/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Qwen2-0.5B-Instruct --quantization q0f16 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f16-MLC
[2024-06-06 23:38:00] INFO auto_config.py:116: Found model configuration: /models/Qwen2-0.5B-Instruct/config.json
[2024-06-06 23:38:00] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
[2024-06-06 23:38:00] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-06 23:38:00] INFO qwen2_model.py:66: prefill_chunk_size defaults to 2048
[2024-06-06 23:38:00] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-06 23:38:00] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 151643
[2024-06-06 23:38:00] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 151643
[2024-06-06 23:38:00] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [151645, 151643]
[2024-06-06 23:38:00] INFO gen_config.py:143: [generation_config.json] Setting repetition_penalty: 1.1
[2024-06-06 23:38:00] INFO gen_config.py:143: [generation_config.json] Setting temperature: 0.7
[2024-06-06 23:38:00] INFO gen_config.py:143: [generation_config.json] Setting top_p: 0.8
[2024-06-06 23:38:00] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen2-0.5B-Instruct/tokenizer.model
[2024-06-06 23:38:00] 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-q0f16-MLC/tokenizer.json
[2024-06-06 23:38:00] 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-q0f16-MLC/vocab.json
[2024-06-06 23:38:00] 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-q0f16-MLC/merges.txt
[2024-06-06 23:38:00] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen2-0.5B-Instruct/added_tokens.json
[2024-06-06 23:38:00] 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-q0f16-MLC/tokenizer_config.json
[2024-06-06 23:38:01] 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 23:38:01] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-06 23:38:01] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-06 23:38:01] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f16-MLC/mlc-chat-config.json
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Qwen2-0.5B-Instruct --quantization q0f16 --output /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f16-MLC
[2024-06-06 23:38:02] INFO auto_config.py:116: Found model configuration: /models/Qwen2-0.5B-Instruct/config.json
[2024-06-06 23:38:04] INFO auto_device.py:79: Found device: cuda:0
[2024-06-06 23:38:05] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-06 23:38:07] INFO auto_device.py:88: Not found device: metal:0
[2024-06-06 23:38:08] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-06 23:38:08] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-06 23:38:08] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-06 23:38:08] INFO auto_device.py:79: Found device: vulkan:3
[2024-06-06 23:38:10] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-06 23:38:10] INFO auto_device.py:35: Using device: cuda:0
[2024-06-06 23:38:10] INFO auto_weight.py:71: Finding weights in: /models/Qwen2-0.5B-Instruct
[2024-06-06 23:38:10] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-06 23:38:10] 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 23:38:10] 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 23:38:10] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-06 23:38:10] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
[2024-06-06 23:38:10] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-06 23:38:10] 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 <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
Weight conversion with arguments:
  --config          /models/Qwen2-0.5B-Instruct/config.json
  --quantization    NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16')
  --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-q0f16-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f16-MLC
/home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm gen_config /ssd2/models/Qwen2-0.5B-Instruct --quantization q0f16 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f16-MLC
[2024-06-06 22:33:44] INFO auto_config.py:116: Found model configuration: /ssd2/models/Qwen2-0.5B-Instruct/config.json
[2024-06-06 22:33:44] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
[2024-06-06 22:33:44] INFO qwen2_model.py:50: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-06 22:33:44] INFO qwen2_model.py:67: prefill_chunk_size defaults to 2048
[2024-06-06 22:33:44] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-06 22:33:44] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 151643
[2024-06-06 22:33:44] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 151643
[2024-06-06 22:33:44] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [151645, 151643]
[2024-06-06 22:33:44] INFO gen_config.py:143: [generation_config.json] Setting repetition_penalty: 1.1
[2024-06-06 22:33:44] INFO gen_config.py:143: [generation_config.json] Setting temperature: 0.7
[2024-06-06 22:33:44] INFO gen_config.py:143: [generation_config.json] Setting top_p: 0.8
[2024-06-06 22:33:44] INFO gen_config.py:157: Not found tokenizer config: /ssd2/models/Qwen2-0.5B-Instruct/tokenizer.model
[2024-06-06 22:33:44] 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-q0f16-MLC/tokenizer.json
[2024-06-06 22:33:44] 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-q0f16-MLC/vocab.json
[2024-06-06 22:33:44] 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-q0f16-MLC/merges.txt
[2024-06-06 22:33:44] INFO gen_config.py:157: Not found tokenizer config: /ssd2/models/Qwen2-0.5B-Instruct/added_tokens.json
[2024-06-06 22:33:44] 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-q0f16-MLC/tokenizer_config.json
[2024-06-06 22:33:44] 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 22:33:44] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-06 22:33:44] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-06 22:33:44] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f16-MLC/mlc-chat-config.json
/home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm convert_weight /ssd2/models/Qwen2-0.5B-Instruct --quantization q0f16 --output /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f16-MLC
[2024-06-06 22:33:45] INFO auto_config.py:116: Found model configuration: /ssd2/models/Qwen2-0.5B-Instruct/config.json
[2024-06-06 22:33:46] INFO auto_device.py:79: Found device: cuda:0
[2024-06-06 22:33:46] INFO auto_device.py:79: Found device: cuda:1
[2024-06-06 22:33:47] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-06 22:33:48] INFO auto_device.py:88: Not found device: metal:0
[2024-06-06 22:33:50] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-06 22:33:50] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-06 22:33:50] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-06 22:33:51] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-06 22:33:51] INFO auto_device.py:35: Using device: cuda:0
[2024-06-06 22:33:51] INFO auto_weight.py:71: Finding weights in: /ssd2/models/Qwen2-0.5B-Instruct
[2024-06-06 22:33:51] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-06 22:33:51] 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 22:33:51] 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 22:33:51] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-06 22:33:51] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
[2024-06-06 22:33:51] INFO qwen2_model.py:50: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-06 22:33:51] 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='q0f16', kind='no-quant', model_dtype='float16')
  --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-q0f16-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f16-MLC

  0%|          | 0/170 [00:00<?, ?it/s]
                                       
[2024-06-06 22:33:52] INFO huggingface_loader.py:185: Loading HF parameters from: /ssd2/models/Qwen2-0.5B-Instruct/model.safetensors

  0%|          | 0/170 [00:00<?, ?it/s]
                                       
[2024-06-06 22:33:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.embed_tokens.weight", shape: (151936, 896), dtype: float16

  0%|          | 0/170 [00:01<?, ?it/s]
  1%|          | 1/170 [00:02<07:29,  2.66s/it]
                                               
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (896,), dtype: float16

  1%|          | 1/170 [00:02<07:29,  2.66s/it]
                                               
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

  1%|          | 1/170 [00:02<07:29,  2.66s/it]
                                               
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

  1%|          | 1/170 [00:02<07:29,  2.66s/it]
                                               
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (896,), dtype: float16

  1%|          | 1/170 [00:02<07:29,  2.66s/it]
                                               
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.c_attn.bias", shape: (1152,), dtype: float16

  1%|          | 1/170 [00:02<07:29,  2.66s/it]
                                               
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

  1%|          | 1/170 [00:02<07:29,  2.66s/it]
                                               
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

  1%|          | 1/170 [00:02<07:29,  2.66s/it]
  5%|▍         | 8/170 [00:02<00:41,  3.92it/s]
                                               
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (896,), dtype: float16

  5%|▍         | 8/170 [00:02<00:41,  3.92it/s]
                                               
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

  5%|▍         | 8/170 [00:02<00:41,  3.92it/s]
                                               
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

  5%|▍         | 8/170 [00:02<00:41,  3.92it/s]
                                               
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (896,), dtype: float16

  5%|▍         | 8/170 [00:02<00:41,  3.92it/s]
  7%|▋         | 12/170 [00:02<00:25,  6.25it/s]
                                                
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.c_attn.bias", shape: (1152,), dtype: float16

  7%|▋         | 12/170 [00:02<00:25,  6.25it/s]
                                                
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

  7%|▋         | 12/170 [00:02<00:25,  6.25it/s]
                                                
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

  7%|▋         | 12/170 [00:02<00:25,  6.25it/s]
                                                
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (896,), dtype: float16

  7%|▋         | 12/170 [00:02<00:25,  6.25it/s]
                                                
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

  7%|▋         | 12/170 [00:02<00:25,  6.25it/s]
                                                
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

  7%|▋         | 12/170 [00:03<00:25,  6.25it/s]
 11%|█         | 18/170 [00:03<00:14, 10.65it/s]
                                                
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (896,), dtype: float16

 11%|█         | 18/170 [00:03<00:14, 10.65it/s]
                                                
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 11%|█         | 18/170 [00:03<00:14, 10.65it/s]
                                                
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 11%|█         | 18/170 [00:03<00:14, 10.65it/s]
                                                
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 11%|█         | 18/170 [00:03<00:14, 10.65it/s]
                                                
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (896,), dtype: float16

 11%|█         | 18/170 [00:03<00:14, 10.65it/s]
                                                
[2024-06-06 22:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 11%|█         | 18/170 [00:03<00:14, 10.65it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 11%|█         | 18/170 [00:03<00:14, 10.65it/s]
 15%|█▍        | 25/170 [00:03<00:08, 16.41it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (896,), dtype: float16

 15%|█▍        | 25/170 [00:03<00:08, 16.41it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 15%|█▍        | 25/170 [00:03<00:08, 16.41it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 15%|█▍        | 25/170 [00:03<00:08, 16.41it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 15%|█▍        | 25/170 [00:03<00:08, 16.41it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (896,), dtype: float16

 15%|█▍        | 25/170 [00:03<00:08, 16.41it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 15%|█▍        | 25/170 [00:03<00:08, 16.41it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 15%|█▍        | 25/170 [00:03<00:08, 16.41it/s]
 19%|█▉        | 32/170 [00:03<00:06, 22.31it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (896,), dtype: float16

 19%|█▉        | 32/170 [00:03<00:06, 22.31it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 19%|█▉        | 32/170 [00:03<00:06, 22.31it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 19%|█▉        | 32/170 [00:03<00:06, 22.31it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 19%|█▉        | 32/170 [00:03<00:06, 22.31it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (896,), dtype: float16

 19%|█▉        | 32/170 [00:03<00:06, 22.31it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 19%|█▉        | 32/170 [00:03<00:06, 22.31it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 19%|█▉        | 32/170 [00:03<00:06, 22.31it/s]
 23%|██▎       | 39/170 [00:03<00:04, 27.96it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (896,), dtype: float16

 23%|██▎       | 39/170 [00:03<00:04, 27.96it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 23%|██▎       | 39/170 [00:03<00:04, 27.96it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 23%|██▎       | 39/170 [00:03<00:04, 27.96it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 23%|██▎       | 39/170 [00:03<00:04, 27.96it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (896,), dtype: float16

 23%|██▎       | 39/170 [00:03<00:04, 27.96it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 23%|██▎       | 39/170 [00:03<00:04, 27.96it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 23%|██▎       | 39/170 [00:03<00:04, 27.96it/s]
 27%|██▋       | 46/170 [00:03<00:03, 33.04it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (896,), dtype: float16

 27%|██▋       | 46/170 [00:03<00:03, 33.04it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 27%|██▋       | 46/170 [00:03<00:03, 33.04it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 27%|██▋       | 46/170 [00:03<00:03, 33.04it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 27%|██▋       | 46/170 [00:03<00:03, 33.04it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (896,), dtype: float16

 27%|██▋       | 46/170 [00:03<00:03, 33.04it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 27%|██▋       | 46/170 [00:03<00:03, 33.04it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 27%|██▋       | 46/170 [00:03<00:03, 33.04it/s]
 31%|███       | 53/170 [00:03<00:03, 37.36it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (896,), dtype: float16

 31%|███       | 53/170 [00:03<00:03, 37.36it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 31%|███       | 53/170 [00:03<00:03, 37.36it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 31%|███       | 53/170 [00:03<00:03, 37.36it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 31%|███       | 53/170 [00:03<00:03, 37.36it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (896,), dtype: float16

 31%|███       | 53/170 [00:03<00:03, 37.36it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 31%|███       | 53/170 [00:03<00:03, 37.36it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 31%|███       | 53/170 [00:03<00:03, 37.36it/s]
 35%|███▌      | 60/170 [00:03<00:02, 40.84it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (896,), dtype: float16

 35%|███▌      | 60/170 [00:03<00:02, 40.84it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 35%|███▌      | 60/170 [00:03<00:02, 40.84it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 35%|███▌      | 60/170 [00:03<00:02, 40.84it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 35%|███▌      | 60/170 [00:03<00:02, 40.84it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (896,), dtype: float16

 35%|███▌      | 60/170 [00:03<00:02, 40.84it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 35%|███▌      | 60/170 [00:03<00:02, 40.84it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 35%|███▌      | 60/170 [00:03<00:02, 40.84it/s]
 39%|███▉      | 67/170 [00:03<00:02, 43.61it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (896,), dtype: float16

 39%|███▉      | 67/170 [00:03<00:02, 43.61it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 39%|███▉      | 67/170 [00:03<00:02, 43.61it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 39%|███▉      | 67/170 [00:03<00:02, 43.61it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 39%|███▉      | 67/170 [00:03<00:02, 43.61it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (896,), dtype: float16

 39%|███▉      | 67/170 [00:03<00:02, 43.61it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 39%|███▉      | 67/170 [00:04<00:02, 43.61it/s]
                                                
[2024-06-06 22:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 39%|███▉      | 67/170 [00:04<00:02, 43.61it/s]
 44%|████▎     | 74/170 [00:04<00:02, 45.67it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (896,), dtype: float16

 44%|████▎     | 74/170 [00:04<00:02, 45.67it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 44%|████▎     | 74/170 [00:04<00:02, 45.67it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 44%|████▎     | 74/170 [00:04<00:02, 45.67it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 44%|████▎     | 74/170 [00:04<00:02, 45.67it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (896,), dtype: float16

 44%|████▎     | 74/170 [00:04<00:02, 45.67it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 44%|████▎     | 74/170 [00:04<00:02, 45.67it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 44%|████▎     | 74/170 [00:04<00:02, 45.67it/s]
 48%|████▊     | 81/170 [00:04<00:01, 47.16it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (896,), dtype: float16

 48%|████▊     | 81/170 [00:04<00:01, 47.16it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 48%|████▊     | 81/170 [00:04<00:01, 47.16it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 48%|████▊     | 81/170 [00:04<00:01, 47.16it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 48%|████▊     | 81/170 [00:04<00:01, 47.16it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (896,), dtype: float16

 48%|████▊     | 81/170 [00:04<00:01, 47.16it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 48%|████▊     | 81/170 [00:04<00:01, 47.16it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 48%|████▊     | 81/170 [00:04<00:01, 47.16it/s]
 52%|█████▏    | 88/170 [00:04<00:01, 48.31it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (896,), dtype: float16

 52%|█████▏    | 88/170 [00:04<00:01, 48.31it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 52%|█████▏    | 88/170 [00:04<00:01, 48.31it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 52%|█████▏    | 88/170 [00:04<00:01, 48.31it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 52%|█████▏    | 88/170 [00:04<00:01, 48.31it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (896,), dtype: float16

 52%|█████▏    | 88/170 [00:04<00:01, 48.31it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 52%|█████▏    | 88/170 [00:04<00:01, 48.31it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 52%|█████▏    | 88/170 [00:04<00:01, 48.31it/s]
 56%|█████▌    | 95/170 [00:04<00:01, 49.15it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (896,), dtype: float16

 56%|█████▌    | 95/170 [00:04<00:01, 49.15it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 56%|█████▌    | 95/170 [00:04<00:01, 49.15it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 56%|█████▌    | 95/170 [00:04<00:01, 49.15it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 56%|█████▌    | 95/170 [00:04<00:01, 49.15it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (896,), dtype: float16

 56%|█████▌    | 95/170 [00:04<00:01, 49.15it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 56%|█████▌    | 95/170 [00:04<00:01, 49.15it/s]
                                                
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 56%|█████▌    | 95/170 [00:04<00:01, 49.15it/s]
 60%|██████    | 102/170 [00:04<00:01, 49.67it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (896,), dtype: float16

 60%|██████    | 102/170 [00:04<00:01, 49.67it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 60%|██████    | 102/170 [00:04<00:01, 49.67it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 60%|██████    | 102/170 [00:04<00:01, 49.67it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 60%|██████    | 102/170 [00:04<00:01, 49.67it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (896,), dtype: float16

 60%|██████    | 102/170 [00:04<00:01, 49.67it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 60%|██████    | 102/170 [00:04<00:01, 49.67it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 60%|██████    | 102/170 [00:04<00:01, 49.67it/s]
 64%|██████▍   | 109/170 [00:04<00:01, 49.81it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (896,), dtype: float16

 64%|██████▍   | 109/170 [00:04<00:01, 49.81it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 64%|██████▍   | 109/170 [00:04<00:01, 49.81it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 64%|██████▍   | 109/170 [00:04<00:01, 49.81it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 64%|██████▍   | 109/170 [00:04<00:01, 49.81it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (896,), dtype: float16

 64%|██████▍   | 109/170 [00:04<00:01, 49.81it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 64%|██████▍   | 109/170 [00:04<00:01, 49.81it/s]
 68%|██████▊   | 115/170 [00:04<00:01, 52.17it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 68%|██████▊   | 115/170 [00:04<00:01, 52.17it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (896,), dtype: float16

 68%|██████▊   | 115/170 [00:04<00:01, 52.17it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 68%|██████▊   | 115/170 [00:04<00:01, 52.17it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 68%|██████▊   | 115/170 [00:04<00:01, 52.17it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 68%|██████▊   | 115/170 [00:04<00:01, 52.17it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (896,), dtype: float16

 68%|██████▊   | 115/170 [00:04<00:01, 52.17it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 68%|██████▊   | 115/170 [00:04<00:01, 52.17it/s]
 72%|███████▏  | 122/170 [00:05<00:00, 49.70it/s]
                                                 
[2024-06-06 22:33:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 72%|███████▏  | 122/170 [00:05<00:00, 49.70it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (896,), dtype: float16

 72%|███████▏  | 122/170 [00:05<00:00, 49.70it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 72%|███████▏  | 122/170 [00:05<00:00, 49.70it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 72%|███████▏  | 122/170 [00:05<00:00, 49.70it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 72%|███████▏  | 122/170 [00:05<00:00, 49.70it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (896,), dtype: float16

 72%|███████▏  | 122/170 [00:05<00:00, 49.70it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 72%|███████▏  | 122/170 [00:05<00:00, 49.70it/s]
 76%|███████▌  | 129/170 [00:05<00:00, 48.17it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 76%|███████▌  | 129/170 [00:05<00:00, 48.17it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (896,), dtype: float16

 76%|███████▌  | 129/170 [00:05<00:00, 48.17it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 76%|███████▌  | 129/170 [00:05<00:00, 48.17it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 76%|███████▌  | 129/170 [00:05<00:00, 48.17it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 76%|███████▌  | 129/170 [00:05<00:00, 48.17it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (896,), dtype: float16

 76%|███████▌  | 129/170 [00:05<00:00, 48.17it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 76%|███████▌  | 129/170 [00:05<00:00, 48.17it/s]
 80%|████████  | 136/170 [00:05<00:00, 48.17it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 80%|████████  | 136/170 [00:05<00:00, 48.17it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (896,), dtype: float16

 80%|████████  | 136/170 [00:05<00:00, 48.17it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 80%|████████  | 136/170 [00:05<00:00, 48.17it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 80%|████████  | 136/170 [00:05<00:00, 48.17it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 80%|████████  | 136/170 [00:05<00:00, 48.17it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (896,), dtype: float16

 80%|████████  | 136/170 [00:05<00:00, 48.17it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 80%|████████  | 136/170 [00:05<00:00, 48.17it/s]
 84%|████████▍ | 143/170 [00:05<00:00, 48.38it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 84%|████████▍ | 143/170 [00:05<00:00, 48.38it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (896,), dtype: float16

 84%|████████▍ | 143/170 [00:05<00:00, 48.38it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 84%|████████▍ | 143/170 [00:05<00:00, 48.38it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 84%|████████▍ | 143/170 [00:05<00:00, 48.38it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 84%|████████▍ | 143/170 [00:05<00:00, 48.38it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (896,), dtype: float16

 84%|████████▍ | 143/170 [00:05<00:00, 48.38it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 84%|████████▍ | 143/170 [00:05<00:00, 48.38it/s]
 88%|████████▊ | 150/170 [00:05<00:00, 48.74it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 88%|████████▊ | 150/170 [00:05<00:00, 48.74it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (896,), dtype: float16

 88%|████████▊ | 150/170 [00:05<00:00, 48.74it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 88%|████████▊ | 150/170 [00:05<00:00, 48.74it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 88%|████████▊ | 150/170 [00:05<00:00, 48.74it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 88%|████████▊ | 150/170 [00:05<00:00, 48.74it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (896,), dtype: float16

 88%|████████▊ | 150/170 [00:05<00:00, 48.74it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 88%|████████▊ | 150/170 [00:05<00:00, 48.74it/s]
 92%|█████████▏| 157/170 [00:05<00:00, 49.31it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 92%|█████████▏| 157/170 [00:05<00:00, 49.31it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (896,), dtype: float16

 92%|█████████▏| 157/170 [00:05<00:00, 49.31it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 92%|█████████▏| 157/170 [00:05<00:00, 49.31it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 92%|█████████▏| 157/170 [00:05<00:00, 49.31it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 92%|█████████▏| 157/170 [00:05<00:00, 49.31it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (896,), dtype: float16

 92%|█████████▏| 157/170 [00:05<00:00, 49.31it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 92%|█████████▏| 157/170 [00:05<00:00, 49.31it/s]
 96%|█████████▋| 164/170 [00:05<00:00, 48.46it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 96%|█████████▋| 164/170 [00:05<00:00, 48.46it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (896,), dtype: float16

 96%|█████████▋| 164/170 [00:05<00:00, 48.46it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 96%|█████████▋| 164/170 [00:05<00:00, 48.46it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 96%|█████████▋| 164/170 [00:05<00:00, 48.46it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 96%|█████████▋| 164/170 [00:05<00:00, 48.46it/s]
                                                 
[2024-06-06 22:33:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (896,), dtype: float16

 96%|█████████▋| 164/170 [00:05<00:00, 48.46it/s]
100%|██████████| 170/170 [00:05<00:00, 28.35it/s]
[2024-06-06 22:33:58] INFO huggingface_loader.py:197: Unloading HF weight file: /ssd2/models/Qwen2-0.5B-Instruct/model.safetensors
[2024-06-06 22:33:59] INFO stats.py:77: Time usage: HF loading: 1.531 sec; Pre-quantization mapping: 1.826 sec; Quantization: 0.000 sec
[2024-06-06 22:33:59] INFO stats.py:91: RAM usage: Peak RAM: 1.840 GB. Total bytes loaded from disk: 1.840 GB
[2024-06-06 22:33:59] INFO convert_weight.py:155: Parameter size after quantization: 0.920 GB
[2024-06-06 22:33:59] INFO convert_weight.py:160: Total parameters: 494,032,768
[2024-06-06 22:33:59] INFO convert_weight.py:161: Bits per parameter: 16.000
[2024-06-06 22:33:59] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f16-MLC

All finished, 25 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f16-MLC/ndarray-cache.json
/home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm gen_config /ssd2/models/Qwen2-0.5B-Instruct --quantization q0f16 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f16-MLC
[2024-06-06 22:36:13] INFO auto_config.py:116: Found model configuration: /ssd2/models/Qwen2-0.5B-Instruct/config.json
[2024-06-06 22:36:13] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
[2024-06-06 22:36:13] INFO qwen2_model.py:50: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-06 22:36:13] INFO qwen2_model.py:67: prefill_chunk_size defaults to 2048
[2024-06-06 22:36:13] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-06 22:36:13] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 151643
[2024-06-06 22:36:13] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 151643
[2024-06-06 22:36:13] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [151645, 151643]
[2024-06-06 22:36:13] INFO gen_config.py:143: [generation_config.json] Setting repetition_penalty: 1.1
[2024-06-06 22:36:13] INFO gen_config.py:143: [generation_config.json] Setting temperature: 0.7
[2024-06-06 22:36:13] INFO gen_config.py:143: [generation_config.json] Setting top_p: 0.8
[2024-06-06 22:36:13] INFO gen_config.py:157: Not found tokenizer config: /ssd2/models/Qwen2-0.5B-Instruct/tokenizer.model
[2024-06-06 22:36:13] 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-q0f16-MLC/tokenizer.json
[2024-06-06 22:36:13] 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-q0f16-MLC/vocab.json
[2024-06-06 22:36:13] 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-q0f16-MLC/merges.txt
[2024-06-06 22:36:13] INFO gen_config.py:157: Not found tokenizer config: /ssd2/models/Qwen2-0.5B-Instruct/added_tokens.json
[2024-06-06 22:36:13] 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-q0f16-MLC/tokenizer_config.json
[2024-06-06 22:36:13] 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 22:36:13] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-06 22:36:13] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-06 22:36:13] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f16-MLC/mlc-chat-config.json
/home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm convert_weight /ssd2/models/Qwen2-0.5B-Instruct --quantization q0f16 --output /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f16-MLC
[2024-06-06 22:36:14] INFO auto_config.py:116: Found model configuration: /ssd2/models/Qwen2-0.5B-Instruct/config.json
[2024-06-06 22:36:15] INFO auto_device.py:79: Found device: cuda:0
[2024-06-06 22:36:15] INFO auto_device.py:79: Found device: cuda:1
[2024-06-06 22:36:16] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-06 22:36:18] INFO auto_device.py:88: Not found device: metal:0
[2024-06-06 22:36:19] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-06 22:36:19] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-06 22:36:19] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-06 22:36:20] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-06 22:36:20] INFO auto_device.py:35: Using device: cuda:0
[2024-06-06 22:36:20] INFO auto_weight.py:71: Finding weights in: /ssd2/models/Qwen2-0.5B-Instruct
[2024-06-06 22:36:20] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-06 22:36:20] 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 22:36:20] 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 22:36:20] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-06 22:36:20] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
[2024-06-06 22:36:20] INFO qwen2_model.py:50: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-06 22:36:20] 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='q0f16', kind='no-quant', model_dtype='float16')
  --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-q0f16-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f16-MLC

  0%|          | 0/170 [00:00<?, ?it/s]
                                       
[2024-06-06 22:36:22] INFO huggingface_loader.py:185: Loading HF parameters from: /ssd2/models/Qwen2-0.5B-Instruct/model.safetensors

  0%|          | 0/170 [00:00<?, ?it/s]
                                       
[2024-06-06 22:36:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.embed_tokens.weight", shape: (151936, 896), dtype: float16

  0%|          | 0/170 [00:01<?, ?it/s]
  1%|          | 1/170 [00:03<09:00,  3.20s/it]
                                               
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (896,), dtype: float16

  1%|          | 1/170 [00:03<09:00,  3.20s/it]
                                               
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

  1%|          | 1/170 [00:03<09:00,  3.20s/it]
                                               
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

  1%|          | 1/170 [00:03<09:00,  3.20s/it]
                                               
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (896,), dtype: float16

  1%|          | 1/170 [00:03<09:00,  3.20s/it]
                                               
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.c_attn.bias", shape: (1152,), dtype: float16

  1%|          | 1/170 [00:03<09:00,  3.20s/it]
                                               
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

  1%|          | 1/170 [00:03<09:00,  3.20s/it]
  4%|▍         | 7/170 [00:03<00:56,  2.86it/s]
                                               
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

  4%|▍         | 7/170 [00:03<00:56,  2.86it/s]
                                               
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (896,), dtype: float16

  4%|▍         | 7/170 [00:03<00:56,  2.86it/s]
                                               
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

  4%|▍         | 7/170 [00:03<00:56,  2.86it/s]
                                               
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

  4%|▍         | 7/170 [00:03<00:56,  2.86it/s]
  6%|▋         | 11/170 [00:03<00:33,  4.74it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (896,), dtype: float16

  6%|▋         | 11/170 [00:03<00:33,  4.74it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.c_attn.bias", shape: (1152,), dtype: float16

  6%|▋         | 11/170 [00:03<00:33,  4.74it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

  6%|▋         | 11/170 [00:03<00:33,  4.74it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

  6%|▋         | 11/170 [00:03<00:33,  4.74it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (896,), dtype: float16

  6%|▋         | 11/170 [00:03<00:33,  4.74it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

  6%|▋         | 11/170 [00:03<00:33,  4.74it/s]
 10%|█         | 17/170 [00:03<00:18,  8.41it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 10%|█         | 17/170 [00:03<00:18,  8.41it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (896,), dtype: float16

 10%|█         | 17/170 [00:03<00:18,  8.41it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 10%|█         | 17/170 [00:03<00:18,  8.41it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 10%|█         | 17/170 [00:03<00:18,  8.41it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 10%|█         | 17/170 [00:03<00:18,  8.41it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (896,), dtype: float16

 10%|█         | 17/170 [00:03<00:18,  8.41it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 10%|█         | 17/170 [00:03<00:18,  8.41it/s]
 14%|█▍        | 24/170 [00:03<00:11, 12.83it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 14%|█▍        | 24/170 [00:03<00:11, 12.83it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (896,), dtype: float16

 14%|█▍        | 24/170 [00:03<00:11, 12.83it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 14%|█▍        | 24/170 [00:03<00:11, 12.83it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 14%|█▍        | 24/170 [00:03<00:11, 12.83it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 14%|█▍        | 24/170 [00:03<00:11, 12.83it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (896,), dtype: float16

 14%|█▍        | 24/170 [00:03<00:11, 12.83it/s]
                                                
[2024-06-06 22:36:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 14%|█▍        | 24/170 [00:03<00:11, 12.83it/s]
 18%|█▊        | 31/170 [00:04<00:08, 17.01it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 18%|█▊        | 31/170 [00:04<00:08, 17.01it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (896,), dtype: float16

 18%|█▊        | 31/170 [00:04<00:08, 17.01it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 18%|█▊        | 31/170 [00:04<00:08, 17.01it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 18%|█▊        | 31/170 [00:04<00:08, 17.01it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 18%|█▊        | 31/170 [00:04<00:08, 17.01it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (896,), dtype: float16

 18%|█▊        | 31/170 [00:04<00:08, 17.01it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 18%|█▊        | 31/170 [00:04<00:08, 17.01it/s]
 22%|██▏       | 38/170 [00:04<00:06, 20.75it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 22%|██▏       | 38/170 [00:04<00:06, 20.75it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (896,), dtype: float16

 22%|██▏       | 38/170 [00:04<00:06, 20.75it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 22%|██▏       | 38/170 [00:04<00:06, 20.75it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 22%|██▏       | 38/170 [00:04<00:06, 20.75it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 22%|██▏       | 38/170 [00:04<00:06, 20.75it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (896,), dtype: float16

 22%|██▏       | 38/170 [00:04<00:06, 20.75it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 22%|██▏       | 38/170 [00:04<00:06, 20.75it/s]
 26%|██▋       | 45/170 [00:04<00:05, 24.06it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 26%|██▋       | 45/170 [00:04<00:05, 24.06it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (896,), dtype: float16

 26%|██▋       | 45/170 [00:04<00:05, 24.06it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 26%|██▋       | 45/170 [00:04<00:05, 24.06it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 26%|██▋       | 45/170 [00:04<00:05, 24.06it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 26%|██▋       | 45/170 [00:04<00:05, 24.06it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (896,), dtype: float16

 26%|██▋       | 45/170 [00:04<00:05, 24.06it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 26%|██▋       | 45/170 [00:04<00:05, 24.06it/s]
 31%|███       | 52/170 [00:04<00:04, 26.61it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 31%|███       | 52/170 [00:04<00:04, 26.61it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (896,), dtype: float16

 31%|███       | 52/170 [00:04<00:04, 26.61it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 31%|███       | 52/170 [00:04<00:04, 26.61it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 31%|███       | 52/170 [00:04<00:04, 26.61it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 31%|███       | 52/170 [00:04<00:04, 26.61it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (896,), dtype: float16

 31%|███       | 52/170 [00:04<00:04, 26.61it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 31%|███       | 52/170 [00:04<00:04, 26.61it/s]
 35%|███▍      | 59/170 [00:04<00:03, 28.55it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 35%|███▍      | 59/170 [00:04<00:03, 28.55it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (896,), dtype: float16

 35%|███▍      | 59/170 [00:04<00:03, 28.55it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 35%|███▍      | 59/170 [00:04<00:03, 28.55it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 35%|███▍      | 59/170 [00:04<00:03, 28.55it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 35%|███▍      | 59/170 [00:04<00:03, 28.55it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (896,), dtype: float16

 35%|███▍      | 59/170 [00:04<00:03, 28.55it/s]
                                                
[2024-06-06 22:36:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 35%|███▍      | 59/170 [00:04<00:03, 28.55it/s]
 39%|███▉      | 66/170 [00:05<00:03, 30.21it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 39%|███▉      | 66/170 [00:05<00:03, 30.21it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (896,), dtype: float16

 39%|███▉      | 66/170 [00:05<00:03, 30.21it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 39%|███▉      | 66/170 [00:05<00:03, 30.21it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 39%|███▉      | 66/170 [00:05<00:03, 30.21it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 39%|███▉      | 66/170 [00:05<00:03, 30.21it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (896,), dtype: float16

 39%|███▉      | 66/170 [00:05<00:03, 30.21it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 39%|███▉      | 66/170 [00:05<00:03, 30.21it/s]
 43%|████▎     | 73/170 [00:05<00:03, 31.33it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 43%|████▎     | 73/170 [00:05<00:03, 31.33it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (896,), dtype: float16

 43%|████▎     | 73/170 [00:05<00:03, 31.33it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 43%|████▎     | 73/170 [00:05<00:03, 31.33it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 43%|████▎     | 73/170 [00:05<00:03, 31.33it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 43%|████▎     | 73/170 [00:05<00:03, 31.33it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (896,), dtype: float16

 43%|████▎     | 73/170 [00:05<00:03, 31.33it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 43%|████▎     | 73/170 [00:05<00:03, 31.33it/s]
 47%|████▋     | 80/170 [00:05<00:02, 32.19it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 47%|████▋     | 80/170 [00:05<00:02, 32.19it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (896,), dtype: float16

 47%|████▋     | 80/170 [00:05<00:02, 32.19it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 47%|████▋     | 80/170 [00:05<00:02, 32.19it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 47%|████▋     | 80/170 [00:05<00:02, 32.19it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 47%|████▋     | 80/170 [00:05<00:02, 32.19it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (896,), dtype: float16

 47%|████▋     | 80/170 [00:05<00:02, 32.19it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 47%|████▋     | 80/170 [00:05<00:02, 32.19it/s]
 51%|█████     | 87/170 [00:05<00:02, 32.91it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 51%|█████     | 87/170 [00:05<00:02, 32.91it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (896,), dtype: float16

 51%|█████     | 87/170 [00:05<00:02, 32.91it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 51%|█████     | 87/170 [00:05<00:02, 32.91it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 51%|█████     | 87/170 [00:05<00:02, 32.91it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 51%|█████     | 87/170 [00:05<00:02, 32.91it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (896,), dtype: float16

 51%|█████     | 87/170 [00:05<00:02, 32.91it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 51%|█████     | 87/170 [00:05<00:02, 32.91it/s]
 55%|█████▌    | 94/170 [00:05<00:02, 33.17it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 55%|█████▌    | 94/170 [00:05<00:02, 33.17it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (896,), dtype: float16

 55%|█████▌    | 94/170 [00:05<00:02, 33.17it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 55%|█████▌    | 94/170 [00:05<00:02, 33.17it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 55%|█████▌    | 94/170 [00:05<00:02, 33.17it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 55%|█████▌    | 94/170 [00:05<00:02, 33.17it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (896,), dtype: float16

 55%|█████▌    | 94/170 [00:05<00:02, 33.17it/s]
                                                
[2024-06-06 22:36:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 55%|█████▌    | 94/170 [00:05<00:02, 33.17it/s]
 59%|█████▉    | 101/170 [00:06<00:02, 33.49it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 59%|█████▉    | 101/170 [00:06<00:02, 33.49it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (896,), dtype: float16

 59%|█████▉    | 101/170 [00:06<00:02, 33.49it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 59%|█████▉    | 101/170 [00:06<00:02, 33.49it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 59%|█████▉    | 101/170 [00:06<00:02, 33.49it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 59%|█████▉    | 101/170 [00:06<00:02, 33.49it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (896,), dtype: float16

 59%|█████▉    | 101/170 [00:06<00:02, 33.49it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 59%|█████▉    | 101/170 [00:06<00:02, 33.49it/s]
 64%|██████▎   | 108/170 [00:06<00:01, 33.77it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 64%|██████▎   | 108/170 [00:06<00:01, 33.77it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (896,), dtype: float16

 64%|██████▎   | 108/170 [00:06<00:01, 33.77it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 64%|██████▎   | 108/170 [00:06<00:01, 33.77it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 64%|██████▎   | 108/170 [00:06<00:01, 33.77it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 64%|██████▎   | 108/170 [00:06<00:01, 33.77it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (896,), dtype: float16

 64%|██████▎   | 108/170 [00:06<00:01, 33.77it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 64%|██████▎   | 108/170 [00:06<00:01, 33.77it/s]
 68%|██████▊   | 115/170 [00:06<00:01, 34.18it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 68%|██████▊   | 115/170 [00:06<00:01, 34.18it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (896,), dtype: float16

 68%|██████▊   | 115/170 [00:06<00:01, 34.18it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 68%|██████▊   | 115/170 [00:06<00:01, 34.18it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 68%|██████▊   | 115/170 [00:06<00:01, 34.18it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 68%|██████▊   | 115/170 [00:06<00:01, 34.18it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (896,), dtype: float16

 68%|██████▊   | 115/170 [00:06<00:01, 34.18it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 68%|██████▊   | 115/170 [00:06<00:01, 34.18it/s]
 72%|███████▏  | 122/170 [00:06<00:01, 33.96it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 72%|███████▏  | 122/170 [00:06<00:01, 33.96it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (896,), dtype: float16

 72%|███████▏  | 122/170 [00:06<00:01, 33.96it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 72%|███████▏  | 122/170 [00:06<00:01, 33.96it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 72%|███████▏  | 122/170 [00:06<00:01, 33.96it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 72%|███████▏  | 122/170 [00:06<00:01, 33.96it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (896,), dtype: float16

 72%|███████▏  | 122/170 [00:06<00:01, 33.96it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 72%|███████▏  | 122/170 [00:06<00:01, 33.96it/s]
 76%|███████▌  | 129/170 [00:06<00:01, 34.08it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 76%|███████▌  | 129/170 [00:06<00:01, 34.08it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (896,), dtype: float16

 76%|███████▌  | 129/170 [00:06<00:01, 34.08it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 76%|███████▌  | 129/170 [00:06<00:01, 34.08it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 76%|███████▌  | 129/170 [00:06<00:01, 34.08it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 76%|███████▌  | 129/170 [00:06<00:01, 34.08it/s]
                                                 
[2024-06-06 22:36:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (896,), dtype: float16

 76%|███████▌  | 129/170 [00:06<00:01, 34.08it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 76%|███████▌  | 129/170 [00:06<00:01, 34.08it/s]
 80%|████████  | 136/170 [00:07<00:01, 33.99it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 80%|████████  | 136/170 [00:07<00:01, 33.99it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (896,), dtype: float16

 80%|████████  | 136/170 [00:07<00:01, 33.99it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 80%|████████  | 136/170 [00:07<00:01, 33.99it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 80%|████████  | 136/170 [00:07<00:01, 33.99it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 80%|████████  | 136/170 [00:07<00:01, 33.99it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (896,), dtype: float16

 80%|████████  | 136/170 [00:07<00:01, 33.99it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 80%|████████  | 136/170 [00:07<00:01, 33.99it/s]
 84%|████████▍ | 143/170 [00:07<00:00, 33.72it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 84%|████████▍ | 143/170 [00:07<00:00, 33.72it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (896,), dtype: float16

 84%|████████▍ | 143/170 [00:07<00:00, 33.72it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 84%|████████▍ | 143/170 [00:07<00:00, 33.72it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 84%|████████▍ | 143/170 [00:07<00:00, 33.72it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 84%|████████▍ | 143/170 [00:07<00:00, 33.72it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (896,), dtype: float16

 84%|████████▍ | 143/170 [00:07<00:00, 33.72it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 84%|████████▍ | 143/170 [00:07<00:00, 33.72it/s]
 88%|████████▊ | 150/170 [00:07<00:00, 33.88it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 88%|████████▊ | 150/170 [00:07<00:00, 33.88it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (896,), dtype: float16

 88%|████████▊ | 150/170 [00:07<00:00, 33.88it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 88%|████████▊ | 150/170 [00:07<00:00, 33.88it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 88%|████████▊ | 150/170 [00:07<00:00, 33.88it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 88%|████████▊ | 150/170 [00:07<00:00, 33.88it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (896,), dtype: float16

 88%|████████▊ | 150/170 [00:07<00:00, 33.88it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 88%|████████▊ | 150/170 [00:07<00:00, 33.88it/s]
 92%|█████████▏| 157/170 [00:07<00:00, 33.94it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 92%|█████████▏| 157/170 [00:07<00:00, 33.94it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (896,), dtype: float16

 92%|█████████▏| 157/170 [00:07<00:00, 33.94it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 92%|█████████▏| 157/170 [00:07<00:00, 33.94it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 92%|█████████▏| 157/170 [00:07<00:00, 33.94it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 92%|█████████▏| 157/170 [00:07<00:00, 33.94it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (896,), dtype: float16

 92%|█████████▏| 157/170 [00:07<00:00, 33.94it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.mlp.down_proj.weight", shape: (896, 4864), dtype: float16

 92%|█████████▏| 157/170 [00:07<00:00, 33.94it/s]
 96%|█████████▋| 164/170 [00:07<00:00, 34.01it/s]
                                                 
[2024-06-06 22:36:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.mlp.gate_up_proj.weight", shape: (9728, 896), dtype: float16

 96%|█████████▋| 164/170 [00:07<00:00, 34.01it/s]
                                                 
[2024-06-06 22:36:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (896,), dtype: float16

 96%|█████████▋| 164/170 [00:07<00:00, 34.01it/s]
                                                 
[2024-06-06 22:36:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.c_attn.bias", shape: (1152,), dtype: float16

 96%|█████████▋| 164/170 [00:07<00:00, 34.01it/s]
                                                 
[2024-06-06 22:36:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.c_attn.weight", shape: (1152, 896), dtype: float16

 96%|█████████▋| 164/170 [00:07<00:00, 34.01it/s]
                                                 
[2024-06-06 22:36:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.o_proj.weight", shape: (896, 896), dtype: float16

 96%|█████████▋| 164/170 [00:08<00:00, 34.01it/s]
                                                 
[2024-06-06 22:36:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (896,), dtype: float16

 96%|█████████▋| 164/170 [00:08<00:00, 34.01it/s]
100%|██████████| 170/170 [00:08<00:00, 21.23it/s]
[2024-06-06 22:36:30] INFO huggingface_loader.py:197: Unloading HF weight file: /ssd2/models/Qwen2-0.5B-Instruct/model.safetensors
[2024-06-06 22:36:30] INFO stats.py:77: Time usage: HF loading: 1.528 sec; Pre-quantization mapping: 1.849 sec; Quantization: 0.000 sec
[2024-06-06 22:36:30] INFO stats.py:91: RAM usage: Peak RAM: 1.840 GB. Total bytes loaded from disk: 1.840 GB
[2024-06-06 22:36:30] INFO convert_weight.py:155: Parameter size after quantization: 0.920 GB
[2024-06-06 22:36:30] INFO convert_weight.py:160: Total parameters: 494,032,768
[2024-06-06 22:36:30] INFO convert_weight.py:161: Bits per parameter: 16.000
[2024-06-06 22:36:30] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f16-MLC

All finished, 25 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Qwen2-0.5B-Instruct-q0f16-MLC/ndarray-cache.json