/home/msyu/workspace/venv/bin/python -m mlc_llm gen_config /tmp/tmpy7oe9l51/repo --quantization q0f16 --conv-template phi-3 --output /tmp/tmpg82xy6xr
[2024-05-08 13:36:57] INFO auto_config.py:115: Found model configuration: /tmp/tmpy7oe9l51/repo/config.json
[2024-05-08 13:36:57] INFO auto_config.py:153: Found model type: phi3. Use `--model-type` to override.
[2024-05-08 13:36:57] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (4096)
[2024-05-08 13:36:57] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048
[2024-05-08 13:36:57] INFO config.py:106: Overriding max_batch_size from 1 to 80
[2024-05-08 13:36:57] INFO gen_config.py:255: [generation_config.json] Setting bos_token_id: 1
[2024-05-08 13:36:57] INFO gen_config.py:255: [generation_config.json] Setting eos_token_id: [32000, 32001, 32007]
[2024-05-08 13:36:57] INFO gen_config.py:255: [generation_config.json] Setting pad_token_id: 32000
[2024-05-08 13:36:57] INFO gen_config.py:267: Found tokenizer config: /tmp/tmpy7oe9l51/repo/tokenizer.model. Copying to /tmp/tmpg82xy6xr/tokenizer.model
[2024-05-08 13:36:57] INFO gen_config.py:267: Found tokenizer config: /tmp/tmpy7oe9l51/repo/tokenizer.json. Copying to /tmp/tmpg82xy6xr/tokenizer.json
[2024-05-08 13:36:57] INFO gen_config.py:269: Not found tokenizer config: /tmp/tmpy7oe9l51/repo/vocab.json
[2024-05-08 13:36:57] INFO gen_config.py:269: Not found tokenizer config: /tmp/tmpy7oe9l51/repo/merges.txt
[2024-05-08 13:36:57] INFO gen_config.py:267: Found tokenizer config: /tmp/tmpy7oe9l51/repo/added_tokens.json. Copying to /tmp/tmpg82xy6xr/added_tokens.json
[2024-05-08 13:36:57] INFO gen_config.py:267: Found tokenizer config: /tmp/tmpy7oe9l51/repo/tokenizer_config.json. Copying to /tmp/tmpg82xy6xr/tokenizer_config.json
[2024-05-08 13:36:57] INFO gen_config.py:80: [System default] Setting temperature: 0.7
[2024-05-08 13:36:57] INFO gen_config.py:80: [System default] Setting presence_penalty: 0.0
[2024-05-08 13:36:57] INFO gen_config.py:80: [System default] Setting frequency_penalty: 0.0
[2024-05-08 13:36:57] INFO gen_config.py:80: [System default] Setting repetition_penalty: 1.0
[2024-05-08 13:36:57] INFO gen_config.py:80: [System default] Setting top_p: 0.95
[2024-05-08 13:36:57] INFO gen_config.py:80: [System default] Setting mean_gen_len: 128
[2024-05-08 13:36:57] INFO gen_config.py:80: [System default] Setting max_gen_len: 512
[2024-05-08 13:36:57] INFO gen_config.py:80: [System default] Setting shift_fill_factor: 0.3
[2024-05-08 13:36:57] INFO gen_config.py:335: Dumping configuration file to: /tmp/tmpg82xy6xr/mlc-chat-config.json
/home/msyu/workspace/venv/bin/python -m mlc_llm convert_weight /tmp/tmpy7oe9l51/repo --quantization q0f16 --source-format auto --output /tmp/tmpg82xy6xr
[2024-05-08 13:36:58] INFO auto_config.py:115: Found model configuration: /tmp/tmpy7oe9l51/repo/config.json
[2024-05-08 13:36:59] INFO auto_device.py:79: Found device: cuda:0
[2024-05-08 13:36:59] INFO auto_device.py:88: Not found device: rocm:0
[2024-05-08 13:37:00] INFO auto_device.py:88: Not found device: metal:0
[2024-05-08 13:37:01] INFO auto_device.py:88: Not found device: vulkan:0
[2024-05-08 13:37:01] INFO auto_device.py:79: Found device: opencl:0
[2024-05-08 13:37:01] INFO auto_device.py:35: Using device: cuda:0
[2024-05-08 13:37:01] INFO auto_weight.py:70: Finding weights in: /tmp/tmpy7oe9l51/repo
[2024-05-08 13:37:01] INFO auto_weight.py:136: Not found Huggingface PyTorch
[2024-05-08 13:37:01] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: /tmp/tmpy7oe9l51/repo/model.safetensors.index.json
[2024-05-08 13:37:01] INFO auto_weight.py:106: Using source weight configuration: /tmp/tmpy7oe9l51/repo/model.safetensors.index.json. Use `--source` to override.
[2024-05-08 13:37:01] INFO auto_weight.py:110: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-05-08 13:37:01] INFO auto_config.py:153: Found model type: phi3. Use `--model-type` to override.
[2024-05-08 13:37:01] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (4096)
[2024-05-08 13:37:01] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048
Weight conversion with arguments:
  --config          /tmp/tmpy7oe9l51/repo/config.json
  --quantization    NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16')
  --model-type      phi3
  --device          cuda:0
  --source          /tmp/tmpy7oe9l51/repo/model.safetensors.index.json
  --source-format   huggingface-safetensor
  --output          /tmp/tmpg82xy6xr
Start storing to cache /tmp/tmpg82xy6xr

  0%|          | 0/195 [00:00<?, ?it/s]
                                       
[2024-05-08 13:37:03] INFO huggingface_loader.py:184: Loading HF parameters from: /tmp/tmpy7oe9l51/repo/model-00002-of-00002.safetensors

  0%|          | 0/195 [00:00<?, ?it/s]
                                       
[2024-05-08 13:37:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "lm_head.weight", shape: (32064, 3072), dtype: float16

  0%|          | 0/195 [00:00<?, ?it/s]
  1%|          | 1/195 [00:01<04:13,  1.31s/it]
                                               
[2024-05-08 13:37:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.ln.weight", shape: (3072,), dtype: float16

  1%|          | 1/195 [00:01<04:13,  1.31s/it]
                                               
[2024-05-08 13:37:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

  1%|          | 1/195 [00:01<04:13,  1.31s/it]
  2%|▏         | 3/195 [00:01<01:15,  2.54it/s]
                                               
[2024-05-08 13:37:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

  2%|▏         | 3/195 [00:01<01:15,  2.54it/s]
  2%|▏         | 4/195 [00:01<01:07,  2.82it/s]
                                               
[2024-05-08 13:37:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.post_attention_layernorm.weight", shape: (3072,), dtype: float16

  2%|▏         | 4/195 [00:01<01:07,  2.82it/s]
                                               
[2024-05-08 13:37:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

  2%|▏         | 4/195 [00:01<01:07,  2.82it/s]
  3%|▎         | 6/195 [00:01<00:41,  4.57it/s]
                                               
[2024-05-08 13:37:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.ln.weight", shape: (3072,), dtype: float16

  3%|▎         | 6/195 [00:01<00:41,  4.57it/s]
                                               
[2024-05-08 13:37:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

  3%|▎         | 6/195 [00:01<00:41,  4.57it/s]
  4%|▍         | 8/195 [00:02<00:29,  6.36it/s]
                                               
[2024-05-08 13:37:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

  4%|▍         | 8/195 [00:02<00:29,  6.36it/s]
                                               
[2024-05-08 13:37:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.post_attention_layernorm.weight", shape: (3072,), dtype: float16

  4%|▍         | 8/195 [00:02<00:29,  6.36it/s]
  5%|▌         | 10/195 [00:02<00:28,  6.56it/s]
                                                
[2024-05-08 13:37:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

  5%|▌         | 10/195 [00:02<00:28,  6.56it/s]
                                                
[2024-05-08 13:37:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

  5%|▌         | 10/195 [00:02<00:28,  6.56it/s]
  6%|▌         | 12/195 [00:02<00:24,  7.54it/s]
                                                
[2024-05-08 13:37:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.ln.weight", shape: (3072,), dtype: float16

  6%|▌         | 12/195 [00:02<00:24,  7.54it/s]
                                                
[2024-05-08 13:37:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

  6%|▌         | 12/195 [00:02<00:24,  7.54it/s]
  7%|▋         | 14/195 [00:02<00:20,  8.89it/s]
                                                
[2024-05-08 13:37:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

  7%|▋         | 14/195 [00:02<00:20,  8.89it/s]
                                                
[2024-05-08 13:37:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.post_attention_layernorm.weight", shape: (3072,), dtype: float16

  7%|▋         | 14/195 [00:02<00:20,  8.89it/s]
  8%|▊         | 16/195 [00:02<00:21,  8.16it/s]
                                                
[2024-05-08 13:37:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

  8%|▊         | 16/195 [00:02<00:21,  8.16it/s]
                                                
[2024-05-08 13:37:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

  8%|▊         | 16/195 [00:03<00:21,  8.16it/s]
  9%|▉         | 18/195 [00:03<00:20,  8.55it/s]
                                                
[2024-05-08 13:37:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.ln.weight", shape: (3072,), dtype: float16

  9%|▉         | 18/195 [00:03<00:20,  8.55it/s]
                                                
[2024-05-08 13:37:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

  9%|▉         | 18/195 [00:03<00:20,  8.55it/s]
 10%|█         | 20/195 [00:03<00:18,  9.72it/s]
                                                
[2024-05-08 13:37:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 10%|█         | 20/195 [00:03<00:18,  9.72it/s]
                                                
[2024-05-08 13:37:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 10%|█         | 20/195 [00:03<00:18,  9.72it/s]
 11%|█▏        | 22/195 [00:03<00:19,  8.66it/s]
                                                
[2024-05-08 13:37:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 11%|█▏        | 22/195 [00:03<00:19,  8.66it/s]
                                                
[2024-05-08 13:37:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 11%|█▏        | 22/195 [00:03<00:19,  8.66it/s]
 12%|█▏        | 24/195 [00:03<00:19,  8.96it/s]
                                                
[2024-05-08 13:37:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.ln.weight", shape: (3072,), dtype: float16

 12%|█▏        | 24/195 [00:03<00:19,  8.96it/s]
                                                
[2024-05-08 13:37:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 12%|█▏        | 24/195 [00:03<00:19,  8.96it/s]
 13%|█▎        | 26/195 [00:03<00:16, 10.09it/s]
                                                
[2024-05-08 13:37:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 13%|█▎        | 26/195 [00:04<00:16, 10.09it/s]
                                                
[2024-05-08 13:37:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 13%|█▎        | 26/195 [00:04<00:16, 10.09it/s]
 14%|█▍        | 28/195 [00:04<00:18,  8.95it/s]
                                                
[2024-05-08 13:37:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 14%|█▍        | 28/195 [00:04<00:18,  8.95it/s]
                                                
[2024-05-08 13:37:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 14%|█▍        | 28/195 [00:04<00:18,  8.95it/s]
 15%|█▌        | 30/195 [00:04<00:17,  9.18it/s]
                                                
[2024-05-08 13:37:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.ln.weight", shape: (3072,), dtype: float16

 15%|█▌        | 30/195 [00:04<00:17,  9.18it/s]
                                                
[2024-05-08 13:37:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 15%|█▌        | 30/195 [00:04<00:17,  9.18it/s]
 16%|█▋        | 32/195 [00:04<00:15, 10.29it/s]
                                                
[2024-05-08 13:37:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 16%|█▋        | 32/195 [00:04<00:15, 10.29it/s]
                                                
[2024-05-08 13:37:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 16%|█▋        | 32/195 [00:04<00:15, 10.29it/s]
 17%|█▋        | 34/195 [00:04<00:17,  9.06it/s]
                                                
[2024-05-08 13:37:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 17%|█▋        | 34/195 [00:04<00:17,  9.06it/s]
                                                
[2024-05-08 13:37:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 17%|█▋        | 34/195 [00:04<00:17,  9.06it/s]
 18%|█▊        | 36/195 [00:05<00:17,  9.26it/s]
                                                
[2024-05-08 13:37:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.ln.weight", shape: (3072,), dtype: float16

 18%|█▊        | 36/195 [00:05<00:17,  9.26it/s]
                                                
[2024-05-08 13:37:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 18%|█▊        | 36/195 [00:05<00:17,  9.26it/s]
 19%|█▉        | 38/195 [00:05<00:15, 10.35it/s]
                                                
[2024-05-08 13:37:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 19%|█▉        | 38/195 [00:05<00:15, 10.35it/s]
                                                
[2024-05-08 13:37:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 19%|█▉        | 38/195 [00:05<00:15, 10.35it/s]
 21%|██        | 40/195 [00:05<00:17,  9.10it/s]
                                                
[2024-05-08 13:37:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 21%|██        | 40/195 [00:05<00:17,  9.10it/s]
                                                
[2024-05-08 13:37:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 21%|██        | 40/195 [00:05<00:17,  9.10it/s]
 22%|██▏       | 42/195 [00:05<00:16,  9.29it/s]
                                                
[2024-05-08 13:37:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.ln.weight", shape: (3072,), dtype: float16

 22%|██▏       | 42/195 [00:05<00:16,  9.29it/s]
                                                
[2024-05-08 13:37:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 22%|██▏       | 42/195 [00:05<00:16,  9.29it/s]
 23%|██▎       | 44/195 [00:05<00:14, 10.37it/s]
                                                
[2024-05-08 13:37:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 23%|██▎       | 44/195 [00:05<00:14, 10.37it/s]
                                                
[2024-05-08 13:37:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 23%|██▎       | 44/195 [00:06<00:14, 10.37it/s]
 24%|██▎       | 46/195 [00:06<00:16,  9.11it/s]
                                                
[2024-05-08 13:37:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 24%|██▎       | 46/195 [00:06<00:16,  9.11it/s]
                                                
[2024-05-08 13:37:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 24%|██▎       | 46/195 [00:06<00:16,  9.11it/s]
 25%|██▍       | 48/195 [00:06<00:15,  9.29it/s]
                                                
[2024-05-08 13:37:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.ln.weight", shape: (3072,), dtype: float16

 25%|██▍       | 48/195 [00:06<00:15,  9.29it/s]
                                                
[2024-05-08 13:37:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 25%|██▍       | 48/195 [00:06<00:15,  9.29it/s]
 26%|██▌       | 50/195 [00:06<00:13, 10.37it/s]
                                                
[2024-05-08 13:37:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 26%|██▌       | 50/195 [00:06<00:13, 10.37it/s]
                                                
[2024-05-08 13:37:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 26%|██▌       | 50/195 [00:06<00:13, 10.37it/s]
 27%|██▋       | 52/195 [00:06<00:15,  9.12it/s]
                                                
[2024-05-08 13:37:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 27%|██▋       | 52/195 [00:06<00:15,  9.12it/s]
                                                
[2024-05-08 13:37:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 27%|██▋       | 52/195 [00:06<00:15,  9.12it/s]
 28%|██▊       | 54/195 [00:06<00:15,  9.31it/s]
                                                
[2024-05-08 13:37:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.ln.weight", shape: (3072,), dtype: float16

 28%|██▊       | 54/195 [00:06<00:15,  9.31it/s]
                                                
[2024-05-08 13:37:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 28%|██▊       | 54/195 [00:06<00:15,  9.31it/s]
 29%|██▊       | 56/195 [00:07<00:13, 10.39it/s]
                                                
[2024-05-08 13:37:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 29%|██▊       | 56/195 [00:07<00:13, 10.39it/s]
                                                
[2024-05-08 13:37:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 29%|██▊       | 56/195 [00:07<00:13, 10.39it/s]
 30%|██▉       | 58/195 [00:07<00:15,  9.12it/s]
                                                
[2024-05-08 13:37:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 30%|██▉       | 58/195 [00:07<00:15,  9.12it/s]
                                                
[2024-05-08 13:37:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 30%|██▉       | 58/195 [00:07<00:15,  9.12it/s]
 31%|███       | 60/195 [00:07<00:14,  9.31it/s]
                                                
[2024-05-08 13:37:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.ln.weight", shape: (3072,), dtype: float16

 31%|███       | 60/195 [00:07<00:14,  9.31it/s]
                                                
[2024-05-08 13:37:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 31%|███       | 60/195 [00:07<00:14,  9.31it/s]
 32%|███▏      | 62/195 [00:07<00:12, 10.38it/s]
                                                
[2024-05-08 13:37:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 32%|███▏      | 62/195 [00:07<00:12, 10.38it/s]
                                                
[2024-05-08 13:37:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 32%|███▏      | 62/195 [00:07<00:12, 10.38it/s]
 33%|███▎      | 64/195 [00:07<00:14,  9.13it/s]
                                                
[2024-05-08 13:37:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 33%|███▎      | 64/195 [00:07<00:14,  9.13it/s]
                                                
[2024-05-08 13:37:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 33%|███▎      | 64/195 [00:08<00:14,  9.13it/s]
 34%|███▍      | 66/195 [00:08<00:13,  9.31it/s]
                                                
[2024-05-08 13:37:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.norm.weight", shape: (3072,), dtype: float16

 34%|███▍      | 66/195 [00:08<00:13,  9.31it/s]
                                                
[2024-05-08 13:37:11] INFO huggingface_loader.py:196: Unloading HF weight file: /tmp/tmpy7oe9l51/repo/model-00002-of-00002.safetensors

 34%|███▍      | 66/195 [00:08<00:13,  9.31it/s]
                                                
[2024-05-08 13:37:11] INFO huggingface_loader.py:184: Loading HF parameters from: /tmp/tmpy7oe9l51/repo/model-00001-of-00002.safetensors

 34%|███▍      | 66/195 [00:08<00:13,  9.31it/s]
                                                
[2024-05-08 13:37:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.embd.weight", shape: (32064, 3072), dtype: float16

 34%|███▍      | 66/195 [00:08<00:13,  9.31it/s]
 35%|███▍      | 68/195 [00:09<00:30,  4.23it/s]
                                                
[2024-05-08 13:37:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.ln.weight", shape: (3072,), dtype: float16

 35%|███▍      | 68/195 [00:09<00:30,  4.23it/s]
                                                
[2024-05-08 13:37:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 35%|███▍      | 68/195 [00:09<00:30,  4.23it/s]
 36%|███▌      | 70/195 [00:09<00:23,  5.34it/s]
                                                
[2024-05-08 13:37:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 36%|███▌      | 70/195 [00:09<00:23,  5.34it/s]
 36%|███▋      | 71/195 [00:09<00:25,  4.93it/s]
                                                
[2024-05-08 13:37:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 36%|███▋      | 71/195 [00:09<00:25,  4.93it/s]
                                                
[2024-05-08 13:37:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 36%|███▋      | 71/195 [00:09<00:25,  4.93it/s]
                                                
[2024-05-08 13:37:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 36%|███▋      | 71/195 [00:09<00:25,  4.93it/s]
 38%|███▊      | 74/195 [00:09<00:17,  6.86it/s]
                                                
[2024-05-08 13:37:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.ln.weight", shape: (3072,), dtype: float16

 38%|███▊      | 74/195 [00:09<00:17,  6.86it/s]
                                                
[2024-05-08 13:37:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 38%|███▊      | 74/195 [00:09<00:17,  6.86it/s]
 39%|███▉      | 76/195 [00:10<00:14,  8.09it/s]
                                                
[2024-05-08 13:37:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 39%|███▉      | 76/195 [00:10<00:14,  8.09it/s]
                                                
[2024-05-08 13:37:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 39%|███▉      | 76/195 [00:10<00:14,  8.09it/s]
 40%|████      | 78/195 [00:10<00:15,  7.41it/s]
                                                
[2024-05-08 13:37:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 40%|████      | 78/195 [00:10<00:15,  7.41it/s]
                                                
[2024-05-08 13:37:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 40%|████      | 78/195 [00:10<00:15,  7.41it/s]
 41%|████      | 80/195 [00:10<00:14,  7.92it/s]
                                                
[2024-05-08 13:37:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.ln.weight", shape: (3072,), dtype: float16

 41%|████      | 80/195 [00:10<00:14,  7.92it/s]
                                                
[2024-05-08 13:37:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 41%|████      | 80/195 [00:10<00:14,  7.92it/s]
 42%|████▏     | 82/195 [00:10<00:12,  9.07it/s]
                                                
[2024-05-08 13:37:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 42%|████▏     | 82/195 [00:10<00:12,  9.07it/s]
                                                
[2024-05-08 13:37:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 42%|████▏     | 82/195 [00:10<00:12,  9.07it/s]
 43%|████▎     | 84/195 [00:10<00:13,  8.31it/s]
                                                
[2024-05-08 13:37:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 43%|████▎     | 84/195 [00:11<00:13,  8.31it/s]
                                                
[2024-05-08 13:37:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 43%|████▎     | 84/195 [00:11<00:13,  8.31it/s]
 44%|████▍     | 86/195 [00:11<00:12,  8.62it/s]
                                                
[2024-05-08 13:37:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.ln.weight", shape: (3072,), dtype: float16

 44%|████▍     | 86/195 [00:11<00:12,  8.62it/s]
                                                
[2024-05-08 13:37:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 44%|████▍     | 86/195 [00:11<00:12,  8.62it/s]
 45%|████▌     | 88/195 [00:11<00:11,  9.73it/s]
                                                
[2024-05-08 13:37:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 45%|████▌     | 88/195 [00:11<00:11,  9.73it/s]
                                                
[2024-05-08 13:37:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 45%|████▌     | 88/195 [00:11<00:11,  9.73it/s]
 46%|████▌     | 90/195 [00:11<00:12,  8.67it/s]
                                                
[2024-05-08 13:37:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 46%|████▌     | 90/195 [00:11<00:12,  8.67it/s]
                                                
[2024-05-08 13:37:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 46%|████▌     | 90/195 [00:11<00:12,  8.67it/s]
 47%|████▋     | 92/195 [00:11<00:11,  8.97it/s]
                                                
[2024-05-08 13:37:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.ln.weight", shape: (3072,), dtype: float16

 47%|████▋     | 92/195 [00:11<00:11,  8.97it/s]
                                                
[2024-05-08 13:37:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 47%|████▋     | 92/195 [00:11<00:11,  8.97it/s]
 48%|████▊     | 94/195 [00:11<00:10, 10.10it/s]
                                                
[2024-05-08 13:37:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 48%|████▊     | 94/195 [00:12<00:10, 10.10it/s]
                                                
[2024-05-08 13:37:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 48%|████▊     | 94/195 [00:12<00:10, 10.10it/s]
 49%|████▉     | 96/195 [00:12<00:11,  8.98it/s]
                                                
[2024-05-08 13:37:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 49%|████▉     | 96/195 [00:12<00:11,  8.98it/s]
                                                
[2024-05-08 13:37:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 49%|████▉     | 96/195 [00:12<00:11,  8.98it/s]
 50%|█████     | 98/195 [00:12<00:10,  9.20it/s]
                                                
[2024-05-08 13:37:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.ln.weight", shape: (3072,), dtype: float16

 50%|█████     | 98/195 [00:12<00:10,  9.20it/s]
                                                
[2024-05-08 13:37:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 50%|█████     | 98/195 [00:12<00:10,  9.20it/s]
 51%|█████▏    | 100/195 [00:12<00:09, 10.31it/s]
                                                 
[2024-05-08 13:37:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 51%|█████▏    | 100/195 [00:12<00:09, 10.31it/s]
                                                 
[2024-05-08 13:37:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 51%|█████▏    | 100/195 [00:12<00:09, 10.31it/s]
 52%|█████▏    | 102/195 [00:12<00:10,  9.10it/s]
                                                 
[2024-05-08 13:37:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 52%|█████▏    | 102/195 [00:12<00:10,  9.10it/s]
                                                 
[2024-05-08 13:37:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 52%|█████▏    | 102/195 [00:12<00:10,  9.10it/s]
 53%|█████▎    | 104/195 [00:13<00:09,  9.29it/s]
                                                 
[2024-05-08 13:37:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.ln.weight", shape: (3072,), dtype: float16

 53%|█████▎    | 104/195 [00:13<00:09,  9.29it/s]
                                                 
[2024-05-08 13:37:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 53%|█████▎    | 104/195 [00:13<00:09,  9.29it/s]
 54%|█████▍    | 106/195 [00:13<00:08, 10.38it/s]
                                                 
[2024-05-08 13:37:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 54%|█████▍    | 106/195 [00:13<00:08, 10.38it/s]
                                                 
[2024-05-08 13:37:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 54%|█████▍    | 106/195 [00:13<00:08, 10.38it/s]
 55%|█████▌    | 108/195 [00:13<00:09,  9.14it/s]
                                                 
[2024-05-08 13:37:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 55%|█████▌    | 108/195 [00:13<00:09,  9.14it/s]
                                                 
[2024-05-08 13:37:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 55%|█████▌    | 108/195 [00:13<00:09,  9.14it/s]
 56%|█████▋    | 110/195 [00:13<00:09,  9.33it/s]
                                                 
[2024-05-08 13:37:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.ln.weight", shape: (3072,), dtype: float16

 56%|█████▋    | 110/195 [00:13<00:09,  9.33it/s]
                                                 
[2024-05-08 13:37:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 56%|█████▋    | 110/195 [00:13<00:09,  9.33it/s]
 57%|█████▋    | 112/195 [00:13<00:07, 10.41it/s]
                                                 
[2024-05-08 13:37:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 57%|█████▋    | 112/195 [00:13<00:07, 10.41it/s]
                                                 
[2024-05-08 13:37:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 57%|█████▋    | 112/195 [00:14<00:07, 10.41it/s]
 58%|█████▊    | 114/195 [00:14<00:08,  9.15it/s]
                                                 
[2024-05-08 13:37:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 58%|█████▊    | 114/195 [00:14<00:08,  9.15it/s]
                                                 
[2024-05-08 13:37:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 58%|█████▊    | 114/195 [00:14<00:08,  9.15it/s]
 59%|█████▉    | 116/195 [00:14<00:08,  9.34it/s]
                                                 
[2024-05-08 13:37:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.ln.weight", shape: (3072,), dtype: float16

 59%|█████▉    | 116/195 [00:14<00:08,  9.34it/s]
                                                 
[2024-05-08 13:37:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 59%|█████▉    | 116/195 [00:14<00:08,  9.34it/s]
 61%|██████    | 118/195 [00:14<00:07, 10.43it/s]
                                                 
[2024-05-08 13:37:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 61%|██████    | 118/195 [00:14<00:07, 10.43it/s]
                                                 
[2024-05-08 13:37:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 61%|██████    | 118/195 [00:14<00:07, 10.43it/s]
 62%|██████▏   | 120/195 [00:14<00:08,  9.16it/s]
                                                 
[2024-05-08 13:37:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 62%|██████▏   | 120/195 [00:14<00:08,  9.16it/s]
                                                 
[2024-05-08 13:37:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 62%|██████▏   | 120/195 [00:14<00:08,  9.16it/s]
 63%|██████▎   | 122/195 [00:14<00:07,  9.34it/s]
                                                 
[2024-05-08 13:37:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.ln.weight", shape: (3072,), dtype: float16

 63%|██████▎   | 122/195 [00:14<00:07,  9.34it/s]
                                                 
[2024-05-08 13:37:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 63%|██████▎   | 122/195 [00:15<00:07,  9.34it/s]
 64%|██████▎   | 124/195 [00:15<00:06, 10.42it/s]
                                                 
[2024-05-08 13:37:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 64%|██████▎   | 124/195 [00:15<00:06, 10.42it/s]
                                                 
[2024-05-08 13:37:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 64%|██████▎   | 124/195 [00:15<00:06, 10.42it/s]
 65%|██████▍   | 126/195 [00:15<00:07,  9.16it/s]
                                                 
[2024-05-08 13:37:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 65%|██████▍   | 126/195 [00:15<00:07,  9.16it/s]
                                                 
[2024-05-08 13:37:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 65%|██████▍   | 126/195 [00:15<00:07,  9.16it/s]
 66%|██████▌   | 128/195 [00:15<00:07,  9.34it/s]
                                                 
[2024-05-08 13:37:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.ln.weight", shape: (3072,), dtype: float16

 66%|██████▌   | 128/195 [00:15<00:07,  9.34it/s]
                                                 
[2024-05-08 13:37:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 66%|██████▌   | 128/195 [00:15<00:07,  9.34it/s]
 67%|██████▋   | 130/195 [00:15<00:06, 10.43it/s]
                                                 
[2024-05-08 13:37:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 67%|██████▋   | 130/195 [00:15<00:06, 10.43it/s]
                                                 
[2024-05-08 13:37:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 67%|██████▋   | 130/195 [00:16<00:06, 10.43it/s]
 68%|██████▊   | 132/195 [00:16<00:06,  9.16it/s]
                                                 
[2024-05-08 13:37:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 68%|██████▊   | 132/195 [00:16<00:06,  9.16it/s]
                                                 
[2024-05-08 13:37:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 68%|██████▊   | 132/195 [00:16<00:06,  9.16it/s]
 69%|██████▊   | 134/195 [00:16<00:06,  9.33it/s]
                                                 
[2024-05-08 13:37:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.ln.weight", shape: (3072,), dtype: float16

 69%|██████▊   | 134/195 [00:16<00:06,  9.33it/s]
                                                 
[2024-05-08 13:37:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 69%|██████▊   | 134/195 [00:16<00:06,  9.33it/s]
 70%|██████▉   | 136/195 [00:16<00:05, 10.42it/s]
                                                 
[2024-05-08 13:37:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 70%|██████▉   | 136/195 [00:16<00:05, 10.42it/s]
                                                 
[2024-05-08 13:37:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 70%|██████▉   | 136/195 [00:16<00:05, 10.42it/s]
 71%|███████   | 138/195 [00:16<00:06,  9.16it/s]
                                                 
[2024-05-08 13:37:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 71%|███████   | 138/195 [00:16<00:06,  9.16it/s]
                                                 
[2024-05-08 13:37:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 71%|███████   | 138/195 [00:16<00:06,  9.16it/s]
 72%|███████▏  | 140/195 [00:16<00:05,  9.34it/s]
                                                 
[2024-05-08 13:37:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.ln.weight", shape: (3072,), dtype: float16

 72%|███████▏  | 140/195 [00:16<00:05,  9.34it/s]
                                                 
[2024-05-08 13:37:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 72%|███████▏  | 140/195 [00:16<00:05,  9.34it/s]
 73%|███████▎  | 142/195 [00:16<00:05, 10.42it/s]
                                                 
[2024-05-08 13:37:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 73%|███████▎  | 142/195 [00:17<00:05, 10.42it/s]
                                                 
[2024-05-08 13:37:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 73%|███████▎  | 142/195 [00:17<00:05, 10.42it/s]
 74%|███████▍  | 144/195 [00:17<00:05,  9.16it/s]
                                                 
[2024-05-08 13:37:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 74%|███████▍  | 144/195 [00:17<00:05,  9.16it/s]
                                                 
[2024-05-08 13:37:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 74%|███████▍  | 144/195 [00:17<00:05,  9.16it/s]
 75%|███████▍  | 146/195 [00:17<00:05,  9.34it/s]
                                                 
[2024-05-08 13:37:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.ln.weight", shape: (3072,), dtype: float16

 75%|███████▍  | 146/195 [00:17<00:05,  9.34it/s]
                                                 
[2024-05-08 13:37:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 75%|███████▍  | 146/195 [00:17<00:05,  9.34it/s]
 76%|███████▌  | 148/195 [00:17<00:04, 10.42it/s]
                                                 
[2024-05-08 13:37:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 76%|███████▌  | 148/195 [00:17<00:04, 10.42it/s]
                                                 
[2024-05-08 13:37:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 76%|███████▌  | 148/195 [00:17<00:04, 10.42it/s]
 77%|███████▋  | 150/195 [00:17<00:04,  9.16it/s]
                                                 
[2024-05-08 13:37:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 77%|███████▋  | 150/195 [00:17<00:04,  9.16it/s]
                                                 
[2024-05-08 13:37:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 77%|███████▋  | 150/195 [00:17<00:04,  9.16it/s]
 78%|███████▊  | 152/195 [00:18<00:04,  9.33it/s]
                                                 
[2024-05-08 13:37:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 78%|███████▊  | 152/195 [00:18<00:04,  9.33it/s]
                                                 
[2024-05-08 13:37:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.ln.weight", shape: (3072,), dtype: float16

 78%|███████▊  | 152/195 [00:18<00:04,  9.33it/s]
                                                 
[2024-05-08 13:37:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 78%|███████▊  | 152/195 [00:18<00:04,  9.33it/s]
 79%|███████▉  | 155/195 [00:18<00:03, 11.11it/s]
                                                 
[2024-05-08 13:37:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 79%|███████▉  | 155/195 [00:18<00:03, 11.11it/s]
                                                 
[2024-05-08 13:37:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 79%|███████▉  | 155/195 [00:18<00:03, 11.11it/s]
 81%|████████  | 157/195 [00:18<00:03,  9.65it/s]
                                                 
[2024-05-08 13:37:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 81%|████████  | 157/195 [00:18<00:03,  9.65it/s]
                                                 
[2024-05-08 13:37:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 81%|████████  | 157/195 [00:18<00:03,  9.65it/s]
 82%|████████▏ | 159/195 [00:18<00:03,  9.70it/s]
                                                 
[2024-05-08 13:37:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.ln.weight", shape: (3072,), dtype: float16

 82%|████████▏ | 159/195 [00:18<00:03,  9.70it/s]
                                                 
[2024-05-08 13:37:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 82%|████████▏ | 159/195 [00:18<00:03,  9.70it/s]
 83%|████████▎ | 161/195 [00:18<00:03, 10.67it/s]
                                                 
[2024-05-08 13:37:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 83%|████████▎ | 161/195 [00:18<00:03, 10.67it/s]
                                                 
[2024-05-08 13:37:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 83%|████████▎ | 161/195 [00:19<00:03, 10.67it/s]
 84%|████████▎ | 163/195 [00:19<00:03,  9.33it/s]
                                                 
[2024-05-08 13:37:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 84%|████████▎ | 163/195 [00:19<00:03,  9.33it/s]
                                                 
[2024-05-08 13:37:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 84%|████████▎ | 163/195 [00:19<00:03,  9.33it/s]
 85%|████████▍ | 165/195 [00:19<00:03,  9.46it/s]
                                                 
[2024-05-08 13:37:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.ln.weight", shape: (3072,), dtype: float16

 85%|████████▍ | 165/195 [00:19<00:03,  9.46it/s]
                                                 
[2024-05-08 13:37:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 85%|████████▍ | 165/195 [00:19<00:03,  9.46it/s]
 86%|████████▌ | 167/195 [00:19<00:02, 10.51it/s]
                                                 
[2024-05-08 13:37:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 86%|████████▌ | 167/195 [00:19<00:02, 10.51it/s]
                                                 
[2024-05-08 13:37:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 86%|████████▌ | 167/195 [00:19<00:02, 10.51it/s]
 87%|████████▋ | 169/195 [00:19<00:02,  9.22it/s]
                                                 
[2024-05-08 13:37:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 87%|████████▋ | 169/195 [00:19<00:02,  9.22it/s]
                                                 
[2024-05-08 13:37:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 87%|████████▋ | 169/195 [00:19<00:02,  9.22it/s]
 88%|████████▊ | 171/195 [00:20<00:02,  9.38it/s]
                                                 
[2024-05-08 13:37:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.ln.weight", shape: (3072,), dtype: float16

 88%|████████▊ | 171/195 [00:20<00:02,  9.38it/s]
                                                 
[2024-05-08 13:37:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 88%|████████▊ | 171/195 [00:20<00:02,  9.38it/s]
 89%|████████▊ | 173/195 [00:20<00:02, 10.44it/s]
                                                 
[2024-05-08 13:37:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 89%|████████▊ | 173/195 [00:20<00:02, 10.44it/s]
                                                 
[2024-05-08 13:37:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 89%|████████▊ | 173/195 [00:20<00:02, 10.44it/s]
 90%|████████▉ | 175/195 [00:20<00:02,  9.17it/s]
                                                 
[2024-05-08 13:37:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 90%|████████▉ | 175/195 [00:20<00:02,  9.17it/s]
                                                 
[2024-05-08 13:37:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 90%|████████▉ | 175/195 [00:20<00:02,  9.17it/s]
 91%|█████████ | 177/195 [00:20<00:01,  9.34it/s]
                                                 
[2024-05-08 13:37:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.ln.weight", shape: (3072,), dtype: float16

 91%|█████████ | 177/195 [00:20<00:01,  9.34it/s]
                                                 
[2024-05-08 13:37:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 91%|█████████ | 177/195 [00:20<00:01,  9.34it/s]
 92%|█████████▏| 179/195 [00:20<00:01, 10.42it/s]
                                                 
[2024-05-08 13:37:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 92%|█████████▏| 179/195 [00:20<00:01, 10.42it/s]
                                                 
[2024-05-08 13:37:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 92%|█████████▏| 179/195 [00:21<00:01, 10.42it/s]
 93%|█████████▎| 181/195 [00:21<00:01,  9.15it/s]
                                                 
[2024-05-08 13:37:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 93%|█████████▎| 181/195 [00:21<00:01,  9.15it/s]
                                                 
[2024-05-08 13:37:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 93%|█████████▎| 181/195 [00:21<00:01,  9.15it/s]
 94%|█████████▍| 183/195 [00:21<00:01,  9.33it/s]
                                                 
[2024-05-08 13:37:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.ln.weight", shape: (3072,), dtype: float16

 94%|█████████▍| 183/195 [00:21<00:01,  9.33it/s]
                                                 
[2024-05-08 13:37:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 94%|█████████▍| 183/195 [00:21<00:01,  9.33it/s]
 95%|█████████▍| 185/195 [00:21<00:00, 10.41it/s]
                                                 
[2024-05-08 13:37:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 95%|█████████▍| 185/195 [00:21<00:00, 10.41it/s]
                                                 
[2024-05-08 13:37:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 95%|█████████▍| 185/195 [00:21<00:00, 10.41it/s]
 96%|█████████▌| 187/195 [00:21<00:00,  9.14it/s]
                                                 
[2024-05-08 13:37:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 96%|█████████▌| 187/195 [00:21<00:00,  9.14it/s]
                                                 
[2024-05-08 13:37:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 96%|█████████▌| 187/195 [00:21<00:00,  9.14it/s]
 97%|█████████▋| 189/195 [00:21<00:00,  9.33it/s]
                                                 
[2024-05-08 13:37:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.ln.weight", shape: (3072,), dtype: float16

 97%|█████████▋| 189/195 [00:21<00:00,  9.33it/s]
                                                 
[2024-05-08 13:37:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.mlp.down_proj.weight", shape: (3072, 8192), dtype: float16

 97%|█████████▋| 189/195 [00:21<00:00,  9.33it/s]
 98%|█████████▊| 191/195 [00:22<00:00, 10.40it/s]
                                                 
[2024-05-08 13:37:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float16

 98%|█████████▊| 191/195 [00:22<00:00, 10.40it/s]
                                                 
[2024-05-08 13:37:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.post_attention_layernorm.weight", shape: (3072,), dtype: float16

 98%|█████████▊| 191/195 [00:22<00:00, 10.40it/s]
 99%|█████████▉| 193/195 [00:22<00:00,  9.13it/s]
                                                 
[2024-05-08 13:37:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.mixer.out_proj.weight", shape: (3072, 3072), dtype: float16

 99%|█████████▉| 193/195 [00:22<00:00,  9.13it/s]
                                                 
[2024-05-08 13:37:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float16

 99%|█████████▉| 193/195 [00:22<00:00,  9.13it/s]
100%|██████████| 195/195 [00:22<00:00,  9.30it/s]
100%|██████████| 195/195 [00:22<00:00,  8.66it/s]
[2024-05-08 13:37:25] INFO huggingface_loader.py:196: Unloading HF weight file: /tmp/tmpy7oe9l51/repo/model-00001-of-00002.safetensors
[2024-05-08 13:37:25] INFO stats.py:76: Time usage: HF loading: 1.450 sec; Pre-quantization mapping: 5.723 sec; Quantization: 0.000 sec
[2024-05-08 13:37:25] INFO stats.py:90: RAM usage: Peak RAM: 9.262 GB. Total bytes loaded from disk: 14.235 GB
[2024-05-08 13:37:25] INFO convert_weight.py:155: Parameter size after quantization: 7.117 GB
[2024-05-08 13:37:25] INFO convert_weight.py:160: Total parameters: 3,821,079,552
[2024-05-08 13:37:25] INFO convert_weight.py:161: Bits per parameter: 16.000
[2024-05-08 13:37:25] INFO convert_weight.py:166: Saved to directory: /tmp/tmpg82xy6xr

All finished, 130 total shards committed, record saved to /tmp/tmpg82xy6xr/ndarray-cache.json