| /opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Qwen2-1.5B-Instruct --quantization q0f16 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC | |
| [2024-06-06 23:39:30] INFO auto_config.py:116: [92mFound[0m model configuration: /models/Qwen2-1.5B-Instruct/config.json | |
| [2024-06-06 23:39:30] INFO auto_config.py:154: [92mFound[0m model type: [1mqwen2[0m. Use `--model-type` to override. | |
| [2024-06-06 23:39:30] INFO qwen2_model.py:49: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (32768) | |
| [2024-06-06 23:39:30] INFO qwen2_model.py:66: [1mprefill_chunk_size[0m defaults to 2048 | |
| [2024-06-06 23:39:30] INFO config.py:107: Overriding [1mmax_batch_size[0m from 1 to 80 | |
| [2024-06-06 23:39:30] INFO gen_config.py:143: [generation_config.json] Setting [1mbos_token_id[0m: 151643 | |
| [2024-06-06 23:39:30] INFO gen_config.py:143: [generation_config.json] Setting [1mpad_token_id[0m: 151643 | |
| [2024-06-06 23:39:30] INFO gen_config.py:143: [generation_config.json] Setting [1meos_token_id[0m: [151645, 151643] | |
| [2024-06-06 23:39:30] INFO gen_config.py:143: [generation_config.json] Setting [1mrepetition_penalty[0m: 1.1 | |
| [2024-06-06 23:39:30] INFO gen_config.py:143: [generation_config.json] Setting [1mtemperature[0m: 0.7 | |
| [2024-06-06 23:39:30] INFO gen_config.py:143: [generation_config.json] Setting [1mtop_p[0m: 0.8 | |
| [2024-06-06 23:39:30] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Qwen2-1.5B-Instruct/tokenizer.model | |
| [2024-06-06 23:39:30] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Qwen2-1.5B-Instruct/tokenizer.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/tokenizer.json[0m | |
| [2024-06-06 23:39:30] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Qwen2-1.5B-Instruct/vocab.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/vocab.json[0m | |
| [2024-06-06 23:39:30] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Qwen2-1.5B-Instruct/merges.txt. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/merges.txt[0m | |
| [2024-06-06 23:39:30] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Qwen2-1.5B-Instruct/added_tokens.json | |
| [2024-06-06 23:39:30] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Qwen2-1.5B-Instruct/tokenizer_config.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/tokenizer_config.json[0m | |
| [2024-06-06 23:39:30] 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 23:39:30] INFO gen_config.py:32: [System default] Setting [1mpresence_penalty[0m: 0.0 | |
| [2024-06-06 23:39:30] INFO gen_config.py:32: [System default] Setting [1mfrequency_penalty[0m: 0.0 | |
| [2024-06-06 23:39:30] INFO gen_config.py:223: Dumping configuration file to: [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/mlc-chat-config.json[0m | |
| /opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Qwen2-1.5B-Instruct --quantization q0f16 --output /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC | |
| [2024-06-06 23:39:32] INFO auto_config.py:116: [92mFound[0m model configuration: /models/Qwen2-1.5B-Instruct/config.json | |
| [2024-06-06 23:39:33] INFO auto_device.py:79: [92mFound[0m device: cuda:0 | |
| [2024-06-06 23:39:35] INFO auto_device.py:88: [91mNot found[0m device: rocm:0 | |
| [2024-06-06 23:39:36] INFO auto_device.py:88: [91mNot found[0m device: metal:0 | |
| [2024-06-06 23:39:38] INFO auto_device.py:79: [92mFound[0m device: vulkan:0 | |
| [2024-06-06 23:39:38] INFO auto_device.py:79: [92mFound[0m device: vulkan:1 | |
| [2024-06-06 23:39:38] INFO auto_device.py:79: [92mFound[0m device: vulkan:2 | |
| [2024-06-06 23:39:38] INFO auto_device.py:79: [92mFound[0m device: vulkan:3 | |
| [2024-06-06 23:39:40] INFO auto_device.py:88: [91mNot found[0m device: opencl:0 | |
| [2024-06-06 23:39:40] INFO auto_device.py:35: Using device: [1mcuda:0[0m | |
| [2024-06-06 23:39:40] INFO auto_weight.py:71: Finding weights in: /models/Qwen2-1.5B-Instruct | |
| [2024-06-06 23:39:40] INFO auto_weight.py:137: [91mNot found[0m Huggingface PyTorch | |
| [2024-06-06 23:39:40] INFO auto_weight.py:144: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: /models/Qwen2-1.5B-Instruct/model.safetensors.index.json | |
| [2024-06-06 23:39:40] INFO auto_weight.py:107: Using source weight configuration: [1m/models/Qwen2-1.5B-Instruct/model.safetensors.index.json[0m. Use `--source` to override. | |
| [2024-06-06 23:39:40] INFO auto_weight.py:111: Using source weight format: [1mhuggingface-safetensor[0m. Use `--source-format` to override. | |
| [2024-06-06 23:39:40] INFO auto_config.py:154: [92mFound[0m model type: [1mqwen2[0m. Use `--model-type` to override. | |
| [2024-06-06 23:39:40] INFO qwen2_model.py:49: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (32768) | |
| [2024-06-06 23:39:40] INFO qwen2_model.py:66: [1mprefill_chunk_size[0m 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 <module> | |
| 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 | |
| [1mWeight conversion with arguments:[0m | |
| [1m--config[0m /models/Qwen2-1.5B-Instruct/config.json | |
| [1m--quantization[0m NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16') | |
| [1m--model-type[0m qwen2 | |
| [1m--device[0m cuda:0 | |
| [1m--source[0m /models/Qwen2-1.5B-Instruct/model.safetensors.index.json | |
| [1m--source-format[0m huggingface-safetensor | |
| [1m--output[0m /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC | |
| Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC | |
| /home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm gen_config /ssd2/models/Qwen2-1.5B-Instruct --quantization q0f16 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC | |
| [2024-06-06 22:37:49] INFO auto_config.py:116: [92mFound[0m model configuration: /ssd2/models/Qwen2-1.5B-Instruct/config.json | |
| [2024-06-06 22:37:49] INFO auto_config.py:154: [92mFound[0m model type: [1mqwen2[0m. Use `--model-type` to override. | |
| [2024-06-06 22:37:49] INFO qwen2_model.py:50: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (32768) | |
| [2024-06-06 22:37:49] INFO qwen2_model.py:67: [1mprefill_chunk_size[0m defaults to 2048 | |
| [2024-06-06 22:37:49] INFO config.py:107: Overriding [1mmax_batch_size[0m from 1 to 80 | |
| [2024-06-06 22:37:49] INFO gen_config.py:143: [generation_config.json] Setting [1mbos_token_id[0m: 151643 | |
| [2024-06-06 22:37:49] INFO gen_config.py:143: [generation_config.json] Setting [1mpad_token_id[0m: 151643 | |
| [2024-06-06 22:37:49] INFO gen_config.py:143: [generation_config.json] Setting [1meos_token_id[0m: [151645, 151643] | |
| [2024-06-06 22:37:49] INFO gen_config.py:143: [generation_config.json] Setting [1mrepetition_penalty[0m: 1.1 | |
| [2024-06-06 22:37:49] INFO gen_config.py:143: [generation_config.json] Setting [1mtemperature[0m: 0.7 | |
| [2024-06-06 22:37:49] INFO gen_config.py:143: [generation_config.json] Setting [1mtop_p[0m: 0.8 | |
| [2024-06-06 22:37:49] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /ssd2/models/Qwen2-1.5B-Instruct/tokenizer.model | |
| [2024-06-06 22:37:49] INFO gen_config.py:155: [92mFound[0m tokenizer config: /ssd2/models/Qwen2-1.5B-Instruct/tokenizer.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/tokenizer.json[0m | |
| [2024-06-06 22:37:49] INFO gen_config.py:155: [92mFound[0m tokenizer config: /ssd2/models/Qwen2-1.5B-Instruct/vocab.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/vocab.json[0m | |
| [2024-06-06 22:37:49] INFO gen_config.py:155: [92mFound[0m tokenizer config: /ssd2/models/Qwen2-1.5B-Instruct/merges.txt. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/merges.txt[0m | |
| [2024-06-06 22:37:49] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /ssd2/models/Qwen2-1.5B-Instruct/added_tokens.json | |
| [2024-06-06 22:37:49] INFO gen_config.py:155: [92mFound[0m tokenizer config: /ssd2/models/Qwen2-1.5B-Instruct/tokenizer_config.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/tokenizer_config.json[0m | |
| [2024-06-06 22:37:49] 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 22:37:49] INFO gen_config.py:32: [System default] Setting [1mpresence_penalty[0m: 0.0 | |
| [2024-06-06 22:37:49] INFO gen_config.py:32: [System default] Setting [1mfrequency_penalty[0m: 0.0 | |
| [2024-06-06 22:37:49] INFO gen_config.py:223: Dumping configuration file to: [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/mlc-chat-config.json[0m | |
| /home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm convert_weight /ssd2/models/Qwen2-1.5B-Instruct --quantization q0f16 --output /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC | |
| [2024-06-06 22:37:50] INFO auto_config.py:116: [92mFound[0m model configuration: /ssd2/models/Qwen2-1.5B-Instruct/config.json | |
| [2024-06-06 22:37:52] INFO auto_device.py:79: [92mFound[0m device: cuda:0 | |
| [2024-06-06 22:37:52] INFO auto_device.py:79: [92mFound[0m device: cuda:1 | |
| [2024-06-06 22:37:53] INFO auto_device.py:88: [91mNot found[0m device: rocm:0 | |
| [2024-06-06 22:37:54] INFO auto_device.py:88: [91mNot found[0m device: metal:0 | |
| [2024-06-06 22:37:55] INFO auto_device.py:79: [92mFound[0m device: vulkan:0 | |
| [2024-06-06 22:37:55] INFO auto_device.py:79: [92mFound[0m device: vulkan:1 | |
| [2024-06-06 22:37:55] INFO auto_device.py:79: [92mFound[0m device: vulkan:2 | |
| [2024-06-06 22:37:56] INFO auto_device.py:88: [91mNot found[0m device: opencl:0 | |
| [2024-06-06 22:37:56] INFO auto_device.py:35: Using device: [1mcuda:0[0m | |
| [2024-06-06 22:37:56] INFO auto_weight.py:71: Finding weights in: /ssd2/models/Qwen2-1.5B-Instruct | |
| [2024-06-06 22:37:56] INFO auto_weight.py:137: [91mNot found[0m Huggingface PyTorch | |
| [2024-06-06 22:37:56] INFO auto_weight.py:144: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: /ssd2/models/Qwen2-1.5B-Instruct/model.safetensors.index.json | |
| [2024-06-06 22:37:56] INFO auto_weight.py:107: Using source weight configuration: [1m/ssd2/models/Qwen2-1.5B-Instruct/model.safetensors.index.json[0m. Use `--source` to override. | |
| [2024-06-06 22:37:56] INFO auto_weight.py:111: Using source weight format: [1mhuggingface-safetensor[0m. Use `--source-format` to override. | |
| [2024-06-06 22:37:56] INFO auto_config.py:154: [92mFound[0m model type: [1mqwen2[0m. Use `--model-type` to override. | |
| [2024-06-06 22:37:56] INFO qwen2_model.py:50: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (32768) | |
| [2024-06-06 22:37:56] INFO qwen2_model.py:67: [1mprefill_chunk_size[0m defaults to 2048 | |
| [1mWeight conversion with arguments:[0m | |
| [1m--config[0m /ssd2/models/Qwen2-1.5B-Instruct/config.json | |
| [1m--quantization[0m NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16') | |
| [1m--model-type[0m qwen2 | |
| [1m--device[0m cuda:0 | |
| [1m--source[0m /ssd2/models/Qwen2-1.5B-Instruct/model.safetensors.index.json | |
| [1m--source-format[0m huggingface-safetensor | |
| [1m--output[0m /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC | |
| Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC | |
| 0%| | 0/198 [00:00<?, ?it/s] [2024-06-06 22:37:58] INFO huggingface_loader.py:185: Loading HF parameters from: /ssd2/models/Qwen2-1.5B-Instruct/model.safetensors | |
| 0%| | 0/198 [00:00<?, ?it/s] [2024-06-06 22:38:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.embed_tokens.weight[0m", shape: (151936, 1536), dtype: float16 | |
| 0%| | 0/198 [00:02<?, ?it/s] 1%| | 1/198 [00:03<12:17, 3.74s/it] [2024-06-06 22:38:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 1%| | 1/198 [00:03<12:17, 3.74s/it] [2024-06-06 22:38:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 1%| | 1/198 [00:03<12:17, 3.74s/it] [2024-06-06 22:38:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 1%| | 1/198 [00:03<12:17, 3.74s/it] 2%|▏ | 4/198 [00:04<02:35, 1.25it/s] [2024-06-06 22:38:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 2%|▏ | 4/198 [00:04<02:35, 1.25it/s] [2024-06-06 22:38:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 2%|▏ | 4/198 [00:04<02:35, 1.25it/s] [2024-06-06 22:38:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 2%|▏ | 4/198 [00:04<02:35, 1.25it/s] [2024-06-06 22:38:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 2%|▏ | 4/198 [00:04<02:35, 1.25it/s] [2024-06-06 22:38:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 2%|▏ | 4/198 [00:04<02:35, 1.25it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 2%|▏ | 4/198 [00:04<02:35, 1.25it/s] 5%|▌ | 10/198 [00:04<00:49, 3.78it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 5%|▌ | 10/198 [00:04<00:49, 3.78it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 5%|▌ | 10/198 [00:04<00:49, 3.78it/s] 6%|▌ | 12/198 [00:04<00:42, 4.36it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 6%|▌ | 12/198 [00:04<00:42, 4.36it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 6%|▌ | 12/198 [00:04<00:42, 4.36it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 6%|▌ | 12/198 [00:04<00:42, 4.36it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 6%|▌ | 12/198 [00:04<00:42, 4.36it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 6%|▌ | 12/198 [00:04<00:42, 4.36it/s] 9%|▊ | 17/198 [00:04<00:24, 7.42it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 9%|▊ | 17/198 [00:04<00:24, 7.42it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 9%|▊ | 17/198 [00:04<00:24, 7.42it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 9%|▊ | 17/198 [00:04<00:24, 7.42it/s] 10%|█ | 20/198 [00:04<00:21, 8.33it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 10%|█ | 20/198 [00:04<00:21, 8.33it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 10%|█ | 20/198 [00:04<00:21, 8.33it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 10%|█ | 20/198 [00:04<00:21, 8.33it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 10%|█ | 20/198 [00:05<00:21, 8.33it/s] 12%|█▏ | 24/198 [00:05<00:15, 11.06it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 12%|█▏ | 24/198 [00:05<00:15, 11.06it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 12%|█▏ | 24/198 [00:05<00:15, 11.06it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 12%|█▏ | 24/198 [00:05<00:15, 11.06it/s] 14%|█▎ | 27/198 [00:05<00:15, 11.30it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 14%|█▎ | 27/198 [00:05<00:15, 11.30it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 14%|█▎ | 27/198 [00:05<00:15, 11.30it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 14%|█▎ | 27/198 [00:05<00:15, 11.30it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 14%|█▎ | 27/198 [00:05<00:15, 11.30it/s] 16%|█▌ | 31/198 [00:05<00:12, 13.34it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 16%|█▌ | 31/198 [00:05<00:12, 13.34it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 16%|█▌ | 31/198 [00:05<00:12, 13.34it/s] 17%|█▋ | 33/198 [00:05<00:13, 11.79it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 17%|█▋ | 33/198 [00:05<00:13, 11.79it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 17%|█▋ | 33/198 [00:05<00:13, 11.79it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 17%|█▋ | 33/198 [00:05<00:13, 11.79it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 17%|█▋ | 33/198 [00:05<00:13, 11.79it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 17%|█▋ | 33/198 [00:05<00:13, 11.79it/s] 19%|█▉ | 38/198 [00:05<00:09, 16.36it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 19%|█▉ | 38/198 [00:06<00:09, 16.36it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 19%|█▉ | 38/198 [00:06<00:09, 16.36it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 19%|█▉ | 38/198 [00:06<00:09, 16.36it/s] 21%|██ | 41/198 [00:06<00:10, 14.94it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 21%|██ | 41/198 [00:06<00:10, 14.94it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 21%|██ | 41/198 [00:06<00:10, 14.94it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 21%|██ | 41/198 [00:06<00:10, 14.94it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 21%|██ | 41/198 [00:06<00:10, 14.94it/s] 23%|██▎ | 45/198 [00:06<00:08, 17.52it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 23%|██▎ | 45/198 [00:06<00:08, 17.52it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 23%|██▎ | 45/198 [00:06<00:08, 17.52it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 23%|██▎ | 45/198 [00:06<00:08, 17.52it/s] 24%|██▍ | 48/198 [00:06<00:09, 15.28it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 24%|██▍ | 48/198 [00:06<00:09, 15.28it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 24%|██▍ | 48/198 [00:06<00:09, 15.28it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 24%|██▍ | 48/198 [00:06<00:09, 15.28it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 24%|██▍ | 48/198 [00:06<00:09, 15.28it/s] 26%|██▋ | 52/198 [00:06<00:08, 16.47it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 26%|██▋ | 52/198 [00:06<00:08, 16.47it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 26%|██▋ | 52/198 [00:07<00:08, 16.47it/s] 27%|██▋ | 54/198 [00:07<00:10, 13.51it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 27%|██▋ | 54/198 [00:07<00:10, 13.51it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 27%|██▋ | 54/198 [00:07<00:10, 13.51it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 27%|██▋ | 54/198 [00:07<00:10, 13.51it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 27%|██▋ | 54/198 [00:07<00:10, 13.51it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 27%|██▋ | 54/198 [00:07<00:10, 13.51it/s] 30%|██▉ | 59/198 [00:07<00:07, 18.05it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 30%|██▉ | 59/198 [00:07<00:07, 18.05it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 30%|██▉ | 59/198 [00:07<00:07, 18.05it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 30%|██▉ | 59/198 [00:07<00:07, 18.05it/s] 31%|███▏ | 62/198 [00:07<00:08, 15.72it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 31%|███▏ | 62/198 [00:07<00:08, 15.72it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 31%|███▏ | 62/198 [00:07<00:08, 15.72it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 31%|███▏ | 62/198 [00:07<00:08, 15.72it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 31%|███▏ | 62/198 [00:07<00:08, 15.72it/s] 33%|███▎ | 66/198 [00:07<00:07, 18.21it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 33%|███▎ | 66/198 [00:07<00:07, 18.21it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 33%|███▎ | 66/198 [00:07<00:07, 18.21it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 33%|███▎ | 66/198 [00:07<00:07, 18.21it/s] 35%|███▍ | 69/198 [00:07<00:08, 15.96it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 35%|███▍ | 69/198 [00:07<00:08, 15.96it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 35%|███▍ | 69/198 [00:07<00:08, 15.96it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 35%|███▍ | 69/198 [00:07<00:08, 15.96it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 35%|███▍ | 69/198 [00:07<00:08, 15.96it/s] 37%|███▋ | 73/198 [00:08<00:07, 17.19it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 37%|███▋ | 73/198 [00:08<00:07, 17.19it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 37%|███▋ | 73/198 [00:08<00:07, 17.19it/s] 38%|███▊ | 75/198 [00:08<00:08, 14.09it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 38%|███▊ | 75/198 [00:08<00:08, 14.09it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 38%|███▊ | 75/198 [00:08<00:08, 14.09it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 38%|███▊ | 75/198 [00:08<00:08, 14.09it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 38%|███▊ | 75/198 [00:08<00:08, 14.09it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 38%|███▊ | 75/198 [00:08<00:08, 14.09it/s] 40%|████ | 80/198 [00:08<00:06, 18.76it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 40%|████ | 80/198 [00:08<00:06, 18.76it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 40%|████ | 80/198 [00:08<00:06, 18.76it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 40%|████ | 80/198 [00:08<00:06, 18.76it/s] 42%|████▏ | 83/198 [00:08<00:07, 16.28it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 42%|████▏ | 83/198 [00:08<00:07, 16.28it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 42%|████▏ | 83/198 [00:08<00:07, 16.28it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 42%|████▏ | 83/198 [00:08<00:07, 16.28it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 42%|████▏ | 83/198 [00:08<00:07, 16.28it/s] 44%|████▍ | 87/198 [00:08<00:05, 18.73it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 44%|████▍ | 87/198 [00:08<00:05, 18.73it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 44%|████▍ | 87/198 [00:09<00:05, 18.73it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 44%|████▍ | 87/198 [00:09<00:05, 18.73it/s] 45%|████▌ | 90/198 [00:09<00:06, 16.24it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 45%|████▌ | 90/198 [00:09<00:06, 16.24it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 45%|████▌ | 90/198 [00:09<00:06, 16.24it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 45%|████▌ | 90/198 [00:09<00:06, 16.24it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 45%|████▌ | 90/198 [00:09<00:06, 16.24it/s] 47%|████▋ | 94/198 [00:09<00:05, 17.41it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 47%|████▋ | 94/198 [00:09<00:05, 17.41it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 47%|████▋ | 94/198 [00:09<00:05, 17.41it/s] 48%|████▊ | 96/198 [00:09<00:07, 14.21it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 48%|████▊ | 96/198 [00:09<00:07, 14.21it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 48%|████▊ | 96/198 [00:09<00:07, 14.21it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 48%|████▊ | 96/198 [00:09<00:07, 14.21it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 48%|████▊ | 96/198 [00:09<00:07, 14.21it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 48%|████▊ | 96/198 [00:09<00:07, 14.21it/s] 51%|█████ | 101/198 [00:09<00:05, 18.90it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 51%|█████ | 101/198 [00:09<00:05, 18.90it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 51%|█████ | 101/198 [00:09<00:05, 18.90it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 51%|█████ | 101/198 [00:09<00:05, 18.90it/s] 53%|█████▎ | 104/198 [00:09<00:05, 16.42it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 53%|█████▎ | 104/198 [00:09<00:05, 16.42it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 53%|█████▎ | 104/198 [00:09<00:05, 16.42it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 53%|█████▎ | 104/198 [00:09<00:05, 16.42it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 53%|█████▎ | 104/198 [00:09<00:05, 16.42it/s] 55%|█████▍ | 108/198 [00:10<00:04, 18.92it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 55%|█████▍ | 108/198 [00:10<00:04, 18.92it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 55%|█████▍ | 108/198 [00:10<00:04, 18.92it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 55%|█████▍ | 108/198 [00:10<00:04, 18.92it/s] 56%|█████▌ | 111/198 [00:10<00:05, 16.19it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 56%|█████▌ | 111/198 [00:10<00:05, 16.19it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 56%|█████▌ | 111/198 [00:10<00:05, 16.19it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 56%|█████▌ | 111/198 [00:10<00:05, 16.19it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 56%|█████▌ | 111/198 [00:10<00:05, 16.19it/s] 58%|█████▊ | 115/198 [00:10<00:04, 17.36it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 58%|█████▊ | 115/198 [00:10<00:04, 17.36it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 58%|█████▊ | 115/198 [00:10<00:04, 17.36it/s] 59%|█████▉ | 117/198 [00:10<00:05, 14.20it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 59%|█████▉ | 117/198 [00:10<00:05, 14.20it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 59%|█████▉ | 117/198 [00:10<00:05, 14.20it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 59%|█████▉ | 117/198 [00:10<00:05, 14.20it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 59%|█████▉ | 117/198 [00:10<00:05, 14.20it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 59%|█████▉ | 117/198 [00:10<00:05, 14.20it/s] 62%|██████▏ | 122/198 [00:10<00:04, 18.89it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 62%|██████▏ | 122/198 [00:11<00:04, 18.89it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 62%|██████▏ | 122/198 [00:11<00:04, 18.89it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 62%|██████▏ | 122/198 [00:11<00:04, 18.89it/s] 63%|██████▎ | 125/198 [00:11<00:04, 16.47it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 63%|██████▎ | 125/198 [00:11<00:04, 16.47it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 63%|██████▎ | 125/198 [00:11<00:04, 16.47it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 63%|██████▎ | 125/198 [00:11<00:04, 16.47it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 63%|██████▎ | 125/198 [00:11<00:04, 16.47it/s] 65%|██████▌ | 129/198 [00:11<00:03, 19.03it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 65%|██████▌ | 129/198 [00:11<00:03, 19.03it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 65%|██████▌ | 129/198 [00:11<00:03, 19.03it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 65%|██████▌ | 129/198 [00:11<00:03, 19.03it/s] 67%|██████▋ | 132/198 [00:11<00:04, 16.50it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 67%|██████▋ | 132/198 [00:11<00:04, 16.50it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 67%|██████▋ | 132/198 [00:11<00:04, 16.50it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 67%|██████▋ | 132/198 [00:11<00:04, 16.50it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 67%|██████▋ | 132/198 [00:11<00:04, 16.50it/s] 69%|██████▊ | 136/198 [00:11<00:03, 17.60it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 69%|██████▊ | 136/198 [00:11<00:03, 17.60it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 69%|██████▊ | 136/198 [00:11<00:03, 17.60it/s] 70%|██████▉ | 138/198 [00:11<00:04, 14.32it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 70%|██████▉ | 138/198 [00:11<00:04, 14.32it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 70%|██████▉ | 138/198 [00:12<00:04, 14.32it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 70%|██████▉ | 138/198 [00:12<00:04, 14.32it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 70%|██████▉ | 138/198 [00:12<00:04, 14.32it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 70%|██████▉ | 138/198 [00:12<00:04, 14.32it/s] 72%|███████▏ | 143/198 [00:12<00:02, 19.01it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 72%|███████▏ | 143/198 [00:12<00:02, 19.01it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 72%|███████▏ | 143/198 [00:12<00:02, 19.01it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 72%|███████▏ | 143/198 [00:12<00:02, 19.01it/s] 74%|███████▎ | 146/198 [00:12<00:03, 16.53it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 74%|███████▎ | 146/198 [00:12<00:03, 16.53it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 74%|███████▎ | 146/198 [00:12<00:03, 16.53it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 74%|███████▎ | 146/198 [00:12<00:03, 16.53it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 74%|███████▎ | 146/198 [00:12<00:03, 16.53it/s] 76%|███████▌ | 150/198 [00:12<00:02, 19.07it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 76%|███████▌ | 150/198 [00:12<00:02, 19.07it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 76%|███████▌ | 150/198 [00:12<00:02, 19.07it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 76%|███████▌ | 150/198 [00:12<00:02, 19.07it/s] 77%|███████▋ | 153/198 [00:12<00:02, 16.50it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 77%|███████▋ | 153/198 [00:12<00:02, 16.50it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 77%|███████▋ | 153/198 [00:12<00:02, 16.50it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 77%|███████▋ | 153/198 [00:12<00:02, 16.50it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 77%|███████▋ | 153/198 [00:12<00:02, 16.50it/s] 79%|███████▉ | 157/198 [00:12<00:02, 17.62it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 79%|███████▉ | 157/198 [00:13<00:02, 17.62it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 79%|███████▉ | 157/198 [00:13<00:02, 17.62it/s] 80%|████████ | 159/198 [00:13<00:02, 14.34it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 80%|████████ | 159/198 [00:13<00:02, 14.34it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 80%|████████ | 159/198 [00:13<00:02, 14.34it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 80%|████████ | 159/198 [00:13<00:02, 14.34it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 80%|████████ | 159/198 [00:13<00:02, 14.34it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 80%|████████ | 159/198 [00:13<00:02, 14.34it/s] 83%|████████▎ | 164/198 [00:13<00:01, 19.03it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 83%|████████▎ | 164/198 [00:13<00:01, 19.03it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 83%|████████▎ | 164/198 [00:13<00:01, 19.03it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 83%|████████▎ | 164/198 [00:13<00:01, 19.03it/s] 84%|████████▍ | 167/198 [00:13<00:01, 16.56it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 84%|████████▍ | 167/198 [00:13<00:01, 16.56it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 84%|████████▍ | 167/198 [00:13<00:01, 16.56it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 84%|████████▍ | 167/198 [00:13<00:01, 16.56it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 84%|████████▍ | 167/198 [00:13<00:01, 16.56it/s] 86%|████████▋ | 171/198 [00:13<00:01, 19.12it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 86%|████████▋ | 171/198 [00:13<00:01, 19.12it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 86%|████████▋ | 171/198 [00:13<00:01, 19.12it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 86%|████████▋ | 171/198 [00:14<00:01, 19.12it/s] 88%|████████▊ | 174/198 [00:14<00:01, 16.58it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 88%|████████▊ | 174/198 [00:14<00:01, 16.58it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 88%|████████▊ | 174/198 [00:14<00:01, 16.58it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 88%|████████▊ | 174/198 [00:14<00:01, 16.58it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 88%|████████▊ | 174/198 [00:14<00:01, 16.58it/s] 90%|████████▉ | 178/198 [00:14<00:01, 17.67it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 90%|████████▉ | 178/198 [00:14<00:01, 17.67it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 90%|████████▉ | 178/198 [00:14<00:01, 17.67it/s] 91%|█████████ | 180/198 [00:14<00:01, 14.28it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 91%|█████████ | 180/198 [00:14<00:01, 14.28it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 91%|█████████ | 180/198 [00:14<00:01, 14.28it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 91%|█████████ | 180/198 [00:14<00:01, 14.28it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 91%|█████████ | 180/198 [00:14<00:01, 14.28it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 91%|█████████ | 180/198 [00:14<00:01, 14.28it/s] 93%|█████████▎| 185/198 [00:14<00:00, 18.87it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 93%|█████████▎| 185/198 [00:14<00:00, 18.87it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 93%|█████████▎| 185/198 [00:14<00:00, 18.87it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 93%|█████████▎| 185/198 [00:14<00:00, 18.87it/s] 95%|█████████▍| 188/198 [00:14<00:00, 16.23it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 95%|█████████▍| 188/198 [00:14<00:00, 16.23it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 95%|█████████▍| 188/198 [00:14<00:00, 16.23it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.input_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 95%|█████████▍| 188/198 [00:14<00:00, 16.23it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 | |
| 95%|█████████▍| 188/198 [00:14<00:00, 16.23it/s] 97%|█████████▋| 192/198 [00:14<00:00, 18.80it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 | |
| 97%|█████████▋| 192/198 [00:15<00:00, 18.80it/s] [2024-06-06 22:38:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 | |
| 97%|█████████▋| 192/198 [00:15<00:00, 18.80it/s] [2024-06-06 22:38:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 | |
| 97%|█████████▋| 192/198 [00:15<00:00, 18.80it/s] 98%|█████████▊| 195/198 [00:15<00:00, 16.37it/s] [2024-06-06 22:38:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 | |
| 98%|█████████▊| 195/198 [00:15<00:00, 16.37it/s] [2024-06-06 22:38:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 | |
| 98%|█████████▊| 195/198 [00:15<00:00, 16.37it/s] [2024-06-06 22:38:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.norm.weight[0m", shape: (1536,), dtype: float16 | |
| 98%|█████████▊| 195/198 [00:15<00:00, 16.37it/s] 100%|██████████| 198/198 [00:15<00:00, 12.92it/s] | |
| [2024-06-06 22:38:14] INFO huggingface_loader.py:197: Unloading HF weight file: /ssd2/models/Qwen2-1.5B-Instruct/model.safetensors | |
| [2024-06-06 22:38:14] INFO stats.py:77: [92mTime usage[0m: HF loading: 1.873 sec; Pre-quantization mapping: 5.689 sec; Quantization: 0.000 sec | |
| [2024-06-06 22:38:14] INFO stats.py:91: [92mRAM usage[0m: Peak RAM: 5.751 GB. Total bytes loaded from disk: 5.751 GB | |
| [2024-06-06 22:38:14] INFO convert_weight.py:155: [92mParameter size[0m after quantization: 2.875 GB | |
| [2024-06-06 22:38:14] INFO convert_weight.py:160: [92mTotal parameters[0m: 1,543,714,304 | |
| [2024-06-06 22:38:14] INFO convert_weight.py:161: [92mBits per parameter[0m: 16.000 | |
| [2024-06-06 22:38:14] INFO convert_weight.py:166: Saved to directory: [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC[0m | |
| All finished, 67 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/ndarray-cache.json | |