/home/ruihang/Workspace/miniconda3/envs/python311/bin/python -m mlc_llm gen_config /models/Llama-2-7b-chat-hf --quantization q0f16 --conv-template llama-2 --output /tmp/tmp8ew5r2yr
[2024-05-22 00:30:05] INFO auto_config.py:115: Found model configuration: /models/Llama-2-7b-chat-hf/config.json
[2024-05-22 00:30:05] INFO auto_config.py:153: Found model type: llama. Use `--model-type` to override.
[2024-05-22 00:30:05] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (4096)
[2024-05-22 00:30:05] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
[2024-05-22 00:30:05] INFO config.py:106: Overriding max_batch_size from 1 to 80
[2024-05-22 00:30:05] INFO gen_config.py:255: [generation_config.json] Setting bos_token_id: 1
[2024-05-22 00:30:05] INFO gen_config.py:255: [generation_config.json] Setting eos_token_id: 2
[2024-05-22 00:30:05] INFO gen_config.py:255: [generation_config.json] Setting pad_token_id: 0
[2024-05-22 00:30:05] INFO gen_config.py:255: [generation_config.json] Setting temperature: 0.6
[2024-05-22 00:30:05] INFO gen_config.py:255: [generation_config.json] Setting top_p: 0.9
[2024-05-22 00:30:05] INFO gen_config.py:267: Found tokenizer config: /models/Llama-2-7b-chat-hf/tokenizer.model. Copying to /tmp/tmp8ew5r2yr/tokenizer.model
[2024-05-22 00:30:05] INFO gen_config.py:267: Found tokenizer config: /models/Llama-2-7b-chat-hf/tokenizer.json. Copying to /tmp/tmp8ew5r2yr/tokenizer.json
[2024-05-22 00:30:05] INFO gen_config.py:269: Not found tokenizer config: /models/Llama-2-7b-chat-hf/vocab.json
[2024-05-22 00:30:05] INFO gen_config.py:269: Not found tokenizer config: /models/Llama-2-7b-chat-hf/merges.txt
[2024-05-22 00:30:05] INFO gen_config.py:269: Not found tokenizer config: /models/Llama-2-7b-chat-hf/added_tokens.json
[2024-05-22 00:30:05] INFO gen_config.py:267: Found tokenizer config: /models/Llama-2-7b-chat-hf/tokenizer_config.json. Copying to /tmp/tmp8ew5r2yr/tokenizer_config.json
[2024-05-22 00:30:05] INFO gen_config.py:80: [System default] Setting presence_penalty: 0.0
[2024-05-22 00:30:05] INFO gen_config.py:80: [System default] Setting frequency_penalty: 0.0
[2024-05-22 00:30:05] INFO gen_config.py:80: [System default] Setting repetition_penalty: 1.0
[2024-05-22 00:30:05] INFO gen_config.py:80: [System default] Setting mean_gen_len: 128
[2024-05-22 00:30:05] INFO gen_config.py:80: [System default] Setting max_gen_len: 512
[2024-05-22 00:30:05] INFO gen_config.py:80: [System default] Setting shift_fill_factor: 0.3
[2024-05-22 00:30:05] INFO gen_config.py:335: Dumping configuration file to: /tmp/tmp8ew5r2yr/mlc-chat-config.json
/home/ruihang/Workspace/miniconda3/envs/python311/bin/python -m mlc_llm convert_weight /models/Llama-2-7b-chat-hf --quantization q0f16 --source-format auto --output /tmp/tmp8ew5r2yr
[2024-05-22 00:30:06] INFO auto_config.py:115: Found model configuration: /models/Llama-2-7b-chat-hf/config.json
[2024-05-22 00:30:06] INFO auto_device.py:79: Found device: cuda:0
[2024-05-22 00:30:06] INFO auto_device.py:79: Found device: cuda:1
[2024-05-22 00:30:07] INFO auto_device.py:88: Not found device: rocm:0
[2024-05-22 00:30:08] INFO auto_device.py:88: Not found device: metal:0
[2024-05-22 00:30:09] INFO auto_device.py:79: Found device: vulkan:0
[2024-05-22 00:30:09] INFO auto_device.py:79: Found device: vulkan:1
[2024-05-22 00:30:09] INFO auto_device.py:79: Found device: vulkan:2
[2024-05-22 00:30:10] INFO auto_device.py:79: Found device: opencl:0
[2024-05-22 00:30:10] INFO auto_device.py:79: Found device: opencl:1
[2024-05-22 00:30:10] INFO auto_device.py:35: Using device: cuda:0
[2024-05-22 00:30:10] INFO auto_weight.py:70: Finding weights in: /models/Llama-2-7b-chat-hf
[2024-05-22 00:30:10] INFO auto_weight.py:120: Found source weight format: huggingface-torch. Source configuration: /models/Llama-2-7b-chat-hf/pytorch_model.bin.index.json
[2024-05-22 00:30:10] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: /models/Llama-2-7b-chat-hf/model.safetensors.index.json
[2024-05-22 00:30:10] INFO auto_weight.py:106: Using source weight configuration: /models/Llama-2-7b-chat-hf/pytorch_model.bin.index.json. Use `--source` to override.
[2024-05-22 00:30:10] INFO auto_weight.py:110: Using source weight format: huggingface-torch. Use `--source-format` to override.
[2024-05-22 00:30:10] INFO auto_config.py:153: Found model type: llama. Use `--model-type` to override.
[2024-05-22 00:30:10] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (4096)
[2024-05-22 00:30:10] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
Weight conversion with arguments:
  --config          /models/Llama-2-7b-chat-hf/config.json
  --quantization    NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16')
  --model-type      llama
  --device          cuda:0
  --source          /models/Llama-2-7b-chat-hf/pytorch_model.bin.index.json
  --source-format   huggingface-torch
  --output          /tmp/tmp8ew5r2yr
Start storing to cache /tmp/tmp8ew5r2yr

  0%|          | 0/195 [00:00<?, ?it/s]
                                       
[2024-05-22 00:30:11] INFO huggingface_loader.py:184: Loading HF parameters from: /models/Llama-2-7b-chat-hf/pytorch_model-00002-of-00002.bin

  0%|          | 0/195 [00:00<?, ?it/s]
                                       
[2024-05-22 00:30:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "lm_head.weight", shape: (32000, 4096), dtype: float16

  0%|          | 0/195 [00:08<?, ?it/s]
  1%|          | 1/195 [00:09<29:48,  9.22s/it]
                                               
[2024-05-22 00:30:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (4096,), dtype: float16

  1%|          | 1/195 [00:09<29:48,  9.22s/it]
                                               
[2024-05-22 00:30:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.24.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

  1%|          | 1/195 [00:09<29:48,  9.22s/it]
  2%|▏         | 3/195 [00:09<07:58,  2.49s/it]
                                               
[2024-05-22 00:30:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.24.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

  2%|▏         | 3/195 [00:09<07:58,  2.49s/it]
  2%|▏         | 4/195 [00:10<06:17,  1.98s/it]
                                               
[2024-05-22 00:30:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (4096,), dtype: float16

  2%|▏         | 4/195 [00:10<06:17,  1.98s/it]
                                               
[2024-05-22 00:30:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.24.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

  2%|▏         | 4/195 [00:10<06:17,  1.98s/it]
  3%|▎         | 6/195 [00:10<03:28,  1.10s/it]
                                               
[2024-05-22 00:30:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.24.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

  3%|▎         | 6/195 [00:10<03:28,  1.10s/it]
  4%|▎         | 7/195 [00:11<02:38,  1.19it/s]
                                               
[2024-05-22 00:30:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (4096,), dtype: float16

  4%|▎         | 7/195 [00:11<02:38,  1.19it/s]
                                               
[2024-05-22 00:30:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.25.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

  4%|▎         | 7/195 [00:11<02:38,  1.19it/s]
  5%|▍         | 9/195 [00:11<01:39,  1.87it/s]
                                               
[2024-05-22 00:30:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.25.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

  5%|▍         | 9/195 [00:11<01:39,  1.87it/s]
  5%|▌         | 10/195 [00:12<02:00,  1.54it/s]
                                                
[2024-05-22 00:30:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (4096,), dtype: float16

  5%|▌         | 10/195 [00:12<02:00,  1.54it/s]
                                                
[2024-05-22 00:30:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.25.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

  5%|▌         | 10/195 [00:12<02:00,  1.54it/s]
  6%|▌         | 12/195 [00:12<01:24,  2.15it/s]
                                                
[2024-05-22 00:30:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.25.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

  6%|▌         | 12/195 [00:12<01:24,  2.15it/s]
  7%|▋         | 13/195 [00:12<01:09,  2.61it/s]
                                                
[2024-05-22 00:30:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (4096,), dtype: float16

  7%|▋         | 13/195 [00:12<01:09,  2.61it/s]
                                                
[2024-05-22 00:30:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.26.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

  7%|▋         | 13/195 [00:12<01:09,  2.61it/s]
  8%|▊         | 15/195 [00:13<00:50,  3.53it/s]
                                                
[2024-05-22 00:30:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.26.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

  8%|▊         | 15/195 [00:13<00:50,  3.53it/s]
  8%|▊         | 16/195 [00:13<01:15,  2.36it/s]
                                                
[2024-05-22 00:30:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (4096,), dtype: float16

  8%|▊         | 16/195 [00:13<01:15,  2.36it/s]
                                                
[2024-05-22 00:30:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.26.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

  8%|▊         | 16/195 [00:14<01:15,  2.36it/s]
  9%|▉         | 18/195 [00:14<00:58,  3.04it/s]
                                                
[2024-05-22 00:30:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.26.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

  9%|▉         | 18/195 [00:14<00:58,  3.04it/s]
 10%|▉         | 19/195 [00:14<00:49,  3.57it/s]
                                                
[2024-05-22 00:30:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (4096,), dtype: float16

 10%|▉         | 19/195 [00:14<00:49,  3.57it/s]
                                                
[2024-05-22 00:30:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.27.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 10%|▉         | 19/195 [00:14<00:49,  3.57it/s]
 11%|█         | 21/195 [00:14<00:38,  4.53it/s]
                                                
[2024-05-22 00:30:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.27.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 11%|█         | 21/195 [00:14<00:38,  4.53it/s]
 11%|█▏        | 22/195 [00:15<00:55,  3.11it/s]
                                                
[2024-05-22 00:30:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 11%|█▏        | 22/195 [00:15<00:55,  3.11it/s]
                                                
[2024-05-22 00:30:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.27.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 11%|█▏        | 22/195 [00:15<00:55,  3.11it/s]
 12%|█▏        | 24/195 [00:15<00:44,  3.87it/s]
                                                
[2024-05-22 00:30:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.27.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 12%|█▏        | 24/195 [00:15<00:44,  3.87it/s]
 13%|█▎        | 25/195 [00:15<00:38,  4.45it/s]
                                                
[2024-05-22 00:30:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.28.input_layernorm.weight", shape: (4096,), dtype: float16

 13%|█▎        | 25/195 [00:15<00:38,  4.45it/s]
                                                
[2024-05-22 00:30:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.28.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 13%|█▎        | 25/195 [00:15<00:38,  4.45it/s]
 14%|█▍        | 27/195 [00:16<00:31,  5.38it/s]
                                                
[2024-05-22 00:30:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.28.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 14%|█▍        | 27/195 [00:16<00:31,  5.38it/s]
 14%|█▍        | 28/195 [00:16<00:53,  3.14it/s]
                                                
[2024-05-22 00:30:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.28.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 14%|█▍        | 28/195 [00:16<00:53,  3.14it/s]
                                                
[2024-05-22 00:30:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.28.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 14%|█▍        | 28/195 [00:16<00:53,  3.14it/s]
 15%|█▌        | 30/195 [00:17<00:42,  3.89it/s]
                                                
[2024-05-22 00:30:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.28.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 15%|█▌        | 30/195 [00:17<00:42,  3.89it/s]
 16%|█▌        | 31/195 [00:17<00:36,  4.47it/s]
                                                
[2024-05-22 00:30:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.29.input_layernorm.weight", shape: (4096,), dtype: float16

 16%|█▌        | 31/195 [00:17<00:36,  4.47it/s]
                                                
[2024-05-22 00:30:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.29.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 16%|█▌        | 31/195 [00:17<00:36,  4.47it/s]
 17%|█▋        | 33/195 [00:17<00:32,  4.97it/s]
                                                
[2024-05-22 00:30:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.29.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 17%|█▋        | 33/195 [00:17<00:32,  4.97it/s]
 17%|█▋        | 34/195 [00:18<00:51,  3.12it/s]
                                                
[2024-05-22 00:30:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.29.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 17%|█▋        | 34/195 [00:18<00:51,  3.12it/s]
                                                
[2024-05-22 00:30:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.29.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 17%|█▋        | 34/195 [00:18<00:51,  3.12it/s]
 18%|█▊        | 36/195 [00:18<00:42,  3.77it/s]
                                                
[2024-05-22 00:30:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.29.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 18%|█▊        | 36/195 [00:18<00:42,  3.77it/s]
                                                
[2024-05-22 00:30:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.30.input_layernorm.weight", shape: (4096,), dtype: float16

 18%|█▊        | 36/195 [00:18<00:42,  3.77it/s]
 19%|█▉        | 38/195 [00:18<00:29,  5.26it/s]
                                                
[2024-05-22 00:30:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.30.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 19%|█▉        | 38/195 [00:18<00:29,  5.26it/s]
 20%|██        | 39/195 [00:19<00:31,  5.02it/s]
                                                
[2024-05-22 00:30:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.30.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 20%|██        | 39/195 [00:19<00:31,  5.02it/s]
 21%|██        | 40/195 [00:19<00:46,  3.35it/s]
                                                
[2024-05-22 00:30:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.30.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 21%|██        | 40/195 [00:19<00:46,  3.35it/s]
                                                
[2024-05-22 00:30:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.30.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 21%|██        | 40/195 [00:19<00:46,  3.35it/s]
 22%|██▏       | 42/195 [00:19<00:37,  4.12it/s]
                                                
[2024-05-22 00:30:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.30.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 22%|██▏       | 42/195 [00:19<00:37,  4.12it/s]
 22%|██▏       | 43/195 [00:20<00:32,  4.72it/s]
                                                
[2024-05-22 00:30:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.31.input_layernorm.weight", shape: (4096,), dtype: float16

 22%|██▏       | 43/195 [00:20<00:32,  4.72it/s]
                                                
[2024-05-22 00:30:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.31.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 22%|██▏       | 43/195 [00:20<00:32,  4.72it/s]
 23%|██▎       | 45/195 [00:20<00:26,  5.62it/s]
                                                
[2024-05-22 00:30:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.31.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 23%|██▎       | 45/195 [00:20<00:26,  5.62it/s]
 24%|██▎       | 46/195 [00:21<00:44,  3.35it/s]
                                                
[2024-05-22 00:30:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.31.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 24%|██▎       | 46/195 [00:21<00:44,  3.35it/s]
                                                
[2024-05-22 00:30:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.31.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 24%|██▎       | 46/195 [00:21<00:44,  3.35it/s]
 25%|██▍       | 48/195 [00:21<00:35,  4.11it/s]
                                                
[2024-05-22 00:30:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.31.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 25%|██▍       | 48/195 [00:21<00:35,  4.11it/s]
 25%|██▌       | 49/195 [00:21<00:31,  4.70it/s]
                                                
[2024-05-22 00:30:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.norm.weight", shape: (4096,), dtype: float16

 25%|██▌       | 49/195 [00:21<00:31,  4.70it/s]
                                                
[2024-05-22 00:30:32] INFO huggingface_loader.py:196: Unloading HF weight file: /models/Llama-2-7b-chat-hf/pytorch_model-00002-of-00002.bin

 25%|██▌       | 49/195 [00:21<00:31,  4.70it/s]
                                                
[2024-05-22 00:30:32] INFO huggingface_loader.py:184: Loading HF parameters from: /models/Llama-2-7b-chat-hf/pytorch_model-00001-of-00002.bin

 25%|██▌       | 49/195 [00:21<00:31,  4.70it/s]
                                                
[2024-05-22 00:31:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.embed_tokens.weight", shape: (32000, 4096), dtype: float16

 25%|██▌       | 49/195 [00:58<00:31,  4.70it/s]
 26%|██▌       | 51/195 [00:58<17:18,  7.21s/it]
                                                
[2024-05-22 00:31:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (4096,), dtype: float16

 26%|██▌       | 51/195 [00:58<17:18,  7.21s/it]
                                                
[2024-05-22 00:31:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 26%|██▌       | 51/195 [00:58<17:18,  7.21s/it]
 27%|██▋       | 53/195 [00:59<11:13,  4.74s/it]
                                                
[2024-05-22 00:31:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 27%|██▋       | 53/195 [00:59<11:13,  4.74s/it]
 28%|██▊       | 54/195 [01:00<09:23,  4.00s/it]
                                                
[2024-05-22 00:31:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 28%|██▊       | 54/195 [01:00<09:23,  4.00s/it]
                                                
[2024-05-22 00:31:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 28%|██▊       | 54/195 [01:00<09:23,  4.00s/it]
 29%|██▊       | 56/195 [01:00<06:03,  2.61s/it]
                                                
[2024-05-22 00:31:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 29%|██▊       | 56/195 [01:00<06:03,  2.61s/it]
 29%|██▉       | 57/195 [01:00<04:50,  2.10s/it]
                                                
[2024-05-22 00:31:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (4096,), dtype: float16

 29%|██▉       | 57/195 [01:00<04:50,  2.10s/it]
                                                
[2024-05-22 00:31:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 29%|██▉       | 57/195 [01:00<04:50,  2.10s/it]
 30%|███       | 59/195 [01:01<03:07,  1.38s/it]
                                                
[2024-05-22 00:31:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 30%|███       | 59/195 [01:01<03:07,  1.38s/it]
 31%|███       | 60/195 [01:01<02:47,  1.24s/it]
                                                
[2024-05-22 00:31:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 31%|███       | 60/195 [01:01<02:47,  1.24s/it]
                                                
[2024-05-22 00:31:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 31%|███       | 60/195 [01:01<02:47,  1.24s/it]
 32%|███▏      | 62/195 [01:02<01:52,  1.18it/s]
                                                
[2024-05-22 00:31:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 32%|███▏      | 62/195 [01:02<01:52,  1.18it/s]
 32%|███▏      | 63/195 [01:02<01:31,  1.44it/s]
                                                
[2024-05-22 00:31:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (4096,), dtype: float16

 32%|███▏      | 63/195 [01:02<01:31,  1.44it/s]
                                                
[2024-05-22 00:31:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 32%|███▏      | 63/195 [01:02<01:31,  1.44it/s]
 33%|███▎      | 65/195 [01:02<01:03,  2.04it/s]
                                                
[2024-05-22 00:31:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 33%|███▎      | 65/195 [01:02<01:03,  2.04it/s]
 34%|███▍      | 66/195 [01:03<01:08,  1.90it/s]
                                                
[2024-05-22 00:31:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 34%|███▍      | 66/195 [01:03<01:08,  1.90it/s]
                                                
[2024-05-22 00:31:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 34%|███▍      | 66/195 [01:03<01:08,  1.90it/s]
 35%|███▍      | 68/195 [01:03<00:48,  2.61it/s]
                                                
[2024-05-22 00:31:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 35%|███▍      | 68/195 [01:03<00:48,  2.61it/s]
                                                
[2024-05-22 00:31:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (4096,), dtype: float16

 35%|███▍      | 68/195 [01:03<00:48,  2.61it/s]
                                                
[2024-05-22 00:31:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 35%|███▍      | 68/195 [01:03<00:48,  2.61it/s]
 36%|███▋      | 71/195 [01:03<00:32,  3.82it/s]
                                                
[2024-05-22 00:31:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 36%|███▋      | 71/195 [01:03<00:32,  3.82it/s]
 37%|███▋      | 72/195 [01:04<00:37,  3.31it/s]
                                                
[2024-05-22 00:31:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 37%|███▋      | 72/195 [01:04<00:37,  3.31it/s]
                                                
[2024-05-22 00:31:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 37%|███▋      | 72/195 [01:04<00:37,  3.31it/s]
 38%|███▊      | 74/195 [01:04<00:30,  4.02it/s]
                                                
[2024-05-22 00:31:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 38%|███▊      | 74/195 [01:04<00:30,  4.02it/s]
                                                
[2024-05-22 00:31:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (4096,), dtype: float16

 38%|███▊      | 74/195 [01:04<00:30,  4.02it/s]
                                                
[2024-05-22 00:31:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 38%|███▊      | 74/195 [01:04<00:30,  4.02it/s]
 39%|███▉      | 77/195 [01:04<00:22,  5.26it/s]
                                                
[2024-05-22 00:31:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 39%|███▉      | 77/195 [01:05<00:22,  5.26it/s]
 40%|████      | 78/195 [01:05<00:27,  4.18it/s]
                                                
[2024-05-22 00:31:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 40%|████      | 78/195 [01:05<00:27,  4.18it/s]
                                                
[2024-05-22 00:31:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 40%|████      | 78/195 [01:05<00:27,  4.18it/s]
 41%|████      | 80/195 [01:05<00:23,  4.83it/s]
                                                
[2024-05-22 00:31:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 41%|████      | 80/195 [01:05<00:23,  4.83it/s]
                                                
[2024-05-22 00:31:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (4096,), dtype: float16

 41%|████      | 80/195 [01:05<00:23,  4.83it/s]
                                                
[2024-05-22 00:31:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 41%|████      | 80/195 [01:05<00:23,  4.83it/s]
 43%|████▎     | 83/195 [01:06<00:18,  6.01it/s]
                                                
[2024-05-22 00:31:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 43%|████▎     | 83/195 [01:06<00:18,  6.01it/s]
 43%|████▎     | 84/195 [01:06<00:24,  4.57it/s]
                                                
[2024-05-22 00:31:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 43%|████▎     | 84/195 [01:06<00:24,  4.57it/s]
                                                
[2024-05-22 00:31:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 43%|████▎     | 84/195 [01:06<00:24,  4.57it/s]
 44%|████▍     | 86/195 [01:06<00:20,  5.19it/s]
                                                
[2024-05-22 00:31:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 44%|████▍     | 86/195 [01:06<00:20,  5.19it/s]
                                                
[2024-05-22 00:31:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (4096,), dtype: float16

 44%|████▍     | 86/195 [01:06<00:20,  5.19it/s]
                                                
[2024-05-22 00:31:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 44%|████▍     | 86/195 [01:06<00:20,  5.19it/s]
 46%|████▌     | 89/195 [01:07<00:16,  6.37it/s]
                                                
[2024-05-22 00:31:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 46%|████▌     | 89/195 [01:07<00:16,  6.37it/s]
 46%|████▌     | 90/195 [01:07<00:21,  4.80it/s]
                                                
[2024-05-22 00:31:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 46%|████▌     | 90/195 [01:07<00:21,  4.80it/s]
                                                
[2024-05-22 00:31:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 46%|████▌     | 90/195 [01:07<00:21,  4.80it/s]
 47%|████▋     | 92/195 [01:07<00:19,  5.41it/s]
                                                
[2024-05-22 00:31:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 47%|████▋     | 92/195 [01:07<00:19,  5.41it/s]
                                                
[2024-05-22 00:31:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (4096,), dtype: float16

 47%|████▋     | 92/195 [01:07<00:19,  5.41it/s]
                                                
[2024-05-22 00:31:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 47%|████▋     | 92/195 [01:07<00:19,  5.41it/s]
 49%|████▊     | 95/195 [01:08<00:15,  6.51it/s]
                                                
[2024-05-22 00:31:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 49%|████▊     | 95/195 [01:08<00:15,  6.51it/s]
 49%|████▉     | 96/195 [01:08<00:20,  4.81it/s]
                                                
[2024-05-22 00:31:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 49%|████▉     | 96/195 [01:08<00:20,  4.81it/s]
                                                
[2024-05-22 00:31:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 49%|████▉     | 96/195 [01:08<00:20,  4.81it/s]
 50%|█████     | 98/195 [01:08<00:17,  5.41it/s]
                                                
[2024-05-22 00:31:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 50%|█████     | 98/195 [01:08<00:17,  5.41it/s]
                                                
[2024-05-22 00:31:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (4096,), dtype: float16

 50%|█████     | 98/195 [01:09<00:17,  5.41it/s]
                                                
[2024-05-22 00:31:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 50%|█████     | 98/195 [01:09<00:17,  5.41it/s]
 52%|█████▏    | 101/195 [01:09<00:14,  6.58it/s]
                                                 
[2024-05-22 00:31:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 52%|█████▏    | 101/195 [01:09<00:14,  6.58it/s]
 52%|█████▏    | 102/195 [01:09<00:18,  4.92it/s]
                                                 
[2024-05-22 00:31:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 52%|█████▏    | 102/195 [01:09<00:18,  4.92it/s]
                                                 
[2024-05-22 00:31:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 52%|█████▏    | 102/195 [01:09<00:18,  4.92it/s]
 53%|█████▎    | 104/195 [01:10<00:16,  5.44it/s]
                                                 
[2024-05-22 00:31:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 53%|█████▎    | 104/195 [01:10<00:16,  5.44it/s]
                                                 
[2024-05-22 00:31:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (4096,), dtype: float16

 53%|█████▎    | 104/195 [01:10<00:16,  5.44it/s]
                                                 
[2024-05-22 00:31:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 53%|█████▎    | 104/195 [01:10<00:16,  5.44it/s]
 55%|█████▍    | 107/195 [01:10<00:13,  6.60it/s]
                                                 
[2024-05-22 00:31:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 55%|█████▍    | 107/195 [01:10<00:13,  6.60it/s]
 55%|█████▌    | 108/195 [01:10<00:17,  4.94it/s]
                                                 
[2024-05-22 00:31:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 55%|█████▌    | 108/195 [01:10<00:17,  4.94it/s]
                                                 
[2024-05-22 00:31:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 55%|█████▌    | 108/195 [01:10<00:17,  4.94it/s]
 56%|█████▋    | 110/195 [01:11<00:15,  5.47it/s]
                                                 
[2024-05-22 00:31:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 56%|█████▋    | 110/195 [01:11<00:15,  5.47it/s]
                                                 
[2024-05-22 00:31:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (4096,), dtype: float16

 56%|█████▋    | 110/195 [01:11<00:15,  5.47it/s]
                                                 
[2024-05-22 00:31:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 56%|█████▋    | 110/195 [01:11<00:15,  5.47it/s]
 58%|█████▊    | 113/195 [01:11<00:12,  6.62it/s]
                                                 
[2024-05-22 00:31:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 58%|█████▊    | 113/195 [01:11<00:12,  6.62it/s]
 58%|█████▊    | 114/195 [01:11<00:16,  4.95it/s]
                                                 
[2024-05-22 00:31:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 58%|█████▊    | 114/195 [01:11<00:16,  4.95it/s]
                                                 
[2024-05-22 00:31:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 58%|█████▊    | 114/195 [01:11<00:16,  4.95it/s]
 59%|█████▉    | 116/195 [01:12<00:14,  5.55it/s]
                                                 
[2024-05-22 00:31:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 59%|█████▉    | 116/195 [01:12<00:14,  5.55it/s]
                                                 
[2024-05-22 00:31:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (4096,), dtype: float16

 59%|█████▉    | 116/195 [01:12<00:14,  5.55it/s]
                                                 
[2024-05-22 00:31:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 59%|█████▉    | 116/195 [01:12<00:14,  5.55it/s]
 61%|██████    | 119/195 [01:12<00:11,  6.63it/s]
                                                 
[2024-05-22 00:31:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 61%|██████    | 119/195 [01:12<00:11,  6.63it/s]
 62%|██████▏   | 120/195 [01:12<00:15,  4.78it/s]
                                                 
[2024-05-22 00:31:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 62%|██████▏   | 120/195 [01:12<00:15,  4.78it/s]
                                                 
[2024-05-22 00:31:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 62%|██████▏   | 120/195 [01:13<00:15,  4.78it/s]
 63%|██████▎   | 122/195 [01:13<00:13,  5.33it/s]
                                                 
[2024-05-22 00:31:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 63%|██████▎   | 122/195 [01:13<00:13,  5.33it/s]
                                                 
[2024-05-22 00:31:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (4096,), dtype: float16

 63%|██████▎   | 122/195 [01:13<00:13,  5.33it/s]
                                                 
[2024-05-22 00:31:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 63%|██████▎   | 122/195 [01:13<00:13,  5.33it/s]
 64%|██████▍   | 125/195 [01:13<00:10,  6.42it/s]
                                                 
[2024-05-22 00:31:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 64%|██████▍   | 125/195 [01:13<00:10,  6.42it/s]
 65%|██████▍   | 126/195 [01:14<00:14,  4.77it/s]
                                                 
[2024-05-22 00:31:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 65%|██████▍   | 126/195 [01:14<00:14,  4.77it/s]
                                                 
[2024-05-22 00:31:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 65%|██████▍   | 126/195 [01:14<00:14,  4.77it/s]
 66%|██████▌   | 128/195 [01:14<00:12,  5.32it/s]
                                                 
[2024-05-22 00:31:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 66%|██████▌   | 128/195 [01:14<00:12,  5.32it/s]
                                                 
[2024-05-22 00:31:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (4096,), dtype: float16

 66%|██████▌   | 128/195 [01:14<00:12,  5.32it/s]
                                                 
[2024-05-22 00:31:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 66%|██████▌   | 128/195 [01:14<00:12,  5.32it/s]
 67%|██████▋   | 131/195 [01:14<00:09,  6.50it/s]
                                                 
[2024-05-22 00:31:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 67%|██████▋   | 131/195 [01:14<00:09,  6.50it/s]
 68%|██████▊   | 132/195 [01:15<00:12,  4.89it/s]
                                                 
[2024-05-22 00:31:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 68%|██████▊   | 132/195 [01:15<00:12,  4.89it/s]
                                                 
[2024-05-22 00:31:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 68%|██████▊   | 132/195 [01:15<00:12,  4.89it/s]
 69%|██████▊   | 134/195 [01:15<00:11,  5.50it/s]
                                                 
[2024-05-22 00:31:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 69%|██████▊   | 134/195 [01:15<00:11,  5.50it/s]
                                                 
[2024-05-22 00:31:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (4096,), dtype: float16

 69%|██████▊   | 134/195 [01:15<00:11,  5.50it/s]
                                                 
[2024-05-22 00:31:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 69%|██████▊   | 134/195 [01:15<00:11,  5.50it/s]
 70%|███████   | 137/195 [01:15<00:08,  6.58it/s]
                                                 
[2024-05-22 00:31:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 70%|███████   | 137/195 [01:15<00:08,  6.58it/s]
 71%|███████   | 138/195 [01:16<00:11,  4.80it/s]
                                                 
[2024-05-22 00:31:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 71%|███████   | 138/195 [01:16<00:11,  4.80it/s]
                                                 
[2024-05-22 00:31:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 71%|███████   | 138/195 [01:16<00:11,  4.80it/s]
 72%|███████▏  | 140/195 [01:16<00:10,  5.42it/s]
                                                 
[2024-05-22 00:31:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 72%|███████▏  | 140/195 [01:16<00:10,  5.42it/s]
                                                 
[2024-05-22 00:31:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (4096,), dtype: float16

 72%|███████▏  | 140/195 [01:16<00:10,  5.42it/s]
                                                 
[2024-05-22 00:31:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 72%|███████▏  | 140/195 [01:16<00:10,  5.42it/s]
 73%|███████▎  | 143/195 [01:16<00:07,  6.51it/s]
                                                 
[2024-05-22 00:31:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 73%|███████▎  | 143/195 [01:16<00:07,  6.51it/s]
 74%|███████▍  | 144/195 [01:17<00:10,  4.87it/s]
                                                 
[2024-05-22 00:31:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 74%|███████▍  | 144/195 [01:17<00:10,  4.87it/s]
                                                 
[2024-05-22 00:31:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 74%|███████▍  | 144/195 [01:17<00:10,  4.87it/s]
 75%|███████▍  | 146/195 [01:17<00:09,  5.41it/s]
                                                 
[2024-05-22 00:31:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 75%|███████▍  | 146/195 [01:17<00:09,  5.41it/s]
                                                 
[2024-05-22 00:31:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (4096,), dtype: float16

 75%|███████▍  | 146/195 [01:17<00:09,  5.41it/s]
                                                 
[2024-05-22 00:31:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 75%|███████▍  | 146/195 [01:17<00:09,  5.41it/s]
 76%|███████▋  | 149/195 [01:17<00:06,  6.58it/s]
                                                 
[2024-05-22 00:31:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 76%|███████▋  | 149/195 [01:17<00:06,  6.58it/s]
 77%|███████▋  | 150/195 [01:18<00:09,  4.82it/s]
                                                 
[2024-05-22 00:31:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 77%|███████▋  | 150/195 [01:18<00:09,  4.82it/s]
                                                 
[2024-05-22 00:31:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 77%|███████▋  | 150/195 [01:18<00:09,  4.82it/s]
 78%|███████▊  | 152/195 [01:18<00:07,  5.44it/s]
                                                 
[2024-05-22 00:31:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 78%|███████▊  | 152/195 [01:18<00:07,  5.44it/s]
                                                 
[2024-05-22 00:31:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (4096,), dtype: float16

 78%|███████▊  | 152/195 [01:18<00:07,  5.44it/s]
                                                 
[2024-05-22 00:31:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 78%|███████▊  | 152/195 [01:18<00:07,  5.44it/s]
 79%|███████▉  | 155/195 [01:18<00:06,  6.53it/s]
                                                 
[2024-05-22 00:31:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 79%|███████▉  | 155/195 [01:19<00:06,  6.53it/s]
 80%|████████  | 156/195 [01:19<00:08,  4.72it/s]
                                                 
[2024-05-22 00:31:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 80%|████████  | 156/195 [01:19<00:08,  4.72it/s]
                                                 
[2024-05-22 00:31:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 80%|████████  | 156/195 [01:19<00:08,  4.72it/s]
 81%|████████  | 158/195 [01:19<00:06,  5.33it/s]
                                                 
[2024-05-22 00:31:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 81%|████████  | 158/195 [01:19<00:06,  5.33it/s]
                                                 
[2024-05-22 00:31:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (4096,), dtype: float16

 81%|████████  | 158/195 [01:19<00:06,  5.33it/s]
                                                 
[2024-05-22 00:31:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 81%|████████  | 158/195 [01:19<00:06,  5.33it/s]
 83%|████████▎ | 161/195 [01:20<00:05,  6.51it/s]
                                                 
[2024-05-22 00:31:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 83%|████████▎ | 161/195 [01:20<00:05,  6.51it/s]
 83%|████████▎ | 162/195 [01:20<00:06,  4.83it/s]
                                                 
[2024-05-22 00:31:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 83%|████████▎ | 162/195 [01:20<00:06,  4.83it/s]
                                                 
[2024-05-22 00:31:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 83%|████████▎ | 162/195 [01:20<00:06,  4.83it/s]
 84%|████████▍ | 164/195 [01:20<00:05,  5.43it/s]
                                                 
[2024-05-22 00:31:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 84%|████████▍ | 164/195 [01:20<00:05,  5.43it/s]
                                                 
[2024-05-22 00:31:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (4096,), dtype: float16

 84%|████████▍ | 164/195 [01:20<00:05,  5.43it/s]
                                                 
[2024-05-22 00:31:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 84%|████████▍ | 164/195 [01:20<00:05,  5.43it/s]
 86%|████████▌ | 167/195 [01:21<00:04,  6.52it/s]
                                                 
[2024-05-22 00:31:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 86%|████████▌ | 167/195 [01:21<00:04,  6.52it/s]
 86%|████████▌ | 168/195 [01:21<00:05,  4.74it/s]
                                                 
[2024-05-22 00:31:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 86%|████████▌ | 168/195 [01:21<00:05,  4.74it/s]
                                                 
[2024-05-22 00:31:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 86%|████████▌ | 168/195 [01:21<00:05,  4.74it/s]
 87%|████████▋ | 170/195 [01:21<00:04,  5.35it/s]
                                                 
[2024-05-22 00:31:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 87%|████████▋ | 170/195 [01:21<00:04,  5.35it/s]
                                                 
[2024-05-22 00:31:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (4096,), dtype: float16

 87%|████████▋ | 170/195 [01:21<00:04,  5.35it/s]
                                                 
[2024-05-22 00:31:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 87%|████████▋ | 170/195 [01:22<00:04,  5.35it/s]
 89%|████████▊ | 173/195 [01:22<00:03,  6.53it/s]
                                                 
[2024-05-22 00:31:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 89%|████████▊ | 173/195 [01:22<00:03,  6.53it/s]
 89%|████████▉ | 174/195 [01:22<00:04,  4.84it/s]
                                                 
[2024-05-22 00:31:34] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 89%|████████▉ | 174/195 [01:22<00:04,  4.84it/s]
                                                 
[2024-05-22 00:31:34] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 89%|████████▉ | 174/195 [01:22<00:04,  4.84it/s]
 90%|█████████ | 176/195 [01:22<00:03,  5.38it/s]
                                                 
[2024-05-22 00:31:34] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 90%|█████████ | 176/195 [01:22<00:03,  5.38it/s]
                                                 
[2024-05-22 00:31:34] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (4096,), dtype: float16

 90%|█████████ | 176/195 [01:23<00:03,  5.38it/s]
                                                 
[2024-05-22 00:31:34] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 90%|█████████ | 176/195 [01:23<00:03,  5.38it/s]
 92%|█████████▏| 179/195 [01:23<00:02,  6.56it/s]
                                                 
[2024-05-22 00:31:34] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 92%|█████████▏| 179/195 [01:23<00:02,  6.56it/s]
 92%|█████████▏| 180/195 [01:23<00:03,  4.82it/s]
                                                 
[2024-05-22 00:31:35] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 92%|█████████▏| 180/195 [01:23<00:03,  4.82it/s]
                                                 
[2024-05-22 00:31:35] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 92%|█████████▏| 180/195 [01:23<00:03,  4.82it/s]
 93%|█████████▎| 182/195 [01:24<00:02,  5.43it/s]
                                                 
[2024-05-22 00:31:35] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 93%|█████████▎| 182/195 [01:24<00:02,  5.43it/s]
                                                 
[2024-05-22 00:31:35] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (4096,), dtype: float16

 93%|█████████▎| 182/195 [01:24<00:02,  5.43it/s]
                                                 
[2024-05-22 00:31:35] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 93%|█████████▎| 182/195 [01:24<00:02,  5.43it/s]
 95%|█████████▍| 185/195 [01:24<00:01,  5.69it/s]
                                                 
[2024-05-22 00:31:35] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 95%|█████████▍| 185/195 [01:24<00:01,  5.69it/s]
 95%|█████████▌| 186/195 [01:25<00:02,  4.42it/s]
                                                 
[2024-05-22 00:31:36] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 95%|█████████▌| 186/195 [01:25<00:02,  4.42it/s]
                                                 
[2024-05-22 00:31:36] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 95%|█████████▌| 186/195 [01:25<00:02,  4.42it/s]
 96%|█████████▋| 188/195 [01:25<00:01,  5.07it/s]
                                                 
[2024-05-22 00:31:36] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 96%|█████████▋| 188/195 [01:25<00:01,  5.07it/s]
                                                 
[2024-05-22 00:31:36] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (4096,), dtype: float16

 96%|█████████▋| 188/195 [01:25<00:01,  5.07it/s]
                                                 
[2024-05-22 00:31:36] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.mlp.down_proj.weight", shape: (4096, 11008), dtype: float16

 96%|█████████▋| 188/195 [01:25<00:01,  5.07it/s]
 98%|█████████▊| 191/195 [01:25<00:00,  6.28it/s]
                                                 
[2024-05-22 00:31:37] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.mlp.gate_up_proj.weight", shape: (22016, 4096), dtype: float16

 98%|█████████▊| 191/195 [01:25<00:00,  6.28it/s]
 98%|█████████▊| 192/195 [01:26<00:00,  4.79it/s]
                                                 
[2024-05-22 00:31:37] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (4096,), dtype: float16

 98%|█████████▊| 192/195 [01:26<00:00,  4.79it/s]
                                                 
[2024-05-22 00:31:37] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.self_attn.qkv_proj.weight", shape: (12288, 4096), dtype: float16

 98%|█████████▊| 192/195 [01:26<00:00,  4.79it/s]
 99%|█████████▉| 194/195 [01:26<00:00,  5.34it/s]
                                                 
[2024-05-22 00:31:37] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16

 99%|█████████▉| 194/195 [01:26<00:00,  5.34it/s]
100%|██████████| 195/195 [01:26<00:00,  2.26it/s]
[2024-05-22 00:31:37] INFO huggingface_loader.py:196: Unloading HF weight file: /models/Llama-2-7b-chat-hf/pytorch_model-00001-of-00002.bin
[2024-05-22 00:31:38] INFO stats.py:76: Time usage: HF loading: 44.115 sec; Pre-quantization mapping: 7.475 sec; Quantization: 0.000 sec
[2024-05-22 00:31:38] INFO stats.py:90: RAM usage: Peak RAM: 9.291 GB. Total bytes loaded from disk: 12.551 GB
[2024-05-22 00:31:38] INFO convert_weight.py:155: Parameter size after quantization: 12.551 GB
[2024-05-22 00:31:38] INFO convert_weight.py:160: Total parameters: 6,738,415,616
[2024-05-22 00:31:38] INFO convert_weight.py:161: Bits per parameter: 16.000
[2024-05-22 00:31:38] INFO convert_weight.py:166: Saved to directory: /tmp/tmp8ew5r2yr

All finished, 131 total shards committed, record saved to /tmp/tmp8ew5r2yr/ndarray-cache.json