/usr/bin/python3 -m mlc_llm gen_config dist/models/stablelm-2-zephyr-1_6b --quantization q0f16 --conv-template stablelm-2 --output /tmp/tmphm3edhbu --context-window-size 4096
[2024-05-24 17:02:51] INFO auto_config.py:115: Found model configuration: dist/models/stablelm-2-zephyr-1_6b/config.json
[2024-05-24 17:02:51] INFO auto_config.py:153: Found model type: stablelm. Use `--model-type` to override.
[2024-05-24 17:02:51] INFO stablelm_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (4096)
[2024-05-24 17:02:51] INFO stablelm_model.py:66: prefill_chunk_size defaults to 2048
[2024-05-24 17:02:51] INFO config.py:106: Overriding context_window_size from 4096 to 4096
[2024-05-24 17:02:51] INFO config.py:106: Overriding max_batch_size from 1 to 80
[2024-05-24 17:02:51] INFO gen_config.py:255: [generation_config.json] Setting bos_token_id: 100257
[2024-05-24 17:02:51] INFO gen_config.py:255: [generation_config.json] Setting eos_token_id: 100257
[2024-05-24 17:02:51] INFO gen_config.py:269: Not found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/tokenizer.model
[2024-05-24 17:02:51] INFO gen_config.py:267: Found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/tokenizer.json. Copying to /tmp/tmphm3edhbu/tokenizer.json
[2024-05-24 17:02:51] INFO gen_config.py:267: Found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/vocab.json. Copying to /tmp/tmphm3edhbu/vocab.json
[2024-05-24 17:02:51] INFO gen_config.py:267: Found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/merges.txt. Copying to /tmp/tmphm3edhbu/merges.txt
[2024-05-24 17:02:51] INFO gen_config.py:269: Not found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/added_tokens.json
[2024-05-24 17:02:51] INFO gen_config.py:267: Found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/tokenizer_config.json. Copying to /tmp/tmphm3edhbu/tokenizer_config.json
[2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting pad_token_id: 0
[2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting temperature: 0.7
[2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting presence_penalty: 0.0
[2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting frequency_penalty: 0.0
[2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting repetition_penalty: 1.0
[2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting top_p: 0.95
[2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting mean_gen_len: 128
[2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting max_gen_len: 512
[2024-05-24 17:02:51] INFO gen_config.py:80: [System default] Setting shift_fill_factor: 0.3
[2024-05-24 17:02:51] INFO gen_config.py:335: Dumping configuration file to: /tmp/tmphm3edhbu/mlc-chat-config.json
/usr/bin/python3 -m mlc_llm convert_weight dist/models/stablelm-2-zephyr-1_6b --quantization q0f16 --source-format auto --output /tmp/tmphm3edhbu
[2024-05-24 17:02:52] INFO auto_config.py:115: Found model configuration: dist/models/stablelm-2-zephyr-1_6b/config.json
[2024-05-24 17:02:54] INFO auto_device.py:79: Found device: cuda:0
[2024-05-24 17:02:55] INFO auto_device.py:88: Not found device: rocm:0
[2024-05-24 17:02:56] INFO auto_device.py:88: Not found device: metal:0
[2024-05-24 17:02:57] INFO auto_device.py:88: Not found device: vulkan:0
[2024-05-24 17:02:58] INFO auto_device.py:88: Not found device: opencl:0
[2024-05-24 17:02:58] INFO auto_device.py:35: Using device: cuda:0
[2024-05-24 17:02:58] INFO auto_weight.py:70: Finding weights in: dist/models/stablelm-2-zephyr-1_6b
[2024-05-24 17:02:58] INFO auto_weight.py:136: Not found Huggingface PyTorch
[2024-05-24 17:02:58] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: dist/models/stablelm-2-zephyr-1_6b/model.safetensors.index.json
[2024-05-24 17:02:58] INFO auto_weight.py:106: Using source weight configuration: dist/models/stablelm-2-zephyr-1_6b/model.safetensors.index.json. Use `--source` to override.
[2024-05-24 17:02:58] INFO auto_weight.py:110: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-05-24 17:02:58] INFO auto_config.py:153: Found model type: stablelm. Use `--model-type` to override.
[2024-05-24 17:02:58] INFO stablelm_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (4096)
[2024-05-24 17:02:58] INFO stablelm_model.py:66: prefill_chunk_size defaults to 2048
Weight conversion with arguments:
  --config          dist/models/stablelm-2-zephyr-1_6b/config.json
  --quantization    NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16')
  --model-type      stablelm
  --device          cuda:0
  --source          dist/models/stablelm-2-zephyr-1_6b/model.safetensors.index.json
  --source-format   huggingface-safetensor
  --output          /tmp/tmphm3edhbu
Start storing to cache /tmp/tmphm3edhbu

  0%|          | 0/220 [00:00<?, ?it/s]
                                       
[2024-05-24 17:03:00] INFO huggingface_loader.py:184: Loading HF parameters from: dist/models/stablelm-2-zephyr-1_6b/model.safetensors

  0%|          | 0/220 [00:00<?, ?it/s]
                                       
[2024-05-24 17:03:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "lm_head.weight", shape: (100352, 2048), dtype: float16

  0%|          | 0/220 [00:03<?, ?it/s]
  0%|          | 1/220 [00:04<17:07,  4.69s/it]
                                               
[2024-05-24 17:03:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.embed_tokens.weight", shape: (100352, 2048), dtype: float16

  0%|          | 1/220 [00:06<17:07,  4.69s/it]
  1%|          | 2/220 [00:07<13:33,  3.73s/it]
                                               
[2024-05-24 17:03:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.input_layernorm.bias", shape: (2048,), dtype: float16

  1%|          | 2/220 [00:07<13:33,  3.73s/it]
                                               
[2024-05-24 17:03:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (2048,), dtype: float16

  1%|          | 2/220 [00:07<13:33,  3.73s/it]
                                               
[2024-05-24 17:03:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

  1%|          | 2/220 [00:07<13:33,  3.73s/it]
                                               
[2024-05-24 17:03:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

  1%|          | 2/220 [00:08<13:33,  3.73s/it]
  3%|▎         | 6/220 [00:08<03:20,  1.07it/s]
                                               
[2024-05-24 17:03:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.bias", shape: (2048,), dtype: float16

  3%|▎         | 6/220 [00:08<03:20,  1.07it/s]
                                               
[2024-05-24 17:03:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (2048,), dtype: float16

  3%|▎         | 6/220 [00:08<03:20,  1.07it/s]
                                               
[2024-05-24 17:03:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

  3%|▎         | 6/220 [00:08<03:20,  1.07it/s]
                                               
[2024-05-24 17:03:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

  3%|▎         | 6/220 [00:08<03:20,  1.07it/s]
  5%|▍         | 10/220 [00:08<01:40,  2.09it/s]
                                                
[2024-05-24 17:03:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

  5%|▍         | 10/220 [00:08<01:40,  2.09it/s]
                                                
[2024-05-24 17:03:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.input_layernorm.bias", shape: (2048,), dtype: float16

  5%|▍         | 10/220 [00:08<01:40,  2.09it/s]
                                                
[2024-05-24 17:03:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (2048,), dtype: float16

  5%|▍         | 10/220 [00:08<01:40,  2.09it/s]
                                                
[2024-05-24 17:03:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

  5%|▍         | 10/220 [00:08<01:40,  2.09it/s]
  6%|▋         | 14/220 [00:08<00:59,  3.47it/s]
                                                
[2024-05-24 17:03:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

  6%|▋         | 14/220 [00:08<00:59,  3.47it/s]
                                                
[2024-05-24 17:03:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.bias", shape: (2048,), dtype: float16

  6%|▋         | 14/220 [00:08<00:59,  3.47it/s]
  7%|▋         | 16/220 [00:08<00:55,  3.68it/s]
                                                
[2024-05-24 17:03:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (2048,), dtype: float16

  7%|▋         | 16/220 [00:08<00:55,  3.68it/s]
                                                
[2024-05-24 17:03:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

  7%|▋         | 16/220 [00:08<00:55,  3.68it/s]
                                                
[2024-05-24 17:03:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

  7%|▋         | 16/220 [00:09<00:55,  3.68it/s]
  9%|▊         | 19/220 [00:09<00:39,  5.12it/s]
                                                
[2024-05-24 17:03:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

  9%|▊         | 19/220 [00:09<00:39,  5.12it/s]
                                                
[2024-05-24 17:03:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.input_layernorm.bias", shape: (2048,), dtype: float16

  9%|▊         | 19/220 [00:09<00:39,  5.12it/s]
                                                
[2024-05-24 17:03:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (2048,), dtype: float16

  9%|▊         | 19/220 [00:09<00:39,  5.12it/s]
                                                
[2024-05-24 17:03:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

  9%|▊         | 19/220 [00:09<00:39,  5.12it/s]
 10%|█         | 23/220 [00:09<00:26,  7.38it/s]
                                                
[2024-05-24 17:03:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 10%|█         | 23/220 [00:09<00:26,  7.38it/s]
                                                
[2024-05-24 17:03:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 10%|█         | 23/220 [00:09<00:26,  7.38it/s]
 11%|█▏        | 25/220 [00:09<00:29,  6.56it/s]
                                                
[2024-05-24 17:03:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 11%|█▏        | 25/220 [00:09<00:29,  6.56it/s]
                                                
[2024-05-24 17:03:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 11%|█▏        | 25/220 [00:09<00:29,  6.56it/s]
                                                
[2024-05-24 17:03:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 11%|█▏        | 25/220 [00:09<00:29,  6.56it/s]
 13%|█▎        | 28/220 [00:09<00:22,  8.46it/s]
                                                
[2024-05-24 17:03:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 13%|█▎        | 28/220 [00:09<00:22,  8.46it/s]
                                                
[2024-05-24 17:03:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.input_layernorm.bias", shape: (2048,), dtype: float16

 13%|█▎        | 28/220 [00:09<00:22,  8.46it/s]
                                                
[2024-05-24 17:03:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (2048,), dtype: float16

 13%|█▎        | 28/220 [00:09<00:22,  8.46it/s]
                                                
[2024-05-24 17:03:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 13%|█▎        | 28/220 [00:10<00:22,  8.46it/s]
 15%|█▍        | 32/220 [00:10<00:19,  9.72it/s]
                                                
[2024-05-24 17:03:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 15%|█▍        | 32/220 [00:10<00:19,  9.72it/s]
                                                
[2024-05-24 17:03:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 15%|█▍        | 32/220 [00:10<00:19,  9.72it/s]
 15%|█▌        | 34/220 [00:10<00:23,  7.88it/s]
                                                
[2024-05-24 17:03:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 15%|█▌        | 34/220 [00:10<00:23,  7.88it/s]
                                                
[2024-05-24 17:03:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 15%|█▌        | 34/220 [00:10<00:23,  7.88it/s]
                                                
[2024-05-24 17:03:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 15%|█▌        | 34/220 [00:10<00:23,  7.88it/s]
 17%|█▋        | 37/220 [00:10<00:18,  9.88it/s]
                                                
[2024-05-24 17:03:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 17%|█▋        | 37/220 [00:10<00:18,  9.88it/s]
                                                
[2024-05-24 17:03:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.input_layernorm.bias", shape: (2048,), dtype: float16

 17%|█▋        | 37/220 [00:10<00:18,  9.88it/s]
                                                
[2024-05-24 17:03:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (2048,), dtype: float16

 17%|█▋        | 37/220 [00:10<00:18,  9.88it/s]
                                                
[2024-05-24 17:03:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 17%|█▋        | 37/220 [00:10<00:18,  9.88it/s]
 19%|█▊        | 41/220 [00:10<00:14, 12.77it/s]
                                                
[2024-05-24 17:03:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 19%|█▊        | 41/220 [00:11<00:14, 12.77it/s]
                                                
[2024-05-24 17:03:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 19%|█▊        | 41/220 [00:11<00:14, 12.77it/s]
 20%|█▉        | 43/220 [00:11<00:17, 10.03it/s]
                                                
[2024-05-24 17:03:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 20%|█▉        | 43/220 [00:11<00:17, 10.03it/s]
                                                
[2024-05-24 17:03:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 20%|█▉        | 43/220 [00:11<00:17, 10.03it/s]
                                                
[2024-05-24 17:03:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 20%|█▉        | 43/220 [00:11<00:17, 10.03it/s]
 21%|██        | 46/220 [00:11<00:13, 12.64it/s]
                                                
[2024-05-24 17:03:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 21%|██        | 46/220 [00:11<00:13, 12.64it/s]
                                                
[2024-05-24 17:03:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.input_layernorm.bias", shape: (2048,), dtype: float16

 21%|██        | 46/220 [00:11<00:13, 12.64it/s]
                                                
[2024-05-24 17:03:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (2048,), dtype: float16

 21%|██        | 46/220 [00:11<00:13, 12.64it/s]
                                                
[2024-05-24 17:03:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 21%|██        | 46/220 [00:11<00:13, 12.64it/s]
 23%|██▎       | 50/220 [00:11<00:10, 16.44it/s]
                                                
[2024-05-24 17:03:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 23%|██▎       | 50/220 [00:11<00:10, 16.44it/s]
                                                
[2024-05-24 17:03:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 23%|██▎       | 50/220 [00:11<00:10, 16.44it/s]
                                                
[2024-05-24 17:03:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 23%|██▎       | 50/220 [00:11<00:10, 16.44it/s]
 24%|██▍       | 53/220 [00:11<00:12, 13.00it/s]
                                                
[2024-05-24 17:03:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 24%|██▍       | 53/220 [00:11<00:12, 13.00it/s]
                                                
[2024-05-24 17:03:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 24%|██▍       | 53/220 [00:11<00:12, 13.00it/s]
                                                
[2024-05-24 17:03:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 24%|██▍       | 53/220 [00:11<00:12, 13.00it/s]
 25%|██▌       | 56/220 [00:11<00:11, 14.10it/s]
                                                
[2024-05-24 17:03:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.input_layernorm.bias", shape: (2048,), dtype: float16

 25%|██▌       | 56/220 [00:11<00:11, 14.10it/s]
                                                
[2024-05-24 17:03:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (2048,), dtype: float16

 25%|██▌       | 56/220 [00:11<00:11, 14.10it/s]
                                                
[2024-05-24 17:03:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 25%|██▌       | 56/220 [00:12<00:11, 14.10it/s]
                                                
[2024-05-24 17:03:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 25%|██▌       | 56/220 [00:12<00:11, 14.10it/s]
 27%|██▋       | 60/220 [00:12<00:13, 11.51it/s]
                                                
[2024-05-24 17:03:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 27%|██▋       | 60/220 [00:12<00:13, 11.51it/s]
                                                
[2024-05-24 17:03:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 27%|██▋       | 60/220 [00:12<00:13, 11.51it/s]
                                                
[2024-05-24 17:03:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 27%|██▋       | 60/220 [00:12<00:13, 11.51it/s]
                                                
[2024-05-24 17:03:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 27%|██▋       | 60/220 [00:12<00:13, 11.51it/s]
 29%|██▉       | 64/220 [00:12<00:10, 14.48it/s]
                                                
[2024-05-24 17:03:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 29%|██▉       | 64/220 [00:12<00:10, 14.48it/s]
                                                
[2024-05-24 17:03:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.input_layernorm.bias", shape: (2048,), dtype: float16

 29%|██▉       | 64/220 [00:12<00:10, 14.48it/s]
                                                
[2024-05-24 17:03:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (2048,), dtype: float16

 29%|██▉       | 64/220 [00:12<00:10, 14.48it/s]
                                                
[2024-05-24 17:03:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 29%|██▉       | 64/220 [00:12<00:10, 14.48it/s]
 31%|███       | 68/220 [00:12<00:09, 16.82it/s]
                                                
[2024-05-24 17:03:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 31%|███       | 68/220 [00:12<00:09, 16.82it/s]
                                                
[2024-05-24 17:03:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 31%|███       | 68/220 [00:13<00:09, 16.82it/s]
                                                
[2024-05-24 17:03:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 31%|███       | 68/220 [00:13<00:09, 16.82it/s]
 32%|███▏      | 71/220 [00:13<00:11, 13.30it/s]
                                                
[2024-05-24 17:03:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 32%|███▏      | 71/220 [00:13<00:11, 13.30it/s]
                                                
[2024-05-24 17:03:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 32%|███▏      | 71/220 [00:13<00:11, 13.30it/s]
                                                
[2024-05-24 17:03:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 32%|███▏      | 71/220 [00:13<00:11, 13.30it/s]
 34%|███▎      | 74/220 [00:13<00:10, 14.27it/s]
                                                
[2024-05-24 17:03:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.input_layernorm.bias", shape: (2048,), dtype: float16

 34%|███▎      | 74/220 [00:13<00:10, 14.27it/s]
                                                
[2024-05-24 17:03:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (2048,), dtype: float16

 34%|███▎      | 74/220 [00:13<00:10, 14.27it/s]
                                                
[2024-05-24 17:03:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 34%|███▎      | 74/220 [00:13<00:10, 14.27it/s]
                                                
[2024-05-24 17:03:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 34%|███▎      | 74/220 [00:13<00:10, 14.27it/s]
 35%|███▌      | 78/220 [00:13<00:11, 11.86it/s]
                                                
[2024-05-24 17:03:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 35%|███▌      | 78/220 [00:13<00:11, 11.86it/s]
                                                
[2024-05-24 17:03:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 35%|███▌      | 78/220 [00:13<00:11, 11.86it/s]
                                                
[2024-05-24 17:03:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 35%|███▌      | 78/220 [00:13<00:11, 11.86it/s]
                                                
[2024-05-24 17:03:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 35%|███▌      | 78/220 [00:13<00:11, 11.86it/s]
 37%|███▋      | 82/220 [00:13<00:09, 14.75it/s]
                                                
[2024-05-24 17:03:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 37%|███▋      | 82/220 [00:13<00:09, 14.75it/s]
                                                
[2024-05-24 17:03:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.input_layernorm.bias", shape: (2048,), dtype: float16

 37%|███▋      | 82/220 [00:13<00:09, 14.75it/s]
                                                
[2024-05-24 17:03:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (2048,), dtype: float16

 37%|███▋      | 82/220 [00:13<00:09, 14.75it/s]
                                                
[2024-05-24 17:03:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 37%|███▋      | 82/220 [00:13<00:09, 14.75it/s]
 39%|███▉      | 86/220 [00:14<00:07, 16.99it/s]
                                                
[2024-05-24 17:03:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 39%|███▉      | 86/220 [00:14<00:07, 16.99it/s]
                                                
[2024-05-24 17:03:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 39%|███▉      | 86/220 [00:14<00:07, 16.99it/s]
                                                
[2024-05-24 17:03:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 39%|███▉      | 86/220 [00:14<00:07, 16.99it/s]
 40%|████      | 89/220 [00:14<00:10, 12.61it/s]
                                                
[2024-05-24 17:03:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 40%|████      | 89/220 [00:14<00:10, 12.61it/s]
                                                
[2024-05-24 17:03:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 40%|████      | 89/220 [00:14<00:10, 12.61it/s]
 41%|████▏     | 91/220 [00:14<00:09, 13.06it/s]
                                                
[2024-05-24 17:03:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 41%|████▏     | 91/220 [00:14<00:09, 13.06it/s]
                                                
[2024-05-24 17:03:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.input_layernorm.bias", shape: (2048,), dtype: float16

 41%|████▏     | 91/220 [00:14<00:09, 13.06it/s]
                                                
[2024-05-24 17:03:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (2048,), dtype: float16

 41%|████▏     | 91/220 [00:14<00:09, 13.06it/s]
                                                
[2024-05-24 17:03:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 41%|████▏     | 91/220 [00:14<00:09, 13.06it/s]
 43%|████▎     | 95/220 [00:14<00:07, 15.78it/s]
                                                
[2024-05-24 17:03:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 43%|████▎     | 95/220 [00:14<00:07, 15.78it/s]
                                                
[2024-05-24 17:03:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 43%|████▎     | 95/220 [00:15<00:07, 15.78it/s]
 44%|████▍     | 97/220 [00:15<00:11, 10.74it/s]
                                                
[2024-05-24 17:03:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 44%|████▍     | 97/220 [00:15<00:11, 10.74it/s]
                                                
[2024-05-24 17:03:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 44%|████▍     | 97/220 [00:15<00:11, 10.74it/s]
                                                
[2024-05-24 17:03:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 44%|████▍     | 97/220 [00:15<00:11, 10.74it/s]
 45%|████▌     | 100/220 [00:15<00:09, 12.85it/s]
                                                 
[2024-05-24 17:03:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 45%|████▌     | 100/220 [00:15<00:09, 12.85it/s]
                                                 
[2024-05-24 17:03:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.input_layernorm.bias", shape: (2048,), dtype: float16

 45%|████▌     | 100/220 [00:15<00:09, 12.85it/s]
                                                 
[2024-05-24 17:03:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (2048,), dtype: float16

 45%|████▌     | 100/220 [00:15<00:09, 12.85it/s]
                                                 
[2024-05-24 17:03:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 45%|████▌     | 100/220 [00:15<00:09, 12.85it/s]
 47%|████▋     | 104/220 [00:15<00:07, 15.71it/s]
                                                 
[2024-05-24 17:03:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 47%|████▋     | 104/220 [00:15<00:07, 15.71it/s]
                                                 
[2024-05-24 17:03:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 47%|████▋     | 104/220 [00:15<00:07, 15.71it/s]
 48%|████▊     | 106/220 [00:15<00:10, 10.56it/s]
                                                 
[2024-05-24 17:03:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 48%|████▊     | 106/220 [00:15<00:10, 10.56it/s]
                                                 
[2024-05-24 17:03:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 48%|████▊     | 106/220 [00:15<00:10, 10.56it/s]
                                                 
[2024-05-24 17:03:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 48%|████▊     | 106/220 [00:15<00:10, 10.56it/s]
 50%|████▉     | 109/220 [00:15<00:08, 12.63it/s]
                                                 
[2024-05-24 17:03:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 50%|████▉     | 109/220 [00:15<00:08, 12.63it/s]
                                                 
[2024-05-24 17:03:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.input_layernorm.bias", shape: (2048,), dtype: float16

 50%|████▉     | 109/220 [00:16<00:08, 12.63it/s]
                                                 
[2024-05-24 17:03:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (2048,), dtype: float16

 50%|████▉     | 109/220 [00:16<00:08, 12.63it/s]
                                                 
[2024-05-24 17:03:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 50%|████▉     | 109/220 [00:16<00:08, 12.63it/s]
 51%|█████▏    | 113/220 [00:16<00:06, 15.44it/s]
                                                 
[2024-05-24 17:03:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 51%|█████▏    | 113/220 [00:16<00:06, 15.44it/s]
                                                 
[2024-05-24 17:03:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 51%|█████▏    | 113/220 [00:16<00:06, 15.44it/s]
 52%|█████▏    | 115/220 [00:16<00:10, 10.34it/s]
                                                 
[2024-05-24 17:03:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 52%|█████▏    | 115/220 [00:16<00:10, 10.34it/s]
                                                 
[2024-05-24 17:03:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 52%|█████▏    | 115/220 [00:16<00:10, 10.34it/s]
                                                 
[2024-05-24 17:03:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 52%|█████▏    | 115/220 [00:16<00:10, 10.34it/s]
 54%|█████▎    | 118/220 [00:16<00:08, 12.43it/s]
                                                 
[2024-05-24 17:03:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 54%|█████▎    | 118/220 [00:16<00:08, 12.43it/s]
                                                 
[2024-05-24 17:03:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.input_layernorm.bias", shape: (2048,), dtype: float16

 54%|█████▎    | 118/220 [00:16<00:08, 12.43it/s]
                                                 
[2024-05-24 17:03:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (2048,), dtype: float16

 54%|█████▎    | 118/220 [00:16<00:08, 12.43it/s]
                                                 
[2024-05-24 17:03:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 54%|█████▎    | 118/220 [00:16<00:08, 12.43it/s]
 55%|█████▌    | 122/220 [00:16<00:06, 15.23it/s]
                                                 
[2024-05-24 17:03:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 55%|█████▌    | 122/220 [00:17<00:06, 15.23it/s]
                                                 
[2024-05-24 17:03:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 55%|█████▌    | 122/220 [00:17<00:06, 15.23it/s]
 56%|█████▋    | 124/220 [00:17<00:09, 10.31it/s]
                                                 
[2024-05-24 17:03:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 56%|█████▋    | 124/220 [00:17<00:09, 10.31it/s]
                                                 
[2024-05-24 17:03:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 56%|█████▋    | 124/220 [00:17<00:09, 10.31it/s]
                                                 
[2024-05-24 17:03:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 56%|█████▋    | 124/220 [00:17<00:09, 10.31it/s]
 58%|█████▊    | 127/220 [00:17<00:07, 12.39it/s]
                                                 
[2024-05-24 17:03:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 58%|█████▊    | 127/220 [00:17<00:07, 12.39it/s]
                                                 
[2024-05-24 17:03:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.input_layernorm.bias", shape: (2048,), dtype: float16

 58%|█████▊    | 127/220 [00:17<00:07, 12.39it/s]
                                                 
[2024-05-24 17:03:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (2048,), dtype: float16

 58%|█████▊    | 127/220 [00:17<00:07, 12.39it/s]
                                                 
[2024-05-24 17:03:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 58%|█████▊    | 127/220 [00:17<00:07, 12.39it/s]
 60%|█████▉    | 131/220 [00:17<00:05, 15.18it/s]
                                                 
[2024-05-24 17:03:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 60%|█████▉    | 131/220 [00:17<00:05, 15.18it/s]
                                                 
[2024-05-24 17:03:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 60%|█████▉    | 131/220 [00:18<00:05, 15.18it/s]
 60%|██████    | 133/220 [00:18<00:08, 10.29it/s]
                                                 
[2024-05-24 17:03:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 60%|██████    | 133/220 [00:18<00:08, 10.29it/s]
                                                 
[2024-05-24 17:03:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 60%|██████    | 133/220 [00:18<00:08, 10.29it/s]
                                                 
[2024-05-24 17:03:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 60%|██████    | 133/220 [00:18<00:08, 10.29it/s]
 62%|██████▏   | 136/220 [00:18<00:06, 12.42it/s]
                                                 
[2024-05-24 17:03:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 62%|██████▏   | 136/220 [00:18<00:06, 12.42it/s]
                                                 
[2024-05-24 17:03:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.input_layernorm.bias", shape: (2048,), dtype: float16

 62%|██████▏   | 136/220 [00:18<00:06, 12.42it/s]
                                                 
[2024-05-24 17:03:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (2048,), dtype: float16

 62%|██████▏   | 136/220 [00:18<00:06, 12.42it/s]
                                                 
[2024-05-24 17:03:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 62%|██████▏   | 136/220 [00:18<00:06, 12.42it/s]
 64%|██████▎   | 140/220 [00:18<00:05, 15.30it/s]
                                                 
[2024-05-24 17:03:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 64%|██████▎   | 140/220 [00:18<00:05, 15.30it/s]
                                                 
[2024-05-24 17:03:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 64%|██████▎   | 140/220 [00:18<00:05, 15.30it/s]
 65%|██████▍   | 142/220 [00:18<00:07, 10.42it/s]
                                                 
[2024-05-24 17:03:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 65%|██████▍   | 142/220 [00:18<00:07, 10.42it/s]
                                                 
[2024-05-24 17:03:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 65%|██████▍   | 142/220 [00:18<00:07, 10.42it/s]
                                                 
[2024-05-24 17:03:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 65%|██████▍   | 142/220 [00:18<00:07, 10.42it/s]
 66%|██████▌   | 145/220 [00:18<00:05, 12.72it/s]
                                                 
[2024-05-24 17:03:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 66%|██████▌   | 145/220 [00:18<00:05, 12.72it/s]
                                                 
[2024-05-24 17:03:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.input_layernorm.bias", shape: (2048,), dtype: float16

 66%|██████▌   | 145/220 [00:18<00:05, 12.72it/s]
                                                 
[2024-05-24 17:03:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (2048,), dtype: float16

 66%|██████▌   | 145/220 [00:18<00:05, 12.72it/s]
                                                 
[2024-05-24 17:03:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 66%|██████▌   | 145/220 [00:18<00:05, 12.72it/s]
 68%|██████▊   | 149/220 [00:19<00:04, 15.53it/s]
                                                 
[2024-05-24 17:03:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 68%|██████▊   | 149/220 [00:19<00:04, 15.53it/s]
                                                 
[2024-05-24 17:03:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 68%|██████▊   | 149/220 [00:19<00:04, 15.53it/s]
                                                 
[2024-05-24 17:03:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 68%|██████▊   | 149/220 [00:19<00:04, 15.53it/s]
 69%|██████▉   | 152/220 [00:19<00:05, 11.57it/s]
                                                 
[2024-05-24 17:03:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 69%|██████▉   | 152/220 [00:19<00:05, 11.57it/s]
                                                 
[2024-05-24 17:03:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 69%|██████▉   | 152/220 [00:19<00:05, 11.57it/s]
 70%|███████   | 154/220 [00:19<00:05, 12.24it/s]
                                                 
[2024-05-24 17:03:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 70%|███████   | 154/220 [00:19<00:05, 12.24it/s]
                                                 
[2024-05-24 17:03:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.input_layernorm.bias", shape: (2048,), dtype: float16

 70%|███████   | 154/220 [00:19<00:05, 12.24it/s]
                                                 
[2024-05-24 17:03:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (2048,), dtype: float16

 70%|███████   | 154/220 [00:19<00:05, 12.24it/s]
                                                 
[2024-05-24 17:03:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 70%|███████   | 154/220 [00:19<00:05, 12.24it/s]
 72%|███████▏  | 158/220 [00:19<00:04, 15.25it/s]
                                                 
[2024-05-24 17:03:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 72%|███████▏  | 158/220 [00:19<00:04, 15.25it/s]
                                                 
[2024-05-24 17:03:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 72%|███████▏  | 158/220 [00:20<00:04, 15.25it/s]
 73%|███████▎  | 160/220 [00:20<00:05, 10.43it/s]
                                                 
[2024-05-24 17:03:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 73%|███████▎  | 160/220 [00:20<00:05, 10.43it/s]
                                                 
[2024-05-24 17:03:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 73%|███████▎  | 160/220 [00:20<00:05, 10.43it/s]
                                                 
[2024-05-24 17:03:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 73%|███████▎  | 160/220 [00:20<00:05, 10.43it/s]
 74%|███████▍  | 163/220 [00:20<00:04, 12.57it/s]
                                                 
[2024-05-24 17:03:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 74%|███████▍  | 163/220 [00:20<00:04, 12.57it/s]
                                                 
[2024-05-24 17:03:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.input_layernorm.bias", shape: (2048,), dtype: float16

 74%|███████▍  | 163/220 [00:20<00:04, 12.57it/s]
                                                 
[2024-05-24 17:03:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (2048,), dtype: float16

 74%|███████▍  | 163/220 [00:20<00:04, 12.57it/s]
                                                 
[2024-05-24 17:03:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 74%|███████▍  | 163/220 [00:20<00:04, 12.57it/s]
 76%|███████▌  | 167/220 [00:20<00:03, 15.44it/s]
                                                 
[2024-05-24 17:03:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 76%|███████▌  | 167/220 [00:20<00:03, 15.44it/s]
                                                 
[2024-05-24 17:03:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 76%|███████▌  | 167/220 [00:20<00:03, 15.44it/s]
 77%|███████▋  | 169/220 [00:20<00:04, 10.40it/s]
                                                 
[2024-05-24 17:03:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 77%|███████▋  | 169/220 [00:20<00:04, 10.40it/s]
                                                 
[2024-05-24 17:03:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 77%|███████▋  | 169/220 [00:20<00:04, 10.40it/s]
                                                 
[2024-05-24 17:03:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 77%|███████▋  | 169/220 [00:20<00:04, 10.40it/s]
 78%|███████▊  | 172/220 [00:21<00:03, 12.53it/s]
                                                 
[2024-05-24 17:03:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 78%|███████▊  | 172/220 [00:21<00:03, 12.53it/s]
                                                 
[2024-05-24 17:03:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.input_layernorm.bias", shape: (2048,), dtype: float16

 78%|███████▊  | 172/220 [00:21<00:03, 12.53it/s]
                                                 
[2024-05-24 17:03:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (2048,), dtype: float16

 78%|███████▊  | 172/220 [00:21<00:03, 12.53it/s]
                                                 
[2024-05-24 17:03:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 78%|███████▊  | 172/220 [00:21<00:03, 12.53it/s]
 80%|████████  | 176/220 [00:21<00:02, 15.31it/s]
                                                 
[2024-05-24 17:03:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 80%|████████  | 176/220 [00:21<00:02, 15.31it/s]
                                                 
[2024-05-24 17:03:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 80%|████████  | 176/220 [00:21<00:02, 15.31it/s]
 81%|████████  | 178/220 [00:21<00:04, 10.26it/s]
                                                 
[2024-05-24 17:03:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 81%|████████  | 178/220 [00:21<00:04, 10.26it/s]
                                                 
[2024-05-24 17:03:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 81%|████████  | 178/220 [00:21<00:04, 10.26it/s]
                                                 
[2024-05-24 17:03:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 81%|████████  | 178/220 [00:21<00:04, 10.26it/s]
 82%|████████▏ | 181/220 [00:21<00:03, 12.43it/s]
                                                 
[2024-05-24 17:03:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 82%|████████▏ | 181/220 [00:21<00:03, 12.43it/s]
                                                 
[2024-05-24 17:03:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.input_layernorm.bias", shape: (2048,), dtype: float16

 82%|████████▏ | 181/220 [00:21<00:03, 12.43it/s]
                                                 
[2024-05-24 17:03:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (2048,), dtype: float16

 82%|████████▏ | 181/220 [00:21<00:03, 12.43it/s]
                                                 
[2024-05-24 17:03:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 82%|████████▏ | 181/220 [00:21<00:03, 12.43it/s]
 84%|████████▍ | 185/220 [00:21<00:02, 15.33it/s]
                                                 
[2024-05-24 17:03:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 84%|████████▍ | 185/220 [00:22<00:02, 15.33it/s]
                                                 
[2024-05-24 17:03:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 84%|████████▍ | 185/220 [00:22<00:02, 15.33it/s]
 85%|████████▌ | 187/220 [00:22<00:02, 11.24it/s]
                                                 
[2024-05-24 17:03:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 85%|████████▌ | 187/220 [00:22<00:02, 11.24it/s]
                                                 
[2024-05-24 17:03:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 85%|████████▌ | 187/220 [00:22<00:02, 11.24it/s]
                                                 
[2024-05-24 17:03:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 85%|████████▌ | 187/220 [00:22<00:02, 11.24it/s]
                                                 
[2024-05-24 17:03:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 85%|████████▌ | 187/220 [00:22<00:02, 11.24it/s]
 87%|████████▋ | 191/220 [00:22<00:02, 13.56it/s]
                                                 
[2024-05-24 17:03:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.input_layernorm.bias", shape: (2048,), dtype: float16

 87%|████████▋ | 191/220 [00:22<00:02, 13.56it/s]
                                                 
[2024-05-24 17:03:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (2048,), dtype: float16

 87%|████████▋ | 191/220 [00:22<00:02, 13.56it/s]
                                                 
[2024-05-24 17:03:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 87%|████████▋ | 191/220 [00:22<00:02, 13.56it/s]
                                                 
[2024-05-24 17:03:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 87%|████████▋ | 191/220 [00:22<00:02, 13.56it/s]
 89%|████████▊ | 195/220 [00:22<00:02, 11.14it/s]
                                                 
[2024-05-24 17:03:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 89%|████████▊ | 195/220 [00:22<00:02, 11.14it/s]
                                                 
[2024-05-24 17:03:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 89%|████████▊ | 195/220 [00:22<00:02, 11.14it/s]
                                                 
[2024-05-24 17:03:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 89%|████████▊ | 195/220 [00:22<00:02, 11.14it/s]
                                                 
[2024-05-24 17:03:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 89%|████████▊ | 195/220 [00:22<00:02, 11.14it/s]
 90%|█████████ | 199/220 [00:23<00:01, 14.05it/s]
                                                 
[2024-05-24 17:03:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 90%|█████████ | 199/220 [00:23<00:01, 14.05it/s]
                                                 
[2024-05-24 17:03:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.input_layernorm.bias", shape: (2048,), dtype: float16

 90%|█████████ | 199/220 [00:23<00:01, 14.05it/s]
                                                 
[2024-05-24 17:03:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (2048,), dtype: float16

 90%|█████████ | 199/220 [00:23<00:01, 14.05it/s]
                                                 
[2024-05-24 17:03:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 90%|█████████ | 199/220 [00:23<00:01, 14.05it/s]
 92%|█████████▏| 203/220 [00:23<00:01, 16.34it/s]
                                                 
[2024-05-24 17:03:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 92%|█████████▏| 203/220 [00:23<00:01, 16.34it/s]
                                                 
[2024-05-24 17:03:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 92%|█████████▏| 203/220 [00:23<00:01, 16.34it/s]
                                                 
[2024-05-24 17:03:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 92%|█████████▏| 203/220 [00:23<00:01, 16.34it/s]
 94%|█████████▎| 206/220 [00:23<00:01, 12.29it/s]
                                                 
[2024-05-24 17:03:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 94%|█████████▎| 206/220 [00:23<00:01, 12.29it/s]
                                                 
[2024-05-24 17:03:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 94%|█████████▎| 206/220 [00:23<00:01, 12.29it/s]
 95%|█████████▍| 208/220 [00:23<00:00, 12.81it/s]
                                                 
[2024-05-24 17:03:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 95%|█████████▍| 208/220 [00:23<00:00, 12.81it/s]
                                                 
[2024-05-24 17:03:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.input_layernorm.bias", shape: (2048,), dtype: float16

 95%|█████████▍| 208/220 [00:23<00:00, 12.81it/s]
                                                 
[2024-05-24 17:03:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (2048,), dtype: float16

 95%|█████████▍| 208/220 [00:23<00:00, 12.81it/s]
                                                 
[2024-05-24 17:03:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.mlp.down_proj.weight", shape: (2048, 5632), dtype: float16

 95%|█████████▍| 208/220 [00:23<00:00, 12.81it/s]
 96%|█████████▋| 212/220 [00:23<00:00, 15.54it/s]
                                                 
[2024-05-24 17:03:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.mlp.gate_up_proj.weight", shape: (11264, 2048), dtype: float16

 96%|█████████▋| 212/220 [00:24<00:00, 15.54it/s]
                                                 
[2024-05-24 17:03:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.bias", shape: (2048,), dtype: float16

 96%|█████████▋| 212/220 [00:24<00:00, 15.54it/s]
 97%|█████████▋| 214/220 [00:24<00:00, 10.64it/s]
                                                 
[2024-05-24 17:03:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (2048,), dtype: float16

 97%|█████████▋| 214/220 [00:24<00:00, 10.64it/s]
                                                 
[2024-05-24 17:03:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.self_attn.qkv_proj.bias", shape: (6144,), dtype: float16

 97%|█████████▋| 214/220 [00:24<00:00, 10.64it/s]
                                                 
[2024-05-24 17:03:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.self_attn.qkv_proj.weight", shape: (6144, 2048), dtype: float16

 97%|█████████▋| 214/220 [00:24<00:00, 10.64it/s]
 99%|█████████▊| 217/220 [00:24<00:00, 12.85it/s]
                                                 
[2024-05-24 17:03:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16

 99%|█████████▊| 217/220 [00:24<00:00, 12.85it/s]
                                                 
[2024-05-24 17:03:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.norm.bias", shape: (2048,), dtype: float16

 99%|█████████▊| 217/220 [00:24<00:00, 12.85it/s]
                                                 
[2024-05-24 17:03:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.norm.weight", shape: (2048,), dtype: float16

 99%|█████████▊| 217/220 [00:24<00:00, 12.85it/s]
100%|██████████| 220/220 [00:24<00:00,  8.96it/s]
[2024-05-24 17:03:24] INFO huggingface_loader.py:196: Unloading HF weight file: dist/models/stablelm-2-zephyr-1_6b/model.safetensors
[2024-05-24 17:03:24] INFO stats.py:76: Time usage: HF loading: 1.644 sec; Pre-quantization mapping: 11.830 sec; Quantization: 0.000 sec
[2024-05-24 17:03:24] INFO stats.py:90: RAM usage: Peak RAM: 3.063 GB. Total bytes loaded from disk: 3.063 GB
[2024-05-24 17:03:24] INFO convert_weight.py:155: Parameter size after quantization: 3.063 GB
[2024-05-24 17:03:24] INFO convert_weight.py:160: Total parameters: 1,644,515,328
[2024-05-24 17:03:24] INFO convert_weight.py:161: Bits per parameter: 16.000
[2024-05-24 17:03:24] INFO convert_weight.py:166: Saved to directory: /tmp/tmphm3edhbu

All finished, 75 total shards committed, record saved to /tmp/tmphm3edhbu/ndarray-cache.json