00:01, 41.67it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 51%|█████ | 87/170 [00:07<00:01, 41.67it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (896,), dtype: float32 + 51%|█████ | 87/170 [00:07<00:01, 41.67it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 51%|█████ | 87/170 [00:07<00:01, 41.67it/s] 55%|█████▌ | 94/170 [00:07<00:01, 43.12it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 55%|█████▌ | 94/170 [00:07<00:01, 43.12it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 55%|█████▌ | 94/170 [00:07<00:01, 43.12it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 55%|█████▌ | 94/170 [00:07<00:01, 43.12it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 55%|█████▌ | 94/170 [00:07<00:01, 43.12it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 55%|█████▌ | 94/170 [00:07<00:01, 43.12it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (896,), dtype: float32 + 55%|█████▌ | 94/170 [00:07<00:01, 43.12it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 55%|█████▌ | 94/170 [00:07<00:01, 43.12it/s] 59%|█████▉ | 101/170 [00:07<00:01, 43.96it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 59%|█████▉ | 101/170 [00:07<00:01, 43.96it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 59%|█████▉ | 101/170 [00:07<00:01, 43.96it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 59%|█████▉ | 101/170 [00:07<00:01, 43.96it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 59%|█████▉ | 101/170 [00:07<00:01, 43.96it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 59%|█████▉ | 101/170 [00:07<00:01, 43.96it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (896,), dtype: float32 + 59%|█████▉ | 101/170 [00:07<00:01, 43.96it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 59%|█████▉ | 101/170 [00:07<00:01, 43.96it/s] 64%|██████▎ | 108/170 [00:07<00:01, 44.77it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 64%|██████▎ | 108/170 [00:07<00:01, 44.77it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 64%|██████▎ | 108/170 [00:08<00:01, 44.77it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 64%|██████▎ | 108/170 [00:08<00:01, 44.77it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 64%|██████▎ | 108/170 [00:08<00:01, 44.77it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 64%|██████▎ | 108/170 [00:08<00:01, 44.77it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (896,), dtype: float32 + 64%|██████▎ | 108/170 [00:08<00:01, 44.77it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 64%|██████▎ | 108/170 [00:08<00:01, 44.77it/s] 68%|██████▊ | 115/170 [00:08<00:01, 45.24it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 68%|██████▊ | 115/170 [00:08<00:01, 45.24it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 68%|██████▊ | 115/170 [00:08<00:01, 45.24it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 68%|██████▊ | 115/170 [00:08<00:01, 45.24it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 68%|██████▊ | 115/170 [00:08<00:01, 45.24it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 68%|██████▊ | 115/170 [00:08<00:01, 45.24it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (896,), dtype: float32 + 68%|██████▊ | 115/170 [00:08<00:01, 45.24it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 68%|██████▊ | 115/170 [00:08<00:01, 45.24it/s] 72%|███████▏ | 122/170 [00:08<00:01, 44.36it/s] [2024-06-06 22:32:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 72%|███████▏ | 122/170 [00:08<00:01, 44.36it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 72%|███████▏ | 122/170 [00:08<00:01, 44.36it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 72%|███████▏ | 122/170 [00:08<00:01, 44.36it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 72%|███████▏ | 122/170 [00:08<00:01, 44.36it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 72%|███████▏ | 122/170 [00:08<00:01, 44.36it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (896,), dtype: float32 + 72%|███████▏ | 122/170 [00:08<00:01, 44.36it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 72%|███████▏ | 122/170 [00:08<00:01, 44.36it/s] 76%|███████▌ | 129/170 [00:08<00:00, 44.88it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 76%|███████▌ | 129/170 [00:08<00:00, 44.88it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 76%|███████▌ | 129/170 [00:08<00:00, 44.88it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 76%|███████▌ | 129/170 [00:08<00:00, 44.88it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 76%|███████▌ | 129/170 [00:08<00:00, 44.88it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 76%|███████▌ | 129/170 [00:08<00:00, 44.88it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (896,), dtype: float32 + 76%|███████▌ | 129/170 [00:08<00:00, 44.88it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 76%|███████▌ | 129/170 [00:08<00:00, 44.88it/s] 80%|████████ | 136/170 [00:08<00:00, 45.43it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 80%|████████ | 136/170 [00:08<00:00, 45.43it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 80%|████████ | 136/170 [00:08<00:00, 45.43it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 80%|████████ | 136/170 [00:08<00:00, 45.43it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 80%|████████ | 136/170 [00:08<00:00, 45.43it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 80%|████████ | 136/170 [00:08<00:00, 45.43it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (896,), dtype: float32 + 80%|████████ | 136/170 [00:08<00:00, 45.43it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 80%|████████ | 136/170 [00:08<00:00, 45.43it/s] 84%|████████▍ | 143/170 [00:08<00:00, 45.78it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 84%|████████▍ | 143/170 [00:08<00:00, 45.78it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 84%|████████▍ | 143/170 [00:08<00:00, 45.78it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 84%|████████▍ | 143/170 [00:08<00:00, 45.78it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 84%|████████▍ | 143/170 [00:08<00:00, 45.78it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 84%|████████▍ | 143/170 [00:08<00:00, 45.78it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (896,), dtype: float32 + 84%|████████▍ | 143/170 [00:08<00:00, 45.78it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 84%|████████▍ | 143/170 [00:08<00:00, 45.78it/s] 88%|████████▊ | 150/170 [00:08<00:00, 45.93it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 88%|████████▊ | 150/170 [00:08<00:00, 45.93it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 88%|████████▊ | 150/170 [00:08<00:00, 45.93it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 88%|████████▊ | 150/170 [00:08<00:00, 45.93it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 88%|████████▊ | 150/170 [00:08<00:00, 45.93it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 88%|████████▊ | 150/170 [00:08<00:00, 45.93it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (896,), dtype: float32 + 88%|████████▊ | 150/170 [00:08<00:00, 45.93it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 88%|████████▊ | 150/170 [00:08<00:00, 45.93it/s] 92%|█████████▏| 157/170 [00:09<00:00, 46.05it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 92%|█████████▏| 157/170 [00:09<00:00, 46.05it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 92%|█████████▏| 157/170 [00:09<00:00, 46.05it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 92%|█████████▏| 157/170 [00:09<00:00, 46.05it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 92%|█████████▏| 157/170 [00:09<00:00, 46.05it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 92%|█████████▏| 157/170 [00:09<00:00, 46.05it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (896,), dtype: float32 + 92%|█████████▏| 157/170 [00:09<00:00, 46.05it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 92%|█████████▏| 157/170 [00:09<00:00, 46.05it/s] 96%|█████████▋| 164/170 [00:09<00:00, 46.19it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 96%|█████████▋| 164/170 [00:09<00:00, 46.19it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 96%|█████████▋| 164/170 [00:09<00:00, 46.19it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 96%|█████████▋| 164/170 [00:09<00:00, 46.19it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 96%|█████████▋| 164/170 [00:09<00:00, 46.19it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 96%|█████████▋| 164/170 [00:09<00:00, 46.19it/s] [2024-06-06 22:32:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (896,), dtype: float32 + 96%|█████████▋| 164/170 [00:09<00:00, 46.19it/s] 100%|██████████| 170/170 [00:09<00:00, 18.32it/s] +[2024-06-06 22:32:58] INFO huggingface_loader.py:197: Unloading HF weight file: /ssd2/models/Qwen2-0.5B-Instruct/model.safetensors +[2024-06-06 22:32:59] INFO stats.py:77: Time usage: HF loading: 3.282 sec; Pre-quantization mapping: 0.313 sec; Quantization: 0.000 sec +[2024-06-06 22:32:59] INFO stats.py:91: RAM usage: Peak RAM: 1.840 GB. Total bytes loaded from disk: 1.840 GB +[2024-06-06 22:32:59] INFO convert_weight.py:155: Parameter size after quantization: 1.840 GB +[2024-06-06 22:32:59] INFO convert_weight.py:160: Total parameters: 494,032,768 +[2024-06-06 22:32:59] INFO convert_weight.py:161: Bits per parameter: 32.000 +[2024-06-06 22:32:59] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC + +All finished, 25 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/ndarray-cache.json +Also saved a bf16 record to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/ndarray-cache-b16.json +/home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm gen_config /ssd2/models/Qwen2-0.5B-Instruct --quantization q0f32 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC +[2024-06-06 22:35:15] INFO auto_config.py:116: Found model configuration: /ssd2/models/Qwen2-0.5B-Instruct/config.json +[2024-06-06 22:35:15] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override. +[2024-06-06 22:35:15] INFO qwen2_model.py:50: context_window_size not found in config.json. Falling back to max_position_embeddings (32768) +[2024-06-06 22:35:15] INFO qwen2_model.py:67: prefill_chunk_size defaults to 2048 +[2024-06-06 22:35:15] INFO config.py:107: Overriding max_batch_size from 1 to 80 +[2024-06-06 22:35:15] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 151643 +[2024-06-06 22:35:15] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 151643 +[2024-06-06 22:35:15] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [151645, 151643] +[2024-06-06 22:35:15] INFO gen_config.py:143: [generation_config.json] Setting repetition_penalty: 1.1 +[2024-06-06 22:35:15] INFO gen_config.py:143: [generation_config.json] Setting temperature: 0.7 +[2024-06-06 22:35:15] INFO gen_config.py:143: [generation_config.json] Setting top_p: 0.8 +[2024-06-06 22:35:15] INFO gen_config.py:157: Not found tokenizer config: /ssd2/models/Qwen2-0.5B-Instruct/tokenizer.model +[2024-06-06 22:35:15] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Qwen2-0.5B-Instruct/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/tokenizer.json +[2024-06-06 22:35:15] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Qwen2-0.5B-Instruct/vocab.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/vocab.json +[2024-06-06 22:35:15] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Qwen2-0.5B-Instruct/merges.txt. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/merges.txt +[2024-06-06 22:35:15] INFO gen_config.py:157: Not found tokenizer config: /ssd2/models/Qwen2-0.5B-Instruct/added_tokens.json +[2024-06-06 22:35:15] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Qwen2-0.5B-Instruct/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/tokenizer_config.json +[2024-06-06 22:35:15] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_level', 'prepend_space_in_encode': False, 'strip_space_in_decode': False} +[2024-06-06 22:35:15] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0 +[2024-06-06 22:35:15] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0 +[2024-06-06 22:35:15] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/mlc-chat-config.json +/home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm convert_weight /ssd2/models/Qwen2-0.5B-Instruct --quantization q0f32 --output /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC +[2024-06-06 22:35:16] INFO auto_config.py:116: Found model configuration: /ssd2/models/Qwen2-0.5B-Instruct/config.json +[2024-06-06 22:35:17] INFO auto_device.py:79: Found device: cuda:0 +[2024-06-06 22:35:17] INFO auto_device.py:79: Found device: cuda:1 +[2024-06-06 22:35:18] INFO auto_device.py:88: Not found device: rocm:0 +[2024-06-06 22:35:19] INFO auto_device.py:88: Not found device: metal:0 +[2024-06-06 22:35:20] INFO auto_device.py:79: Found device: vulkan:0 +[2024-06-06 22:35:20] INFO auto_device.py:79: Found device: vulkan:1 +[2024-06-06 22:35:20] INFO auto_device.py:79: Found device: vulkan:2 +[2024-06-06 22:35:22] INFO auto_device.py:88: Not found device: opencl:0 +[2024-06-06 22:35:22] INFO auto_device.py:35: Using device: cuda:0 +[2024-06-06 22:35:22] INFO auto_weight.py:71: Finding weights in: /ssd2/models/Qwen2-0.5B-Instruct +[2024-06-06 22:35:22] INFO auto_weight.py:137: Not found Huggingface PyTorch +[2024-06-06 22:35:22] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /ssd2/models/Qwen2-0.5B-Instruct/model.safetensors.index.json +[2024-06-06 22:35:22] INFO auto_weight.py:107: Using source weight configuration: /ssd2/models/Qwen2-0.5B-Instruct/model.safetensors.index.json. Use `--source` to override. +[2024-06-06 22:35:22] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override. +[2024-06-06 22:35:22] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override. +[2024-06-06 22:35:22] INFO qwen2_model.py:50: context_window_size not found in config.json. Falling back to max_position_embeddings (32768) +[2024-06-06 22:35:22] INFO qwen2_model.py:67: prefill_chunk_size defaults to 2048 +Weight conversion with arguments: + --config /ssd2/models/Qwen2-0.5B-Instruct/config.json + --quantization NoQuantize(name='q0f32', kind='no-quant', model_dtype='float32') + --model-type qwen2 + --device cuda:0 + --source /ssd2/models/Qwen2-0.5B-Instruct/model.safetensors.index.json + --source-format huggingface-safetensor + --output /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC +Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC + 0%| | 0/170 [00:00 type is zero. + setattr(self, word, getattr(machar, word).flat[0]) +/home/rickzhou/miniconda3/envs/mlc/lib/python3.11/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. + return self._float_to_str(self.smallest_subnormal) + 1%| | 1/170 [00:03<09:40, 3.43s/it] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (896,), dtype: float32 + 1%| | 1/170 [00:03<09:40, 3.43s/it] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 1%| | 1/170 [00:03<09:40, 3.43s/it] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 1%| | 1/170 [00:03<09:40, 3.43s/it] 2%|▏ | 4/170 [00:03<01:53, 1.46it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 2%|▏ | 4/170 [00:03<01:53, 1.46it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 2%|▏ | 4/170 [00:03<01:53, 1.46it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 2%|▏ | 4/170 [00:03<01:53, 1.46it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 2%|▏ | 4/170 [00:03<01:53, 1.46it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (896,), dtype: float32 + 2%|▏ | 4/170 [00:03<01:53, 1.46it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 2%|▏ | 4/170 [00:03<01:53, 1.46it/s] 6%|▌ | 10/170 [00:03<00:35, 4.48it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 6%|▌ | 10/170 [00:03<00:35, 4.48it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 6%|▌ | 10/170 [00:03<00:35, 4.48it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 6%|▌ | 10/170 [00:03<00:35, 4.48it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 6%|▌ | 10/170 [00:03<00:35, 4.48it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 6%|▌ | 10/170 [00:03<00:35, 4.48it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (896,), dtype: float32 + 6%|▌ | 10/170 [00:03<00:35, 4.48it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 6%|▌ | 10/170 [00:03<00:35, 4.48it/s] 10%|█ | 17/170 [00:03<00:18, 8.35it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 10%|█ | 17/170 [00:03<00:18, 8.35it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 10%|█ | 17/170 [00:03<00:18, 8.35it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 10%|█ | 17/170 [00:03<00:18, 8.35it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 10%|█ | 17/170 [00:03<00:18, 8.35it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 10%|█ | 17/170 [00:03<00:18, 8.35it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (896,), dtype: float32 + 10%|█ | 17/170 [00:03<00:18, 8.35it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 10%|█ | 17/170 [00:03<00:18, 8.35it/s] 14%|█▍ | 24/170 [00:04<00:11, 12.32it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 14%|█▍ | 24/170 [00:04<00:11, 12.32it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 14%|█▍ | 24/170 [00:04<00:11, 12.32it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 14%|█▍ | 24/170 [00:04<00:11, 12.32it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 14%|█▍ | 24/170 [00:04<00:11, 12.32it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 14%|█▍ | 24/170 [00:04<00:11, 12.32it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (896,), dtype: float32 + 14%|█▍ | 24/170 [00:04<00:11, 12.32it/s] [2024-06-06 22:35:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 14%|█▍ | 24/170 [00:04<00:11, 12.32it/s] 18%|█▊ | 31/170 [00:04<00:08, 16.13it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 18%|█▊ | 31/170 [00:04<00:08, 16.13it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 18%|█▊ | 31/170 [00:04<00:08, 16.13it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 18%|█▊ | 31/170 [00:04<00:08, 16.13it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 18%|█▊ | 31/170 [00:04<00:08, 16.13it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 18%|█▊ | 31/170 [00:04<00:08, 16.13it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (896,), dtype: float32 + 18%|█▊ | 31/170 [00:04<00:08, 16.13it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 18%|█▊ | 31/170 [00:04<00:08, 16.13it/s] 22%|██▏ | 38/170 [00:04<00:06, 19.54it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 22%|██▏ | 38/170 [00:04<00:06, 19.54it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 22%|██▏ | 38/170 [00:04<00:06, 19.54it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 22%|██▏ | 38/170 [00:04<00:06, 19.54it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 22%|██▏ | 38/170 [00:04<00:06, 19.54it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 22%|██▏ | 38/170 [00:04<00:06, 19.54it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (896,), dtype: float32 + 22%|██▏ | 38/170 [00:04<00:06, 19.54it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 22%|██▏ | 38/170 [00:04<00:06, 19.54it/s] 26%|██▋ | 45/170 [00:04<00:05, 22.51it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 26%|██▋ | 45/170 [00:04<00:05, 22.51it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 26%|██▋ | 45/170 [00:04<00:05, 22.51it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 26%|██▋ | 45/170 [00:04<00:05, 22.51it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 26%|██▋ | 45/170 [00:04<00:05, 22.51it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 26%|██▋ | 45/170 [00:04<00:05, 22.51it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (896,), dtype: float32 + 26%|██▋ | 45/170 [00:04<00:05, 22.51it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 26%|██▋ | 45/170 [00:04<00:05, 22.51it/s] 31%|███ | 52/170 [00:05<00:04, 24.99it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 31%|███ | 52/170 [00:05<00:04, 24.99it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 31%|███ | 52/170 [00:05<00:04, 24.99it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 31%|███ | 52/170 [00:05<00:04, 24.99it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 31%|███ | 52/170 [00:05<00:04, 24.99it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 31%|███ | 52/170 [00:05<00:04, 24.99it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (896,), dtype: float32 + 31%|███ | 52/170 [00:05<00:04, 24.99it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 31%|███ | 52/170 [00:05<00:04, 24.99it/s] 35%|███▍ | 59/170 [00:05<00:04, 26.41it/s] [2024-06-06 22:35:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 35%|███▍ | 59/170 [00:05<00:04, 26.41it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 35%|███▍ | 59/170 [00:05<00:04, 26.41it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 35%|███▍ | 59/170 [00:05<00:04, 26.41it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 35%|███▍ | 59/170 [00:05<00:04, 26.41it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 35%|███▍ | 59/170 [00:05<00:04, 26.41it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (896,), dtype: float32 + 35%|███▍ | 59/170 [00:05<00:04, 26.41it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 35%|███▍ | 59/170 [00:05<00:04, 26.41it/s] 39%|███▉ | 66/170 [00:05<00:03, 27.45it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 39%|███▉ | 66/170 [00:05<00:03, 27.45it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 39%|███▉ | 66/170 [00:05<00:03, 27.45it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 39%|███▉ | 66/170 [00:05<00:03, 27.45it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 39%|███▉ | 66/170 [00:05<00:03, 27.45it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 39%|███▉ | 66/170 [00:05<00:03, 27.45it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (896,), dtype: float32 + 39%|███▉ | 66/170 [00:05<00:03, 27.45it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 39%|███▉ | 66/170 [00:05<00:03, 27.45it/s] 43%|████▎ | 73/170 [00:05<00:03, 28.49it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 43%|████▎ | 73/170 [00:05<00:03, 28.49it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 43%|████▎ | 73/170 [00:05<00:03, 28.49it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 43%|████▎ | 73/170 [00:05<00:03, 28.49it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 43%|████▎ | 73/170 [00:05<00:03, 28.49it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 43%|████▎ | 73/170 [00:05<00:03, 28.49it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (896,), dtype: float32 + 43%|████▎ | 73/170 [00:05<00:03, 28.49it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 43%|████▎ | 73/170 [00:05<00:03, 28.49it/s] 47%|████▋ | 80/170 [00:05<00:03, 28.99it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 47%|████▋ | 80/170 [00:05<00:03, 28.99it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 47%|████▋ | 80/170 [00:05<00:03, 28.99it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 47%|████▋ | 80/170 [00:06<00:03, 28.99it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 47%|████▋ | 80/170 [00:06<00:03, 28.99it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 47%|████▋ | 80/170 [00:06<00:03, 28.99it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (896,), dtype: float32 + 47%|████▋ | 80/170 [00:06<00:03, 28.99it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 47%|████▋ | 80/170 [00:06<00:03, 28.99it/s] 51%|█████ | 87/170 [00:06<00:02, 30.13it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 51%|█████ | 87/170 [00:06<00:02, 30.13it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 51%|█████ | 87/170 [00:06<00:02, 30.13it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 51%|█████ | 87/170 [00:06<00:02, 30.13it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 51%|█████ | 87/170 [00:06<00:02, 30.13it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 51%|█████ | 87/170 [00:06<00:02, 30.13it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (896,), dtype: float32 + 51%|█████ | 87/170 [00:06<00:02, 30.13it/s] [2024-06-06 22:35:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 51%|█████ | 87/170 [00:06<00:02, 30.13it/s] 55%|█████▌ | 94/170 [00:06<00:02, 30.81it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 55%|█████▌ | 94/170 [00:06<00:02, 30.81it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 55%|█████▌ | 94/170 [00:06<00:02, 30.81it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 55%|█████▌ | 94/170 [00:06<00:02, 30.81it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 55%|█████▌ | 94/170 [00:06<00:02, 30.81it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 55%|█████▌ | 94/170 [00:06<00:02, 30.81it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (896,), dtype: float32 + 55%|█████▌ | 94/170 [00:06<00:02, 30.81it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 55%|█████▌ | 94/170 [00:06<00:02, 30.81it/s] 59%|█████▉ | 101/170 [00:06<00:02, 31.26it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 59%|█████▉ | 101/170 [00:06<00:02, 31.26it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 59%|█████▉ | 101/170 [00:06<00:02, 31.26it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 59%|█████▉ | 101/170 [00:06<00:02, 31.26it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 59%|█████▉ | 101/170 [00:06<00:02, 31.26it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 59%|█████▉ | 101/170 [00:06<00:02, 31.26it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (896,), dtype: float32 + 59%|█████▉ | 101/170 [00:06<00:02, 31.26it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 59%|█████▉ | 101/170 [00:06<00:02, 31.26it/s] 64%|██████▎ | 108/170 [00:06<00:01, 31.47it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 64%|██████▎ | 108/170 [00:06<00:01, 31.47it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 64%|██████▎ | 108/170 [00:06<00:01, 31.47it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 64%|██████▎ | 108/170 [00:06<00:01, 31.47it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 64%|██████▎ | 108/170 [00:06<00:01, 31.47it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 64%|██████▎ | 108/170 [00:06<00:01, 31.47it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (896,), dtype: float32 + 64%|██████▎ | 108/170 [00:06<00:01, 31.47it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 64%|██████▎ | 108/170 [00:06<00:01, 31.47it/s] 68%|██████▊ | 115/170 [00:07<00:01, 31.64it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 68%|██████▊ | 115/170 [00:07<00:01, 31.64it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 68%|██████▊ | 115/170 [00:07<00:01, 31.64it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 68%|██████▊ | 115/170 [00:07<00:01, 31.64it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 68%|██████▊ | 115/170 [00:07<00:01, 31.64it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 68%|██████▊ | 115/170 [00:07<00:01, 31.64it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (896,), dtype: float32 + 68%|██████▊ | 115/170 [00:07<00:01, 31.64it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 68%|██████▊ | 115/170 [00:07<00:01, 31.64it/s] 72%|███████▏ | 122/170 [00:07<00:01, 31.68it/s] [2024-06-06 22:35:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 72%|███████▏ | 122/170 [00:07<00:01, 31.68it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 72%|███████▏ | 122/170 [00:07<00:01, 31.68it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 72%|███████▏ | 122/170 [00:07<00:01, 31.68it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 72%|███████▏ | 122/170 [00:07<00:01, 31.68it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 72%|███████▏ | 122/170 [00:07<00:01, 31.68it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (896,), dtype: float32 + 72%|███████▏ | 122/170 [00:07<00:01, 31.68it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 72%|███████▏ | 122/170 [00:07<00:01, 31.68it/s] 76%|███████▌ | 129/170 [00:07<00:01, 31.82it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 76%|███████▌ | 129/170 [00:07<00:01, 31.82it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 76%|███████▌ | 129/170 [00:07<00:01, 31.82it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 76%|███████▌ | 129/170 [00:07<00:01, 31.82it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 76%|███████▌ | 129/170 [00:07<00:01, 31.82it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 76%|███████▌ | 129/170 [00:07<00:01, 31.82it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (896,), dtype: float32 + 76%|███████▌ | 129/170 [00:07<00:01, 31.82it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 76%|███████▌ | 129/170 [00:07<00:01, 31.82it/s] 80%|████████ | 136/170 [00:07<00:01, 31.78it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 80%|████████ | 136/170 [00:07<00:01, 31.78it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 80%|████████ | 136/170 [00:07<00:01, 31.78it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 80%|████████ | 136/170 [00:07<00:01, 31.78it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 80%|████████ | 136/170 [00:07<00:01, 31.78it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 80%|████████ | 136/170 [00:07<00:01, 31.78it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (896,), dtype: float32 + 80%|████████ | 136/170 [00:07<00:01, 31.78it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 80%|████████ | 136/170 [00:07<00:01, 31.78it/s] 84%|████████▍ | 143/170 [00:07<00:00, 31.98it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 84%|████████▍ | 143/170 [00:07<00:00, 31.98it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 84%|████████▍ | 143/170 [00:07<00:00, 31.98it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 84%|████████▍ | 143/170 [00:07<00:00, 31.98it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 84%|████████▍ | 143/170 [00:07<00:00, 31.98it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 84%|████████▍ | 143/170 [00:07<00:00, 31.98it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (896,), dtype: float32 + 84%|████████▍ | 143/170 [00:07<00:00, 31.98it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 84%|████████▍ | 143/170 [00:07<00:00, 31.98it/s] 88%|██���█████▊ | 150/170 [00:08<00:00, 31.52it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 88%|████████▊ | 150/170 [00:08<00:00, 31.52it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 88%|████████▊ | 150/170 [00:08<00:00, 31.52it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 88%|████████▊ | 150/170 [00:08<00:00, 31.52it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 88%|████████▊ | 150/170 [00:08<00:00, 31.52it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 88%|████████▊ | 150/170 [00:08<00:00, 31.52it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (896,), dtype: float32 + 88%|████████▊ | 150/170 [00:08<00:00, 31.52it/s] [2024-06-06 22:35:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 88%|████████▊ | 150/170 [00:08<00:00, 31.52it/s] 92%|█████████▏| 157/170 [00:08<00:00, 31.84it/s] [2024-06-06 22:35:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 92%|█████████▏| 157/170 [00:08<00:00, 31.84it/s] [2024-06-06 22:35:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 92%|█████████▏| 157/170 [00:08<00:00, 31.84it/s] [2024-06-06 22:35:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 92%|█████████▏| 157/170 [00:08<00:00, 31.84it/s] [2024-06-06 22:35:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 92%|█████████▏| 157/170 [00:08<00:00, 31.84it/s] [2024-06-06 22:35:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 92%|█████████▏| 157/170 [00:08<00:00, 31.84it/s] [2024-06-06 22:35:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (896,), dtype: float32 + 92%|█████████▏| 157/170 [00:08<00:00, 31.84it/s] [2024-06-06 22:35:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.mlp.down_proj.weight", shape: (896, 4864), dtype: float32 + 92%|█████████▏| 157/170 [00:08<00:00, 31.84it/s] 96%|█████████▋| 164/170 [00:08<00:00, 31.97it/s] [2024-06-06 22:35:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float32 + 96%|█████████▋| 164/170 [00:08<00:00, 31.97it/s] [2024-06-06 22:35:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (896,), dtype: float32 + 96%|█████████▋| 164/170 [00:08<00:00, 31.97it/s] [2024-06-06 22:35:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.c_attn.bias", shape: (1152,), dtype: float32 + 96%|█████████▋| 164/170 [00:08<00:00, 31.97it/s] [2024-06-06 22:35:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.c_attn.weight", shape: (1152, 896), dtype: float32 + 96%|█████████▋| 164/170 [00:08<00:00, 31.97it/s] [2024-06-06 22:35:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.o_proj.weight", shape: (896, 896), dtype: float32 + 96%|█████████▋| 164/170 [00:08<00:00, 31.97it/s] [2024-06-06 22:35:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (896,), dtype: float32 + 96%|█████████▋| 164/170 [00:08<00:00, 31.97it/s] 100%|██████████| 170/170 [00:08<00:00, 19.72it/s] +[2024-06-06 22:35:32] INFO huggingface_loader.py:197: Unloading HF weight file: /ssd2/models/Qwen2-0.5B-Instruct/model.safetensors +[2024-06-06 22:35:32] INFO stats.py:77: Time usage: HF loading: 1.497 sec; Pre-quantization mapping: 0.325 sec; Quantization: 0.000 sec +[2024-06-06 22:35:32] INFO stats.py:91: RAM usage: Peak RAM: 1.840 GB. Total bytes loaded from disk: 1.840 GB +[2024-06-06 22:35:32] INFO convert_weight.py:155: Parameter size after quantization: 1.840 GB +[2024-06-06 22:35:32] INFO convert_weight.py:160: Total parameters: 494,032,768 +[2024-06-06 22:35:32] INFO convert_weight.py:161: Bits per parameter: 32.000 +[2024-06-06 22:35:32] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC + +All finished, 25 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/ndarray-cache.json +Also saved a bf16 record to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f32-MLC/ndarray-cache-b16.json