diff --git "a/logs.txt" "b/logs.txt"
new file mode 100644--- /dev/null
+++ "b/logs.txt"
@@ -0,0 +1,522 @@
+/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Mistral-7B-Instruct-v0.3 --quantization q0f16 --conv-template mistral_default --output /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC
+[2024-06-02 06:17:11] INFO auto_config.py:116: Found model configuration: /models/Mistral-7B-Instruct-v0.3/config.json
+[2024-06-02 06:17:11] INFO auto_config.py:154: Found model type: mistral. Use `--model-type` to override.
+[2024-06-02 06:17:11] INFO mistral_model.py:56: prefill_chunk_size defaults to 2048
+[2024-06-02 06:17:11] INFO config.py:107: Overriding max_batch_size from 1 to 80
+[2024-06-02 06:17:11] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 1
+[2024-06-02 06:17:11] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: 2
+[2024-06-02 06:17:11] INFO gen_config.py:155: Found tokenizer config: /models/Mistral-7B-Instruct-v0.3/tokenizer.model. Copying to /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC/tokenizer.model
+[2024-06-02 06:17:11] INFO gen_config.py:155: Found tokenizer config: /models/Mistral-7B-Instruct-v0.3/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC/tokenizer.json
+[2024-06-02 06:17:11] INFO gen_config.py:157: Not found tokenizer config: /models/Mistral-7B-Instruct-v0.3/vocab.json
+[2024-06-02 06:17:11] INFO gen_config.py:157: Not found tokenizer config: /models/Mistral-7B-Instruct-v0.3/merges.txt
+[2024-06-02 06:17:11] INFO gen_config.py:157: Not found tokenizer config: /models/Mistral-7B-Instruct-v0.3/added_tokens.json
+[2024-06-02 06:17:11] INFO gen_config.py:155: Found tokenizer config: /models/Mistral-7B-Instruct-v0.3/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC/tokenizer_config.json
+[2024-06-02 06:17:11] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_fallback', 'prepend_space_in_encode': False, 'strip_space_in_decode': True}
+[2024-06-02 06:17:11] INFO gen_config.py:32: [System default] Setting pad_token_id: 0
+[2024-06-02 06:17:11] INFO gen_config.py:32: [System default] Setting temperature: 1.0
+[2024-06-02 06:17:11] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
+[2024-06-02 06:17:11] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
+[2024-06-02 06:17:11] INFO gen_config.py:32: [System default] Setting repetition_penalty: 1.0
+[2024-06-02 06:17:11] INFO gen_config.py:32: [System default] Setting top_p: 1.0
+[2024-06-02 06:17:11] INFO gen_config.py:32: [System default] Setting mean_gen_len: 128
+[2024-06-02 06:17:11] INFO gen_config.py:32: [System default] Setting max_gen_len: 512
+[2024-06-02 06:17:11] INFO gen_config.py:32: [System default] Setting shift_fill_factor: 0.3
+[2024-06-02 06:17:11] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC/mlc-chat-config.json
+/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Mistral-7B-Instruct-v0.3 --quantization q0f16 --output /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC
+[2024-06-02 06:17:13] INFO auto_config.py:116: Found model configuration: /models/Mistral-7B-Instruct-v0.3/config.json
+[2024-06-02 06:17:14] INFO auto_device.py:79: Found device: cuda:0
+[2024-06-02 06:17:16] INFO auto_device.py:88: Not found device: rocm:0
+[2024-06-02 06:17:17] INFO auto_device.py:88: Not found device: metal:0
+[2024-06-02 06:17:19] INFO auto_device.py:79: Found device: vulkan:0
+[2024-06-02 06:17:19] INFO auto_device.py:79: Found device: vulkan:1
+[2024-06-02 06:17:19] INFO auto_device.py:79: Found device: vulkan:2
+[2024-06-02 06:17:19] INFO auto_device.py:79: Found device: vulkan:3
+[2024-06-02 06:17:21] INFO auto_device.py:88: Not found device: opencl:0
+[2024-06-02 06:17:21] INFO auto_device.py:35: Using device: cuda:0
+[2024-06-02 06:17:21] INFO auto_weight.py:71: Finding weights in: /models/Mistral-7B-Instruct-v0.3
+[2024-06-02 06:17:21] INFO auto_weight.py:137: Not found Huggingface PyTorch
+[2024-06-02 06:17:21] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /models/Mistral-7B-Instruct-v0.3/model.safetensors.index.json
+[2024-06-02 06:17:21] INFO auto_weight.py:107: Using source weight configuration: /models/Mistral-7B-Instruct-v0.3/model.safetensors.index.json. Use `--source` to override.
+[2024-06-02 06:17:21] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
+[2024-06-02 06:17:21] INFO auto_config.py:154: Found model type: mistral. Use `--model-type` to override.
+[2024-06-02 06:17:21] INFO mistral_model.py:56: prefill_chunk_size defaults to 2048
+Weight conversion with arguments:
+  --config          /models/Mistral-7B-Instruct-v0.3/config.json
+  --quantization    NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16')
+  --model-type      mistral
+  --device          cuda:0
+  --source          /models/Mistral-7B-Instruct-v0.3/model.safetensors.index.json
+  --source-format   huggingface-safetensor
+  --output          /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC
+Start storing to cache /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC
+
  0%|          | 0/195 [00:00<?, ?it/s]
                                       
[2024-06-02 06:17:22] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Mistral-7B-Instruct-v0.3/model-00003-of-00003.safetensors
+
  0%|          | 0/195 [00:00<?, ?it/s]
                                       
[2024-06-02 06:17:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "lm_head.weight", shape: (32768, 4096), dtype: float16
+
  0%|          | 0/195 [00:07<?, ?it/s]
  1%|          | 1/195 [00:08<26:13,  8.11s/it]
                                               
[2024-06-02 06:17:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (4096,), dtype: float16
+
  1%|          | 1/195 [00:08<26:13,  8.11s/it]
                                               
[2024-06-02 06:17:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
  1%|          | 1/195 [00:08<26:13,  8.11s/it]
  2%|▏         | 3/195 [00:08<07:26,  2.32s/it]
                                               
[2024-06-02 06:17:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
  2%|▏         | 3/195 [00:09<07:26,  2.32s/it]
  2%|▏         | 4/195 [00:10<06:36,  2.07s/it]
                                               
[2024-06-02 06:17:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
  2%|▏         | 4/195 [00:10<06:36,  2.07s/it]
                                               
[2024-06-02 06:17:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (4096,), dtype: float16
+
  2%|▏         | 4/195 [00:10<06:36,  2.07s/it]
                                               
[2024-06-02 06:17:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
  2%|▏         | 4/195 [00:10<06:36,  2.07s/it]
  4%|▎         | 7/195 [00:10<02:59,  1.05it/s]
                                               
[2024-06-02 06:17:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
  4%|▎         | 7/195 [00:11<02:59,  1.05it/s]
  4%|▍         | 8/195 [00:12<03:07,  1.00s/it]
                                               
[2024-06-02 06:17:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
  4%|▍         | 8/195 [00:12<03:07,  1.00s/it]
                                               
[2024-06-02 06:17:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
  4%|▍         | 8/195 [00:12<03:07,  1.00s/it]
  5%|▌         | 10/195 [00:12<02:03,  1.50it/s]
                                                
[2024-06-02 06:17:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
  5%|▌         | 10/195 [00:12<02:03,  1.50it/s]
  6%|▌         | 11/195 [00:12<01:42,  1.79it/s]
                                                
[2024-06-02 06:17:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (4096,), dtype: float16
+
  6%|▌         | 11/195 [00:12<01:42,  1.79it/s]
                                                
[2024-06-02 06:17:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
  6%|▌         | 11/195 [00:12<01:42,  1.79it/s]
  7%|▋         | 13/195 [00:13<01:22,  2.21it/s]
                                                
[2024-06-02 06:17:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
  7%|▋         | 13/195 [00:13<01:22,  2.21it/s]
  7%|▋         | 14/195 [00:14<01:48,  1.67it/s]
                                                
[2024-06-02 06:17:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
  7%|▋         | 14/195 [00:14<01:48,  1.67it/s]
                                                
[2024-06-02 06:17:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
  7%|▋         | 14/195 [00:14<01:48,  1.67it/s]
  8%|▊         | 16/195 [00:14<01:15,  2.36it/s]
                                                
[2024-06-02 06:17:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
  8%|▊         | 16/195 [00:14<01:15,  2.36it/s]
  9%|▊         | 17/195 [00:14<01:05,  2.71it/s]
                                                
[2024-06-02 06:17:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (4096,), dtype: float16
+
  9%|▊         | 17/195 [00:14<01:05,  2.71it/s]
                                                
[2024-06-02 06:17:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
  9%|▊         | 17/195 [00:14<01:05,  2.71it/s]
 10%|▉         | 19/195 [00:15<00:59,  2.98it/s]
                                                
[2024-06-02 06:17:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 10%|▉         | 19/195 [00:15<00:59,  2.98it/s]
 10%|█         | 20/195 [00:16<01:29,  1.96it/s]
                                                
[2024-06-02 06:17:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 10%|█         | 20/195 [00:16<01:29,  1.96it/s]
                                                
[2024-06-02 06:17:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 10%|█         | 20/195 [00:16<01:29,  1.96it/s]
 11%|█▏        | 22/195 [00:16<01:03,  2.71it/s]
                                                
[2024-06-02 06:17:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 11%|█▏        | 22/195 [00:16<01:03,  2.71it/s]
 12%|█▏        | 23/195 [00:16<00:56,  3.06it/s]
                                                
[2024-06-02 06:17:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (4096,), dtype: float16
+
 12%|█▏        | 23/195 [00:16<00:56,  3.06it/s]
                                                
[2024-06-02 06:17:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 12%|█▏        | 23/195 [00:17<00:56,  3.06it/s]
 13%|█▎        | 25/195 [00:17<00:52,  3.22it/s]
                                                
[2024-06-02 06:17:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 13%|█▎        | 25/195 [00:17<00:52,  3.22it/s]
 13%|█▎        | 26/195 [00:18<01:23,  2.03it/s]
                                                
[2024-06-02 06:17:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 13%|█▎        | 26/195 [00:18<01:23,  2.03it/s]
                                                
[2024-06-02 06:17:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 13%|█▎        | 26/195 [00:18<01:23,  2.03it/s]
 14%|█▍        | 28/195 [00:18<00:59,  2.80it/s]
                                                
[2024-06-02 06:17:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 14%|█▍        | 28/195 [00:18<00:59,  2.80it/s]
 15%|█▍        | 29/195 [00:18<00:52,  3.17it/s]
                                                
[2024-06-02 06:17:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (4096,), dtype: float16
+
 15%|█▍        | 29/195 [00:18<00:52,  3.17it/s]
                                                
[2024-06-02 06:17:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 15%|█▍        | 29/195 [00:19<00:52,  3.17it/s]
 16%|█▌        | 31/195 [00:19<00:48,  3.35it/s]
                                                
[2024-06-02 06:17:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 16%|█▌        | 31/195 [00:20<00:48,  3.35it/s]
 16%|█▋        | 32/195 [00:20<01:17,  2.10it/s]
                                                
[2024-06-02 06:17:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 16%|█▋        | 32/195 [00:20<01:17,  2.10it/s]
                                                
[2024-06-02 06:17:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 16%|█▋        | 32/195 [00:20<01:17,  2.10it/s]
 17%|█▋        | 34/195 [00:20<00:55,  2.88it/s]
                                                
[2024-06-02 06:17:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 17%|█▋        | 34/195 [00:21<00:55,  2.88it/s]
 18%|█▊        | 35/195 [00:21<00:49,  3.25it/s]
                                                
[2024-06-02 06:17:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.input_layernorm.weight", shape: (4096,), dtype: float16
+
 18%|█▊        | 35/195 [00:21<00:49,  3.25it/s]
                                                
[2024-06-02 06:17:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 18%|█▊        | 35/195 [00:21<00:49,  3.25it/s]
 19%|█▉        | 37/195 [00:21<00:46,  3.42it/s]
                                                
[2024-06-02 06:17:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 19%|█▉        | 37/195 [00:22<00:46,  3.42it/s]
 19%|█▉        | 38/195 [00:22<01:13,  2.12it/s]
                                                
[2024-06-02 06:17:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 19%|█▉        | 38/195 [00:22<01:13,  2.12it/s]
                                                
[2024-06-02 06:17:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 19%|█▉        | 38/195 [00:22<01:13,  2.12it/s]
 21%|██        | 40/195 [00:23<00:53,  2.91it/s]
                                                
[2024-06-02 06:17:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 21%|██        | 40/195 [00:23<00:53,  2.91it/s]
 21%|██        | 41/195 [00:23<00:46,  3.28it/s]
                                                
[2024-06-02 06:17:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.input_layernorm.weight", shape: (4096,), dtype: float16
+
 21%|██        | 41/195 [00:23<00:46,  3.28it/s]
                                                
[2024-06-02 06:17:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 21%|██        | 41/195 [00:23<00:46,  3.28it/s]
 22%|██▏       | 43/195 [00:23<00:45,  3.37it/s]
                                                
[2024-06-02 06:17:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 22%|██▏       | 43/195 [00:24<00:45,  3.37it/s]
 23%|██▎       | 44/195 [00:25<01:17,  1.94it/s]
                                                
[2024-06-02 06:17:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 23%|██▎       | 44/195 [00:25<01:17,  1.94it/s]
                                                
[2024-06-02 06:17:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 23%|██▎       | 44/195 [00:25<01:17,  1.94it/s]
 24%|██▎       | 46/195 [00:25<00:56,  2.65it/s]
                                                
[2024-06-02 06:17:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 24%|██▎       | 46/195 [00:25<00:56,  2.65it/s]
 24%|██▍       | 47/195 [00:25<00:49,  3.00it/s]
                                                
[2024-06-02 06:17:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.input_layernorm.weight", shape: (4096,), dtype: float16
+
 24%|██▍       | 47/195 [00:25<00:49,  3.00it/s]
                                                
[2024-06-02 06:17:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 24%|██▍       | 47/195 [00:25<00:49,  3.00it/s]
 25%|██▌       | 49/195 [00:26<00:45,  3.21it/s]
                                                
[2024-06-02 06:17:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 25%|██▌       | 49/195 [00:26<00:45,  3.21it/s]
 26%|██▌       | 50/195 [00:27<01:11,  2.03it/s]
                                                
[2024-06-02 06:17:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 26%|██▌       | 50/195 [00:27<01:11,  2.03it/s]
                                                
[2024-06-02 06:17:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 26%|██▌       | 50/195 [00:27<01:11,  2.03it/s]
 27%|██▋       | 52/195 [00:27<00:51,  2.79it/s]
                                                
[2024-06-02 06:17:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 27%|██▋       | 52/195 [00:27<00:51,  2.79it/s]
 27%|██▋       | 53/195 [00:27<00:44,  3.16it/s]
                                                
[2024-06-02 06:17:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.input_layernorm.weight", shape: (4096,), dtype: float16
+
 27%|██▋       | 53/195 [00:27<00:44,  3.16it/s]
                                                
[2024-06-02 06:17:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 27%|██▋       | 53/195 [00:27<00:44,  3.16it/s]
 28%|██▊       | 55/195 [00:28<00:42,  3.31it/s]
                                                
[2024-06-02 06:17:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 28%|██▊       | 55/195 [00:28<00:42,  3.31it/s]
 29%|██▊       | 56/195 [00:29<01:06,  2.08it/s]
                                                
[2024-06-02 06:17:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 29%|██▊       | 56/195 [00:29<01:06,  2.08it/s]
                                                
[2024-06-02 06:17:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 29%|██▊       | 56/195 [00:29<01:06,  2.08it/s]
 30%|██▉       | 58/195 [00:29<00:48,  2.82it/s]
                                                
[2024-06-02 06:17:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 30%|██▉       | 58/195 [00:29<00:48,  2.82it/s]
 30%|███       | 59/195 [00:29<00:42,  3.19it/s]
                                                
[2024-06-02 06:17:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (4096,), dtype: float16
+
 30%|███       | 59/195 [00:29<00:42,  3.19it/s]
                                                
[2024-06-02 06:17:51] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Mistral-7B-Instruct-v0.3/model-00003-of-00003.safetensors
+
 30%|███       | 59/195 [00:29<00:42,  3.19it/s]
                                                
[2024-06-02 06:17:52] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Mistral-7B-Instruct-v0.3/model-00001-of-00003.safetensors
+
 30%|███       | 59/195 [00:30<00:42,  3.19it/s]
                                                
[2024-06-02 06:17:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.embed_tokens.weight", shape: (32768, 4096), dtype: float16
+
 30%|███       | 59/195 [00:34<00:42,  3.19it/s]
 31%|███▏      | 61/195 [00:35<02:48,  1.26s/it]
                                                
[2024-06-02 06:17:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (4096,), dtype: float16
+
 31%|███▏      | 61/195 [00:35<02:48,  1.26s/it]
                                                
[2024-06-02 06:17:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 31%|███▏      | 61/195 [00:35<02:48,  1.26s/it]
 32%|███▏      | 63/195 [00:36<02:00,  1.09it/s]
                                                
[2024-06-02 06:17:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 32%|███▏      | 63/195 [00:36<02:00,  1.09it/s]
 33%|███▎      | 64/195 [00:37<02:05,  1.05it/s]
                                                
[2024-06-02 06:17:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 33%|███▎      | 64/195 [00:37<02:05,  1.05it/s]
                                                
[2024-06-02 06:17:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 33%|███▎      | 64/195 [00:37<02:05,  1.05it/s]
 34%|███▍      | 66/195 [00:37<01:28,  1.46it/s]
                                                
[2024-06-02 06:17:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 34%|███▍      | 66/195 [00:37<01:28,  1.46it/s]
 34%|███▍      | 67/195 [00:37<01:13,  1.73it/s]
                                                
[2024-06-02 06:17:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (4096,), dtype: float16
+
 34%|███▍      | 67/195 [00:37<01:13,  1.73it/s]
                                                
[2024-06-02 06:18:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 34%|███▍      | 67/195 [00:37<01:13,  1.73it/s]
 35%|███▌      | 69/195 [00:38<00:58,  2.17it/s]
                                                
[2024-06-02 06:18:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 35%|███▌      | 69/195 [00:38<00:58,  2.17it/s]
 36%|███▌      | 70/195 [00:39<01:14,  1.67it/s]
                                                
[2024-06-02 06:18:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 36%|███▌      | 70/195 [00:39<01:14,  1.67it/s]
                                                
[2024-06-02 06:18:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 36%|███▌      | 70/195 [00:39<01:14,  1.67it/s]
 37%|███▋      | 72/195 [00:39<00:55,  2.21it/s]
                                                
[2024-06-02 06:18:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 37%|███▋      | 72/195 [00:39<00:55,  2.21it/s]
 37%|███▋      | 73/195 [00:39<00:47,  2.57it/s]
                                                
[2024-06-02 06:18:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 37%|███▋      | 73/195 [00:40<00:47,  2.57it/s]
 38%|███▊      | 74/195 [00:41<01:07,  1.80it/s]
                                                
[2024-06-02 06:18:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 38%|███▊      | 74/195 [00:41<01:07,  1.80it/s]
 38%|███▊      | 75/195 [00:41<00:57,  2.08it/s]
                                                
[2024-06-02 06:18:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 38%|███▊      | 75/195 [00:41<00:57,  2.08it/s]
 39%|███▉      | 76/195 [00:41<00:47,  2.53it/s]
                                                
[2024-06-02 06:18:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (4096,), dtype: float16
+
 39%|███▉      | 76/195 [00:41<00:47,  2.53it/s]
                                                
[2024-06-02 06:18:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 39%|███▉      | 76/195 [00:41<00:47,  2.53it/s]
 40%|████      | 78/195 [00:42<00:39,  2.94it/s]
                                                
[2024-06-02 06:18:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 40%|████      | 78/195 [00:42<00:39,  2.94it/s]
 41%|████      | 79/195 [00:43<01:00,  1.92it/s]
                                                
[2024-06-02 06:18:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 41%|████      | 79/195 [00:43<01:00,  1.92it/s]
                                                
[2024-06-02 06:18:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 41%|████      | 79/195 [00:43<01:00,  1.92it/s]
 42%|████▏     | 81/195 [00:43<00:41,  2.75it/s]
                                                
[2024-06-02 06:18:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 42%|████▏     | 81/195 [00:43<00:41,  2.75it/s]
 42%|████▏     | 82/195 [00:43<00:35,  3.15it/s]
                                                
[2024-06-02 06:18:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (4096,), dtype: float16
+
 42%|████▏     | 82/195 [00:43<00:35,  3.15it/s]
                                                
[2024-06-02 06:18:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 42%|████▏     | 82/195 [00:43<00:35,  3.15it/s]
 43%|████▎     | 84/195 [00:44<00:33,  3.35it/s]
                                                
[2024-06-02 06:18:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 43%|████▎     | 84/195 [00:44<00:33,  3.35it/s]
 44%|████▎     | 85/195 [00:45<00:52,  2.10it/s]
                                                
[2024-06-02 06:18:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 44%|████▎     | 85/195 [00:45<00:52,  2.10it/s]
                                                
[2024-06-02 06:18:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 44%|████▎     | 85/195 [00:45<00:52,  2.10it/s]
 45%|████▍     | 87/195 [00:45<00:37,  2.90it/s]
                                                
[2024-06-02 06:18:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 45%|████▍     | 87/195 [00:45<00:37,  2.90it/s]
 45%|████▌     | 88/195 [00:45<00:32,  3.29it/s]
                                                
[2024-06-02 06:18:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (4096,), dtype: float16
+
 45%|████▌     | 88/195 [00:45<00:32,  3.29it/s]
                                                
[2024-06-02 06:18:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 45%|████▌     | 88/195 [00:45<00:32,  3.29it/s]
 46%|████▌     | 90/195 [00:46<00:30,  3.44it/s]
                                                
[2024-06-02 06:18:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 46%|████▌     | 90/195 [00:46<00:30,  3.44it/s]
 47%|████▋     | 91/195 [00:47<00:48,  2.13it/s]
                                                
[2024-06-02 06:18:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 47%|████▋     | 91/195 [00:47<00:48,  2.13it/s]
                                                
[2024-06-02 06:18:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 47%|████▋     | 91/195 [00:47<00:48,  2.13it/s]
 48%|████▊     | 93/195 [00:47<00:34,  2.93it/s]
                                                
[2024-06-02 06:18:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 48%|████▊     | 93/195 [00:47<00:34,  2.93it/s]
 48%|████▊     | 94/195 [00:47<00:30,  3.32it/s]
                                                
[2024-06-02 06:18:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (4096,), dtype: float16
+
 48%|████▊     | 94/195 [00:47<00:30,  3.32it/s]
                                                
[2024-06-02 06:18:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 48%|████▊     | 94/195 [00:47<00:30,  3.32it/s]
 49%|████▉     | 96/195 [00:48<00:28,  3.44it/s]
                                                
[2024-06-02 06:18:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 49%|████▉     | 96/195 [00:48<00:28,  3.44it/s]
 50%|████▉     | 97/195 [00:49<00:46,  2.12it/s]
                                                
[2024-06-02 06:18:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 50%|████▉     | 97/195 [00:49<00:46,  2.12it/s]
                                                
[2024-06-02 06:18:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 50%|████▉     | 97/195 [00:49<00:46,  2.12it/s]
 51%|█████     | 99/195 [00:49<00:32,  2.92it/s]
                                                
[2024-06-02 06:18:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 51%|█████     | 99/195 [00:49<00:32,  2.92it/s]
 51%|█████▏    | 100/195 [00:49<00:28,  3.30it/s]
                                                 
[2024-06-02 06:18:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (4096,), dtype: float16
+
 51%|█████▏    | 100/195 [00:49<00:28,  3.30it/s]
                                                 
[2024-06-02 06:18:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 51%|█████▏    | 100/195 [00:50<00:28,  3.30it/s]
 52%|█████▏    | 102/195 [00:50<00:27,  3.44it/s]
                                                 
[2024-06-02 06:18:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 52%|█████▏    | 102/195 [00:50<00:27,  3.44it/s]
 53%|█████▎    | 103/195 [00:51<00:43,  2.13it/s]
                                                 
[2024-06-02 06:18:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 53%|█████▎    | 103/195 [00:51<00:43,  2.13it/s]
                                                 
[2024-06-02 06:18:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 53%|█████▎    | 103/195 [00:51<00:43,  2.13it/s]
 54%|█████▍    | 105/195 [00:51<00:30,  2.93it/s]
                                                 
[2024-06-02 06:18:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 54%|█████▍    | 105/195 [00:51<00:30,  2.93it/s]
 54%|█████▍    | 106/195 [00:51<00:26,  3.31it/s]
                                                 
[2024-06-02 06:18:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (4096,), dtype: float16
+
 54%|█████▍    | 106/195 [00:51<00:26,  3.31it/s]
                                                 
[2024-06-02 06:18:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 54%|█████▍    | 106/195 [00:52<00:26,  3.31it/s]
 55%|█████▌    | 108/195 [00:52<00:25,  3.47it/s]
                                                 
[2024-06-02 06:18:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 55%|█████▌    | 108/195 [00:52<00:25,  3.47it/s]
 56%|█████▌    | 109/195 [00:53<00:40,  2.15it/s]
                                                 
[2024-06-02 06:18:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 56%|█████▌    | 109/195 [00:53<00:40,  2.15it/s]
                                                 
[2024-06-02 06:18:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 56%|█████▌    | 109/195 [00:53<00:40,  2.15it/s]
 57%|█████▋    | 111/195 [00:53<00:28,  2.96it/s]
                                                 
[2024-06-02 06:18:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 57%|█████▋    | 111/195 [00:53<00:28,  2.96it/s]
 57%|█████▋    | 112/195 [00:53<00:24,  3.33it/s]
                                                 
[2024-06-02 06:18:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (4096,), dtype: float16
+
 57%|█████▋    | 112/195 [00:53<00:24,  3.33it/s]
                                                 
[2024-06-02 06:18:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 57%|█████▋    | 112/195 [00:54<00:24,  3.33it/s]
 58%|█████▊    | 114/195 [00:54<00:23,  3.49it/s]
                                                 
[2024-06-02 06:18:17] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 58%|█████▊    | 114/195 [00:54<00:23,  3.49it/s]
 59%|█████▉    | 115/195 [00:55<00:37,  2.16it/s]
                                                 
[2024-06-02 06:18:17] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 59%|█████▉    | 115/195 [00:55<00:37,  2.16it/s]
                                                 
[2024-06-02 06:18:17] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 59%|█████▉    | 115/195 [00:55<00:37,  2.16it/s]
 60%|██████    | 117/195 [00:55<00:26,  2.95it/s]
                                                 
[2024-06-02 06:18:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 60%|██████    | 117/195 [00:55<00:26,  2.95it/s]
 61%|██████    | 118/195 [00:56<00:23,  3.34it/s]
                                                 
[2024-06-02 06:18:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (4096,), dtype: float16
+
 61%|██████    | 118/195 [00:56<00:23,  3.34it/s]
                                                 
[2024-06-02 06:18:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 61%|██████    | 118/195 [00:56<00:23,  3.34it/s]
 62%|██████▏   | 120/195 [00:56<00:21,  3.49it/s]
                                                 
[2024-06-02 06:18:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 62%|██████▏   | 120/195 [00:57<00:21,  3.49it/s]
 62%|██████▏   | 121/195 [00:57<00:34,  2.16it/s]
                                                 
[2024-06-02 06:18:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 62%|██████▏   | 121/195 [00:57<00:34,  2.16it/s]
                                                 
[2024-06-02 06:18:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 62%|██████▏   | 121/195 [00:57<00:34,  2.16it/s]
 63%|██████▎   | 123/195 [00:57<00:24,  2.97it/s]
                                                 
[2024-06-02 06:18:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 63%|██████▎   | 123/195 [00:58<00:24,  2.97it/s]
 64%|██████▎   | 124/195 [00:58<00:21,  3.34it/s]
                                                 
[2024-06-02 06:18:20] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Mistral-7B-Instruct-v0.3/model-00001-of-00003.safetensors
+
 64%|██████▎   | 124/195 [00:58<00:21,  3.34it/s]
                                                 
[2024-06-02 06:18:20] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Mistral-7B-Instruct-v0.3/model-00002-of-00003.safetensors
+
 64%|██████▎   | 124/195 [00:58<00:21,  3.34it/s]
                                                 
[2024-06-02 06:18:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (4096,), dtype: float16
+
 64%|██████▎   | 124/195 [01:03<00:21,  3.34it/s]
 64%|██████▍   | 125/195 [01:03<01:43,  1.48s/it]
                                                 
[2024-06-02 06:18:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 64%|██████▍   | 125/195 [01:03<01:43,  1.48s/it]
 65%|██████▍   | 126/195 [01:04<01:25,  1.24s/it]
                                                 
[2024-06-02 06:18:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 65%|██████▍   | 126/195 [01:04<01:25,  1.24s/it]
                                                 
[2024-06-02 06:18:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (4096,), dtype: float16
+
 65%|██████▍   | 126/195 [01:04<01:25,  1.24s/it]
                                                 
[2024-06-02 06:18:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 65%|██████▍   | 126/195 [01:04<01:25,  1.24s/it]
 66%|██████▌   | 129/195 [01:04<00:45,  1.44it/s]
                                                 
[2024-06-02 06:18:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 66%|██████▌   | 129/195 [01:05<00:45,  1.44it/s]
 67%|██████▋   | 130/195 [01:05<00:50,  1.28it/s]
                                                 
[2024-06-02 06:18:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 67%|██████▋   | 130/195 [01:05<00:50,  1.28it/s]
                                                 
[2024-06-02 06:18:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 67%|██████▋   | 130/195 [01:05<00:50,  1.28it/s]
 68%|██████▊   | 132/195 [01:05<00:34,  1.83it/s]
                                                 
[2024-06-02 06:18:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 68%|██████▊   | 132/195 [01:06<00:34,  1.83it/s]
 68%|██████▊   | 133/195 [01:06<00:29,  2.14it/s]
                                                 
[2024-06-02 06:18:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (4096,), dtype: float16
+
 68%|██████▊   | 133/195 [01:06<00:29,  2.14it/s]
                                                 
[2024-06-02 06:18:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 68%|██████▊   | 133/195 [01:06<00:29,  2.14it/s]
 69%|██████▉   | 135/195 [01:06<00:23,  2.54it/s]
                                                 
[2024-06-02 06:18:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 69%|██████▉   | 135/195 [01:07<00:23,  2.54it/s]
 70%|██████▉   | 136/195 [01:07<00:32,  1.83it/s]
                                                 
[2024-06-02 06:18:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 70%|██████▉   | 136/195 [01:07<00:32,  1.83it/s]
                                                 
[2024-06-02 06:18:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 70%|██████▉   | 136/195 [01:07<00:32,  1.83it/s]
 71%|███████   | 138/195 [01:08<00:22,  2.55it/s]
                                                 
[2024-06-02 06:18:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 71%|███████   | 138/195 [01:08<00:22,  2.55it/s]
 71%|███████▏  | 139/195 [01:08<00:19,  2.92it/s]
                                                 
[2024-06-02 06:18:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (4096,), dtype: float16
+
 71%|███████▏  | 139/195 [01:08<00:19,  2.92it/s]
                                                 
[2024-06-02 06:18:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 71%|███████▏  | 139/195 [01:08<00:19,  2.92it/s]
 72%|█████��█▏  | 141/195 [01:08<00:16,  3.18it/s]
                                                 
[2024-06-02 06:18:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 72%|███████▏  | 141/195 [01:09<00:16,  3.18it/s]
 73%|███████▎  | 142/195 [01:09<00:25,  2.07it/s]
                                                 
[2024-06-02 06:18:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 73%|███████▎  | 142/195 [01:09<00:25,  2.07it/s]
                                                 
[2024-06-02 06:18:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 73%|███████▎  | 142/195 [01:09<00:25,  2.07it/s]
 74%|███████▍  | 144/195 [01:10<00:17,  2.85it/s]
                                                 
[2024-06-02 06:18:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 74%|███████▍  | 144/195 [01:10<00:17,  2.85it/s]
 74%|███████▍  | 145/195 [01:10<00:15,  3.23it/s]
                                                 
[2024-06-02 06:18:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (4096,), dtype: float16
+
 74%|███████▍  | 145/195 [01:10<00:15,  3.23it/s]
                                                 
[2024-06-02 06:18:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 74%|███████▍  | 145/195 [01:10<00:15,  3.23it/s]
 75%|███████▌  | 147/195 [01:10<00:14,  3.41it/s]
                                                 
[2024-06-02 06:18:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 75%|███████▌  | 147/195 [01:11<00:14,  3.41it/s]
 76%|███████▌  | 148/195 [01:11<00:21,  2.15it/s]
                                                 
[2024-06-02 06:18:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 76%|███████▌  | 148/195 [01:11<00:21,  2.15it/s]
                                                 
[2024-06-02 06:18:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 76%|███████▌  | 148/195 [01:12<00:21,  2.15it/s]
 77%|███████▋  | 150/195 [01:12<00:15,  2.97it/s]
                                                 
[2024-06-02 06:18:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 77%|███████▋  | 150/195 [01:12<00:15,  2.97it/s]
 77%|███████▋  | 151/195 [01:12<00:13,  3.36it/s]
                                                 
[2024-06-02 06:18:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (4096,), dtype: float16
+
 77%|███████▋  | 151/195 [01:12<00:13,  3.36it/s]
                                                 
[2024-06-02 06:18:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 77%|███████▋  | 151/195 [01:12<00:13,  3.36it/s]
 78%|███████▊  | 153/195 [01:12<00:11,  3.54it/s]
                                                 
[2024-06-02 06:18:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 78%|███████▊  | 153/195 [01:13<00:11,  3.54it/s]
 79%|███████▉  | 154/195 [01:13<00:18,  2.18it/s]
                                                 
[2024-06-02 06:18:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 79%|███████▉  | 154/195 [01:13<00:18,  2.18it/s]
                                                 
[2024-06-02 06:18:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 79%|███████▉  | 154/195 [01:14<00:18,  2.18it/s]
 80%|████████  | 156/195 [01:14<00:13,  2.99it/s]
                                                 
[2024-06-02 06:18:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 80%|████████  | 156/195 [01:14<00:13,  2.99it/s]
 81%|████████  | 157/195 [01:14<00:11,  3.34it/s]
                                                 
[2024-06-02 06:18:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (4096,), dtype: float16
+
 81%|████████  | 157/195 [01:14<00:11,  3.34it/s]
                                                 
[2024-06-02 06:18:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 81%|████████  | 157/195 [01:14<00:11,  3.34it/s]
 82%|████████▏ | 159/195 [01:14<00:10,  3.53it/s]
                                                 
[2024-06-02 06:18:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 82%|████████▏ | 159/195 [01:15<00:10,  3.53it/s]
 82%|████████▏ | 160/195 [01:16<00:19,  1.76it/s]
                                                 
[2024-06-02 06:18:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 82%|████████▏ | 160/195 [01:16<00:19,  1.76it/s]
                                                 
[2024-06-02 06:18:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 82%|████████▏ | 160/195 [01:16<00:19,  1.76it/s]
 83%|████████▎ | 162/195 [01:16<00:13,  2.48it/s]
                                                 
[2024-06-02 06:18:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 83%|████████▎ | 162/195 [01:16<00:13,  2.48it/s]
 84%|████████▎ | 163/195 [01:16<00:11,  2.84it/s]
                                                 
[2024-06-02 06:18:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (4096,), dtype: float16
+
 84%|████████▎ | 163/195 [01:16<00:11,  2.84it/s]
                                                 
[2024-06-02 06:18:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 84%|████████▎ | 163/195 [01:17<00:11,  2.84it/s]
 85%|████████▍ | 165/195 [01:17<00:09,  3.15it/s]
                                                 
[2024-06-02 06:18:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 85%|████████▍ | 165/195 [01:18<00:09,  3.15it/s]
 85%|████████▌ | 166/195 [01:19<00:20,  1.43it/s]
                                                 
[2024-06-02 06:18:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 85%|████████▌ | 166/195 [01:19<00:20,  1.43it/s]
                                                 
[2024-06-02 06:18:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 85%|████████▌ | 166/195 [01:19<00:20,  1.43it/s]
 86%|████████▌ | 168/195 [01:19<00:13,  2.07it/s]
                                                 
[2024-06-02 06:18:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 86%|████████▌ | 168/195 [01:19<00:13,  2.07it/s]
 87%|████████▋ | 169/195 [01:19<00:10,  2.41it/s]
                                                 
[2024-06-02 06:18:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (4096,), dtype: float16
+
 87%|████████▋ | 169/195 [01:19<00:10,  2.41it/s]
                                                 
[2024-06-02 06:18:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 87%|████████▋ | 169/195 [01:20<00:10,  2.41it/s]
 88%|████████▊ | 171/195 [01:20<00:08,  2.80it/s]
                                                 
[2024-06-02 06:18:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 88%|████████▊ | 171/195 [01:22<00:08,  2.80it/s]
 88%|████████▊ | 172/195 [01:22<00:17,  1.28it/s]
                                                 
[2024-06-02 06:18:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 88%|████████▊ | 172/195 [01:22<00:17,  1.28it/s]
                                                 
[2024-06-02 06:18:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 88%|████████▊ | 172/195 [01:22<00:17,  1.28it/s]
 89%|████████▉ | 174/195 [01:23<00:11,  1.87it/s]
                                                 
[2024-06-02 06:18:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 89%|████████▉ | 174/195 [01:23<00:11,  1.87it/s]
 90%|████████▉ | 175/195 [01:23<00:09,  2.19it/s]
                                                 
[2024-06-02 06:18:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (4096,), dtype: float16
+
 90%|████████▉ | 175/195 [01:23<00:09,  2.19it/s]
                                                 
[2024-06-02 06:18:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 90%|████████▉ | 175/195 [01:23<00:09,  2.19it/s]
 91%|█████████ | 177/195 [01:23<00:06,  2.59it/s]
                                                 
[2024-06-02 06:18:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 91%|█████████ | 177/195 [01:25<00:06,  2.59it/s]
 91%|█████████▏| 178/195 [01:25<00:11,  1.42it/s]
                                                 
[2024-06-02 06:18:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 91%|█████████▏| 178/195 [01:25<00:11,  1.42it/s]
                                                 
[2024-06-02 06:18:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 91%|█████████▏| 178/195 [01:25<00:11,  1.42it/s]
 92%|█████████▏| 180/195 [01:25<00:07,  2.04it/s]
                                                 
[2024-06-02 06:18:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 92%|█████████▏| 180/195 [01:26<00:07,  2.04it/s]
 93%|█████████▎| 181/195 [01:26<00:05,  2.37it/s]
                                                 
[2024-06-02 06:18:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (4096,), dtype: float16
+
 93%|█████████▎| 181/195 [01:26<00:05,  2.37it/s]
                                                 
[2024-06-02 06:18:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 93%|█████████▎| 181/195 [01:26<00:05,  2.37it/s]
 94%|█████████▍| 183/195 [01:26<00:04,  2.72it/s]
                                                 
[2024-06-02 06:18:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 94%|█████████▍| 183/195 [01:28<00:04,  2.72it/s]
 94%|█████████▍| 184/195 [01:28<00:07,  1.38it/s]
                                                 
[2024-06-02 06:18:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 94%|█████████▍| 184/195 [01:28<00:07,  1.38it/s]
                                                 
[2024-06-02 06:18:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 94%|█████████▍| 184/195 [01:28<00:07,  1.38it/s]
 95%|█████████▌| 186/195 [01:29<00:04,  1.99it/s]
                                                 
[2024-06-02 06:18:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 95%|█████████▌| 186/195 [01:29<00:04,  1.99it/s]
 96%|█████████▌| 187/195 [01:29<00:03,  2.32it/s]
                                                 
[2024-06-02 06:18:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (4096,), dtype: float16
+
 96%|█████████▌| 187/195 [01:29<00:03,  2.32it/s]
                                                 
[2024-06-02 06:18:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 96%|█████████▌| 187/195 [01:29<00:03,  2.32it/s]
 97%|█████████▋| 189/195 [01:29<00:02,  2.64it/s]
                                                 
[2024-06-02 06:18:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 97%|█████████▋| 189/195 [01:30<00:02,  2.64it/s]
 97%|█████████▋| 190/195 [01:31<00:02,  1.70it/s]
                                                 
[2024-06-02 06:18:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 97%|█████████▋| 190/195 [01:31<00:02,  1.70it/s]
                                                 
[2024-06-02 06:18:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 97%|█████████▋| 190/195 [01:31<00:02,  1.70it/s]
 98%|█████████▊| 192/195 [01:31<00:01,  2.39it/s]
                                                 
[2024-06-02 06:18:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 98%|█████████▊| 192/195 [01:31<00:01,  2.39it/s]
 99%|█████████▉| 193/195 [01:31<00:00,  2.75it/s]
                                                 
[2024-06-02 06:18:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 99%|█████████▉| 193/195 [01:31<00:00,  2.75it/s]
 99%|█████████▉| 194/195 [01:31<00:00,  2.97it/s]
                                                 
[2024-06-02 06:18:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 99%|█████████▉| 194/195 [01:31<00:00,  2.97it/s]
100%|██████████| 195/195 [01:31<00:00,  3.39it/s]
100%|██████████| 195/195 [01:31<00:00,  2.12it/s]
+[2024-06-02 06:18:54] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Mistral-7B-Instruct-v0.3/model-00002-of-00003.safetensors
+[2024-06-02 06:18:54] INFO stats.py:77: Time usage: HF loading: 16.591 sec; Pre-quantization mapping: 34.492 sec; Quantization: 0.000 sec
+[2024-06-02 06:18:54] INFO stats.py:91: RAM usage: Peak RAM: 9.313 GB. Total bytes loaded from disk: 27.001 GB
+[2024-06-02 06:18:54] INFO convert_weight.py:155: Parameter size after quantization: 13.500 GB
+[2024-06-02 06:18:54] INFO convert_weight.py:160: Total parameters: 7,248,023,552
+[2024-06-02 06:18:54] INFO convert_weight.py:161: Bits per parameter: 16.000
+[2024-06-02 06:18:54] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC
+
+All finished, 131 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC/ndarray-cache.json
+/home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm gen_config /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3 --quantization q0f16 --conv-template mistral_default --output /ssd2/models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC
+[2024-06-02 04:09:14] INFO auto_config.py:115: Found model configuration: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/config.json
+[2024-06-02 04:09:14] INFO auto_config.py:153: Found model type: mistral. Use `--model-type` to override.
+[2024-06-02 04:09:14] INFO mistral_model.py:56: prefill_chunk_size defaults to 2048
+[2024-06-02 04:09:14] INFO config.py:106: Overriding max_batch_size from 1 to 80
+[2024-06-02 04:09:14] INFO gen_config.py:142: [generation_config.json] Setting bos_token_id: 1
+[2024-06-02 04:09:14] INFO gen_config.py:142: [generation_config.json] Setting eos_token_id: 2
+[2024-06-02 04:09:14] INFO gen_config.py:154: Found tokenizer config: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/tokenizer.model. Copying to /ssd2/models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC/tokenizer.model
+[2024-06-02 04:09:14] INFO gen_config.py:154: Found tokenizer config: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/tokenizer.json. Copying to /ssd2/models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC/tokenizer.json
+[2024-06-02 04:09:14] INFO gen_config.py:156: Not found tokenizer config: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/vocab.json
+[2024-06-02 04:09:14] INFO gen_config.py:156: Not found tokenizer config: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/merges.txt
+[2024-06-02 04:09:14] INFO gen_config.py:156: Not found tokenizer config: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/added_tokens.json
+[2024-06-02 04:09:14] INFO gen_config.py:154: Found tokenizer config: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/tokenizer_config.json. Copying to /ssd2/models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC/tokenizer_config.json
+[2024-06-02 04:09:14] INFO gen_config.py:215: Detected tokenizer info: {'token_postproc_method': 'byte_fallback', 'prepend_space_in_encode': False, 'strip_space_in_decode': True}
+[2024-06-02 04:09:14] INFO gen_config.py:31: [System default] Setting pad_token_id: 0
+[2024-06-02 04:09:14] INFO gen_config.py:31: [System default] Setting temperature: 1.0
+[2024-06-02 04:09:14] INFO gen_config.py:31: [System default] Setting presence_penalty: 0.0
+[2024-06-02 04:09:14] INFO gen_config.py:31: [System default] Setting frequency_penalty: 0.0
+[2024-06-02 04:09:14] INFO gen_config.py:31: [System default] Setting repetition_penalty: 1.0
+[2024-06-02 04:09:14] INFO gen_config.py:31: [System default] Setting top_p: 1.0
+[2024-06-02 04:09:14] INFO gen_config.py:31: [System default] Setting mean_gen_len: 128
+[2024-06-02 04:09:14] INFO gen_config.py:31: [System default] Setting max_gen_len: 512
+[2024-06-02 04:09:14] INFO gen_config.py:31: [System default] Setting shift_fill_factor: 0.3
+[2024-06-02 04:09:14] INFO gen_config.py:222: Dumping configuration file to: /ssd2/models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC/mlc-chat-config.json
+/home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm convert_weight /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3 --quantization q0f16 --output /ssd2/models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC
+[2024-06-02 04:09:15] INFO auto_config.py:115: Found model configuration: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/config.json
+[2024-06-02 04:09:16] INFO auto_device.py:79: Found device: cuda:0
+[2024-06-02 04:09:16] INFO auto_device.py:79: Found device: cuda:1
+[2024-06-02 04:09:17] INFO auto_device.py:88: Not found device: rocm:0
+[2024-06-02 04:09:18] INFO auto_device.py:88: Not found device: metal:0
+[2024-06-02 04:09:19] INFO auto_device.py:79: Found device: vulkan:0
+[2024-06-02 04:09:19] INFO auto_device.py:79: Found device: vulkan:1
+[2024-06-02 04:09:19] INFO auto_device.py:79: Found device: vulkan:2
+[2024-06-02 04:09:20] INFO auto_device.py:88: Not found device: opencl:0
+[2024-06-02 04:09:20] INFO auto_device.py:35: Using device: cuda:0
+[2024-06-02 04:09:20] INFO auto_weight.py:70: Finding weights in: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3
+[2024-06-02 04:09:20] INFO auto_weight.py:136: Not found Huggingface PyTorch
+[2024-06-02 04:09:20] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/model.safetensors.index.json
+[2024-06-02 04:09:20] INFO auto_weight.py:106: Using source weight configuration: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/model.safetensors.index.json. Use `--source` to override.
+[2024-06-02 04:09:20] INFO auto_weight.py:110: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
+[2024-06-02 04:09:20] INFO auto_config.py:153: Found model type: mistral. Use `--model-type` to override.
+[2024-06-02 04:09:20] INFO mistral_model.py:56: prefill_chunk_size defaults to 2048
+Weight conversion with arguments:
+  --config          /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/config.json
+  --quantization    NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16')
+  --model-type      mistral
+  --device          cuda:0
+  --source          /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/model.safetensors.index.json
+  --source-format   huggingface-safetensor
+  --output          /ssd2/models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC
+Start storing to cache /ssd2/models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC
+
  0%|          | 0/195 [00:00<?, ?it/s]
                                       
[2024-06-02 04:09:22] INFO huggingface_loader.py:184: Loading HF parameters from: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/model-00003-of-00003.safetensors
+
  0%|          | 0/195 [00:00<?, ?it/s]
                                       
[2024-06-02 04:09:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "lm_head.weight", shape: (32768, 4096), dtype: float16
+
  0%|          | 0/195 [00:02<?, ?it/s]
  1%|          | 1/195 [00:03<10:34,  3.27s/it]
                                               
[2024-06-02 04:09:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (4096,), dtype: float16
+
  1%|          | 1/195 [00:03<10:34,  3.27s/it]
                                               
[2024-06-02 04:09:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
  1%|          | 1/195 [00:03<10:34,  3.27s/it]
  2%|▏         | 3/195 [00:04<03:37,  1.13s/it]
                                               
[2024-06-02 04:09:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
  2%|▏         | 3/195 [00:04<03:37,  1.13s/it]
  2%|▏         | 4/195 [00:05<04:04,  1.28s/it]
                                               
[2024-06-02 04:09:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
  2%|▏         | 4/195 [00:05<04:04,  1.28s/it]
                                               
[2024-06-02 04:09:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (4096,), dtype: float16
+
  2%|▏         | 4/195 [00:05<04:04,  1.28s/it]
                                               
[2024-06-02 04:09:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
  2%|▏         | 4/195 [00:05<04:04,  1.28s/it]
  4%|▎         | 7/195 [00:06<02:05,  1.50it/s]
                                               
[2024-06-02 04:09:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
  4%|▎         | 7/195 [00:06<02:05,  1.50it/s]
  4%|▍         | 8/195 [00:07<02:41,  1.16it/s]
                                               
[2024-06-02 04:09:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
  4%|▍         | 8/195 [00:07<02:41,  1.16it/s]
                                               
[2024-06-02 04:09:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
  4%|▍         | 8/195 [00:08<02:41,  1.16it/s]
  5%|▌         | 10/195 [00:08<01:50,  1.68it/s]
                                                
[2024-06-02 04:09:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
  5%|▌         | 10/195 [00:08<01:50,  1.68it/s]
  6%|▌         | 11/195 [00:08<01:34,  1.94it/s]
                                                
[2024-06-02 04:09:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (4096,), dtype: float16
+
  6%|▌         | 11/195 [00:08<01:34,  1.94it/s]
                                                
[2024-06-02 04:09:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.24.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
  6%|▌         | 11/195 [00:08<01:34,  1.94it/s]
  7%|▋         | 13/195 [00:09<01:23,  2.17it/s]
                                                
[2024-06-02 04:09:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.24.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
  7%|▋         | 13/195 [00:09<01:23,  2.17it/s]
  7%|▋         | 14/195 [00:10<02:05,  1.44it/s]
                                                
[2024-06-02 04:09:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
  7%|▋         | 14/195 [00:10<02:05,  1.44it/s]
                                                
[2024-06-02 04:09:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.24.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
  7%|▋         | 14/195 [00:10<02:05,  1.44it/s]
  8%|▊         | 16/195 [00:11<01:28,  2.02it/s]
                                                
[2024-06-02 04:09:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.24.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
  8%|▊         | 16/195 [00:11<01:28,  2.02it/s]
  9%|▊         | 17/195 [00:11<01:17,  2.29it/s]
                                                
[2024-06-02 04:09:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (4096,), dtype: float16
+
  9%|▊         | 17/195 [00:11<01:17,  2.29it/s]
                                                
[2024-06-02 04:09:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.25.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
  9%|▊         | 17/195 [00:11<01:17,  2.29it/s]
 10%|▉         | 19/195 [00:12<01:12,  2.42it/s]
                                                
[2024-06-02 04:09:34] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.25.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 10%|▉         | 19/195 [00:12<01:12,  2.42it/s]
 10%|█         | 20/195 [00:13<01:54,  1.53it/s]
                                                
[2024-06-02 04:09:35] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 10%|█         | 20/195 [00:13<01:54,  1.53it/s]
                                                
[2024-06-02 04:09:36] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.25.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 10%|█         | 20/195 [00:13<01:54,  1.53it/s]
 11%|█▏        | 22/195 [00:13<01:21,  2.13it/s]
                                                
[2024-06-02 04:09:36] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.25.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 11%|█▏        | 22/195 [00:14<01:21,  2.13it/s]
 12%|█▏        | 23/195 [00:14<01:11,  2.40it/s]
                                                
[2024-06-02 04:09:36] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (4096,), dtype: float16
+
 12%|█▏        | 23/195 [00:14<01:11,  2.40it/s]
                                                
[2024-06-02 04:09:36] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.26.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 12%|█▏        | 23/195 [00:14<01:11,  2.40it/s]
 13%|█▎        | 25/195 [00:14<01:07,  2.50it/s]
                                                
[2024-06-02 04:09:37] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.26.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 13%|█▎        | 25/195 [00:15<01:07,  2.50it/s]
 13%|█▎        | 26/195 [00:16<01:48,  1.56it/s]
                                                
[2024-06-02 04:09:38] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 13%|█▎        | 26/195 [00:16<01:48,  1.56it/s]
                                                
[2024-06-02 04:09:38] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.26.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 13%|█▎        | 26/195 [00:16<01:48,  1.56it/s]
 14%|█▍        | 28/195 [00:16<01:17,  2.15it/s]
                                                
[2024-06-02 04:09:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.26.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 14%|█▍        | 28/195 [00:16<01:17,  2.15it/s]
 15%|█▍        | 29/195 [00:17<01:08,  2.42it/s]
                                                
[2024-06-02 04:09:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (4096,), dtype: float16
+
 15%|█▍        | 29/195 [00:17<01:08,  2.42it/s]
                                                
[2024-06-02 04:09:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.27.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 15%|█▍        | 29/195 [00:17<01:08,  2.42it/s]
 16%|█▌        | 31/195 [00:17<01:05,  2.51it/s]
                                                
[2024-06-02 04:09:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.27.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 16%|█▌        | 31/195 [00:18<01:05,  2.51it/s]
 16%|█▋        | 32/195 [00:19<01:44,  1.56it/s]
                                                
[2024-06-02 04:09:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 16%|█▋        | 32/195 [00:19<01:44,  1.56it/s]
                                                
[2024-06-02 04:09:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.27.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 16%|█▋        | 32/195 [00:19<01:44,  1.56it/s]
 17%|█▋        | 34/195 [00:19<01:14,  2.16it/s]
                                                
[2024-06-02 04:09:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.27.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 17%|█▋        | 34/195 [00:19<01:14,  2.16it/s]
 18%|█▊        | 35/195 [00:19<01:05,  2.43it/s]
                                                
[2024-06-02 04:09:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.28.input_layernorm.weight", shape: (4096,), dtype: float16
+
 18%|█▊        | 35/195 [00:19<01:05,  2.43it/s]
                                                
[2024-06-02 04:09:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.28.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 18%|█▊        | 35/195 [00:20<01:05,  2.43it/s]
 19%|█▉        | 37/195 [00:20<01:02,  2.53it/s]
                                                
[2024-06-02 04:09:43] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.28.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 19%|█▉        | 37/195 [00:21<01:02,  2.53it/s]
 19%|█▉        | 38/195 [00:22<01:39,  1.58it/s]
                                                
[2024-06-02 04:09:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.28.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 19%|█▉        | 38/195 [00:22<01:39,  1.58it/s]
                                                
[2024-06-02 04:09:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.28.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 19%|█▉        | 38/195 [00:22<01:39,  1.58it/s]
 21%|██        | 40/195 [00:22<01:10,  2.19it/s]
                                                
[2024-06-02 04:09:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.28.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 21%|██        | 40/195 [00:22<01:10,  2.19it/s]
 21%|██        | 41/195 [00:22<01:02,  2.46it/s]
                                                
[2024-06-02 04:09:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.29.input_layernorm.weight", shape: (4096,), dtype: float16
+
 21%|██        | 41/195 [00:22<01:02,  2.46it/s]
                                                
[2024-06-02 04:09:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.29.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 21%|██        | 41/195 [00:22<01:02,  2.46it/s]
 22%|██▏       | 43/195 [00:23<01:00,  2.53it/s]
                                                
[2024-06-02 04:09:46] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.29.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 22%|██▏       | 43/195 [00:23<01:00,  2.53it/s]
 23%|██▎       | 44/195 [00:24<01:36,  1.57it/s]
                                                
[2024-06-02 04:09:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.29.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 23%|██▎       | 44/195 [00:24<01:36,  1.57it/s]
                                                
[2024-06-02 04:09:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.29.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 23%|██▎       | 44/195 [00:25<01:36,  1.57it/s]
 24%|██▎       | 46/195 [00:25<01:09,  2.15it/s]
                                                
[2024-06-02 04:09:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.29.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 24%|██▎       | 46/195 [00:25<01:09,  2.15it/s]
 24%|██▍       | 47/195 [00:25<01:01,  2.42it/s]
                                                
[2024-06-02 04:09:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.30.input_layernorm.weight", shape: (4096,), dtype: float16
+
 24%|██▍       | 47/195 [00:25<01:01,  2.42it/s]
                                                
[2024-06-02 04:09:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.30.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 24%|██▍       | 47/195 [00:25<01:01,  2.42it/s]
 25%|██▌       | 49/195 [00:26<00:58,  2.51it/s]
                                                
[2024-06-02 04:09:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.30.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 25%|██▌       | 49/195 [00:26<00:58,  2.51it/s]
 26%|██▌       | 50/195 [00:27<01:32,  1.56it/s]
                                                
[2024-06-02 04:09:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.30.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 26%|██▌       | 50/195 [00:27<01:32,  1.56it/s]
                                                
[2024-06-02 04:09:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.30.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 26%|██▌       | 50/195 [00:27<01:32,  1.56it/s]
 27%|██▋       | 52/195 [00:28<01:06,  2.16it/s]
                                                
[2024-06-02 04:09:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.30.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 27%|██▋       | 52/195 [00:28<01:06,  2.16it/s]
 27%|██▋       | 53/195 [00:28<00:58,  2.42it/s]
                                                
[2024-06-02 04:09:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.31.input_layernorm.weight", shape: (4096,), dtype: float16
+
 27%|██▋       | 53/195 [00:28<00:58,  2.42it/s]
                                                
[2024-06-02 04:09:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.31.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 27%|██▋       | 53/195 [00:28<00:58,  2.42it/s]
 28%|██▊       | 55/195 [00:29<00:55,  2.53it/s]
                                                
[2024-06-02 04:09:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.31.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 28%|██▊       | 55/195 [00:29<00:55,  2.53it/s]
 29%|██▊       | 56/195 [00:30<01:29,  1.56it/s]
                                                
[2024-06-02 04:09:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.31.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 29%|██▊       | 56/195 [00:30<01:29,  1.56it/s]
                                                
[2024-06-02 04:09:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.31.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 29%|██▊       | 56/195 [00:30<01:29,  1.56it/s]
 30%|██▉       | 58/195 [00:31<01:03,  2.16it/s]
                                                
[2024-06-02 04:09:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.31.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 30%|██▉       | 58/195 [00:31<01:03,  2.16it/s]
 30%|███       | 59/195 [00:31<00:56,  2.43it/s]
                                                
[2024-06-02 04:09:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.norm.weight", shape: (4096,), dtype: float16
+
 30%|███       | 59/195 [00:31<00:56,  2.43it/s]
                                                
[2024-06-02 04:09:53] INFO huggingface_loader.py:196: Unloading HF weight file: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/model-00003-of-00003.safetensors
+
 30%|███       | 59/195 [00:31<00:56,  2.43it/s]
                                                
[2024-06-02 04:09:53] INFO huggingface_loader.py:184: Loading HF parameters from: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/model-00001-of-00003.safetensors
+
 30%|███       | 59/195 [00:31<00:56,  2.43it/s]
                                                
[2024-06-02 04:09:55] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.embed_tokens.weight", shape: (32768, 4096), dtype: float16
+
 30%|███       | 59/195 [00:32<00:56,  2.43it/s]
 31%|███▏      | 61/195 [00:34<01:45,  1.27it/s]
                                                
[2024-06-02 04:09:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (4096,), dtype: float16
+
 31%|███▏      | 61/195 [00:34<01:45,  1.27it/s]
                                                
[2024-06-02 04:09:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 31%|███▏      | 61/195 [00:34<01:45,  1.27it/s]
 32%|███▏      | 63/195 [00:34<01:24,  1.55it/s]
                                                
[2024-06-02 04:09:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 32%|███▏      | 63/195 [00:35<01:24,  1.55it/s]
 33%|███▎      | 64/195 [00:36<01:47,  1.22it/s]
                                                
[2024-06-02 04:09:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 33%|███▎      | 64/195 [00:36<01:47,  1.22it/s]
                                                
[2024-06-02 04:09:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 33%|███▎      | 64/195 [00:36<01:47,  1.22it/s]
 34%|███▍      | 66/195 [00:36<01:19,  1.63it/s]
                                                
[2024-06-02 04:09:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 34%|███▍      | 66/195 [00:36<01:19,  1.63it/s]
 34%|███▍      | 67/195 [00:37<01:07,  1.88it/s]
                                                
[2024-06-02 04:09:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (4096,), dtype: float16
+
 34%|███▍      | 67/195 [00:37<01:07,  1.88it/s]
                                                
[2024-06-02 04:09:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 34%|███▍      | 67/195 [00:37<01:07,  1.88it/s]
 35%|███▌      | 69/195 [00:37<00:59,  2.12it/s]
                                                
[2024-06-02 04:10:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 35%|███▌      | 69/195 [00:38<00:59,  2.12it/s]
 36%|███▌      | 70/195 [00:39<01:26,  1.44it/s]
                                                
[2024-06-02 04:10:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 36%|███▌      | 70/195 [00:39<01:26,  1.44it/s]
                                                
[2024-06-02 04:10:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 36%|███▌      | 70/195 [00:39<01:26,  1.44it/s]
 37%|███▋      | 72/195 [00:39<01:04,  1.89it/s]
                                                
[2024-06-02 04:10:02] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 37%|███▋      | 72/195 [00:39<01:04,  1.89it/s]
 37%|███▋      | 73/195 [00:40<00:56,  2.17it/s]
                                                
[2024-06-02 04:10:02] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 37%|███▋      | 73/195 [00:40<00:56,  2.17it/s]
 38%|███▊      | 74/195 [00:41<01:25,  1.41it/s]
                                                
[2024-06-02 04:10:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 38%|███▊      | 74/195 [00:41<01:25,  1.41it/s]
 38%|███▊      | 75/195 [00:41<01:13,  1.63it/s]
                                                
[2024-06-02 04:10:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 38%|███▊      | 75/195 [00:41<01:13,  1.63it/s]
 39%|███▉      | 76/195 [00:42<01:00,  1.97it/s]
                                                
[2024-06-02 04:10:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (4096,), dtype: float16
+
 39%|███▉      | 76/195 [00:42<01:00,  1.97it/s]
                                                
[2024-06-02 04:10:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 39%|███▉      | 76/195 [00:42<01:00,  1.97it/s]
 40%|████      | 78/195 [00:42<00:52,  2.23it/s]
                                                
[2024-06-02 04:10:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 40%|████      | 78/195 [00:43<00:52,  2.23it/s]
 41%|████      | 79/195 [00:44<01:21,  1.42it/s]
                                                
[2024-06-02 04:10:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 41%|████      | 79/195 [00:44<01:21,  1.42it/s]
                                                
[2024-06-02 04:10:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 41%|████      | 79/195 [00:44<01:21,  1.42it/s]
 42%|████▏     | 81/195 [00:44<00:55,  2.05it/s]
                                                
[2024-06-02 04:10:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 42%|████▏     | 81/195 [00:44<00:55,  2.05it/s]
 42%|████▏     | 82/195 [00:44<00:48,  2.34it/s]
                                                
[2024-06-02 04:10:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (4096,), dtype: float16
+
 42%|████▏     | 82/195 [00:44<00:48,  2.34it/s]
                                                
[2024-06-02 04:10:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 42%|████▏     | 82/195 [00:45<00:48,  2.34it/s]
 43%|████▎     | 84/195 [00:45<00:44,  2.47it/s]
                                                
[2024-06-02 04:10:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 43%|████▎     | 84/195 [00:46<00:44,  2.47it/s]
 44%|████▎     | 85/195 [00:47<01:11,  1.54it/s]
                                                
[2024-06-02 04:10:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 44%|████▎     | 85/195 [00:47<01:11,  1.54it/s]
                                                
[2024-06-02 04:10:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 44%|████▎     | 85/195 [00:47<01:11,  1.54it/s]
 45%|████▍     | 87/195 [00:47<00:49,  2.16it/s]
                                                
[2024-06-02 04:10:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 45%|████▍     | 87/195 [00:47<00:49,  2.16it/s]
 45%|████▌     | 88/195 [00:47<00:43,  2.45it/s]
                                                
[2024-06-02 04:10:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (4096,), dtype: float16
+
 45%|████▌     | 88/195 [00:47<00:43,  2.45it/s]
                                                
[2024-06-02 04:10:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 45%|████▌     | 88/195 [00:47<00:43,  2.45it/s]
 46%|████▌     | 90/195 [00:48<00:41,  2.54it/s]
                                                
[2024-06-02 04:10:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 46%|████▌     | 90/195 [00:48<00:41,  2.54it/s]
 47%|████▋     | 91/195 [00:50<01:06,  1.56it/s]
                                                
[2024-06-02 04:10:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 47%|████▋     | 91/195 [00:50<01:06,  1.56it/s]
                                                
[2024-06-02 04:10:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 47%|████▋     | 91/195 [00:50<01:06,  1.56it/s]
 48%|████▊     | 93/195 [00:50<00:47,  2.15it/s]
                                                
[2024-06-02 04:10:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 48%|████▊     | 93/195 [00:50<00:47,  2.15it/s]
 48%|████▊     | 94/195 [00:50<00:41,  2.44it/s]
                                                
[2024-06-02 04:10:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (4096,), dtype: float16
+
 48%|████▊     | 94/195 [00:50<00:41,  2.44it/s]
                                                
[2024-06-02 04:10:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 48%|████▊     | 94/195 [00:50<00:41,  2.44it/s]
 49%|████▉     | 96/195 [00:51<00:39,  2.53it/s]
                                                
[2024-06-02 04:10:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 49%|████▉     | 96/195 [00:51<00:39,  2.53it/s]
 50%|████▉     | 97/195 [00:52<01:02,  1.57it/s]
                                                
[2024-06-02 04:10:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 50%|████▉     | 97/195 [00:52<01:02,  1.57it/s]
                                                
[2024-06-02 04:10:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 50%|████▉     | 97/195 [00:53<01:02,  1.57it/s]
 51%|█████     | 99/195 [00:53<00:43,  2.18it/s]
                                                
[2024-06-02 04:10:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 51%|█████     | 99/195 [00:53<00:43,  2.18it/s]
 51%|█████▏    | 100/195 [00:53<00:38,  2.48it/s]
                                                 
[2024-06-02 04:10:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (4096,), dtype: float16
+
 51%|█████▏    | 100/195 [00:53<00:38,  2.48it/s]
                                                 
[2024-06-02 04:10:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 51%|█████▏    | 100/195 [00:53<00:38,  2.48it/s]
 52%|█████▏    | 102/195 [00:54<00:36,  2.54it/s]
                                                 
[2024-06-02 04:10:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 52%|█████▏    | 102/195 [00:54<00:36,  2.54it/s]
 53%|█████▎    | 103/195 [00:55<00:58,  1.57it/s]
                                                 
[2024-06-02 04:10:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 53%|█████▎    | 103/195 [00:55<00:58,  1.57it/s]
                                                 
[2024-06-02 04:10:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 53%|█████▎    | 103/195 [00:55<00:58,  1.57it/s]
 54%|█████▍    | 105/195 [00:56<00:41,  2.19it/s]
                                                 
[2024-06-02 04:10:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 54%|█████▍    | 105/195 [00:56<00:41,  2.19it/s]
 54%|█████▍    | 106/195 [00:56<00:36,  2.47it/s]
                                                 
[2024-06-02 04:10:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (4096,), dtype: float16
+
 54%|█████▍    | 106/195 [00:56<00:36,  2.47it/s]
                                                 
[2024-06-02 04:10:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 54%|█████▍    | 106/195 [00:56<00:36,  2.47it/s]
 55%|█████▌    | 108/195 [00:56<00:34,  2.55it/s]
                                                 
[2024-06-02 04:10:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 55%|█████▌    | 108/195 [00:57<00:34,  2.55it/s]
 56%|█████▌    | 109/195 [00:58<00:54,  1.58it/s]
                                                 
[2024-06-02 04:10:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 56%|█████▌    | 109/195 [00:58<00:54,  1.58it/s]
                                                 
[2024-06-02 04:10:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 56%|█████▌    | 109/195 [00:58<00:54,  1.58it/s]
 57%|█████▋    | 111/195 [00:58<00:38,  2.19it/s]
                                                 
[2024-06-02 04:10:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 57%|█████▋    | 111/195 [00:58<00:38,  2.19it/s]
 57%|█████▋    | 112/195 [00:59<00:33,  2.45it/s]
                                                 
[2024-06-02 04:10:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (4096,), dtype: float16
+
 57%|█████▋    | 112/195 [00:59<00:33,  2.45it/s]
                                                 
[2024-06-02 04:10:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 57%|█████▋    | 112/195 [00:59<00:33,  2.45it/s]
 58%|█████▊    | 114/195 [00:59<00:31,  2.53it/s]
                                                 
[2024-06-02 04:10:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 58%|█████▊    | 114/195 [01:00<00:31,  2.53it/s]
 59%|█████▉    | 115/195 [01:01<00:50,  1.57it/s]
                                                 
[2024-06-02 04:10:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 59%|█████▉    | 115/195 [01:01<00:50,  1.57it/s]
                                                 
[2024-06-02 04:10:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 59%|█████▉    | 115/195 [01:01<00:50,  1.57it/s]
 60%|██████    | 117/195 [01:01<00:35,  2.19it/s]
                                                 
[2024-06-02 04:10:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 60%|██████    | 117/195 [01:01<00:35,  2.19it/s]
 61%|██████    | 118/195 [01:01<00:31,  2.47it/s]
                                                 
[2024-06-02 04:10:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (4096,), dtype: float16
+
 61%|██████    | 118/195 [01:01<00:31,  2.47it/s]
                                                 
[2024-06-02 04:10:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 61%|██████    | 118/195 [01:02<00:31,  2.47it/s]
 62%|██████▏   | 120/195 [01:02<00:29,  2.55it/s]
                                                 
[2024-06-02 04:10:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 62%|██████▏   | 120/195 [01:03<00:29,  2.55it/s]
 62%|██████▏   | 121/195 [01:04<00:46,  1.58it/s]
                                                 
[2024-06-02 04:10:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 62%|██████▏   | 121/195 [01:04<00:46,  1.58it/s]
                                                 
[2024-06-02 04:10:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 62%|██████▏   | 121/195 [01:04<00:46,  1.58it/s]
 63%|██████▎   | 123/195 [01:04<00:32,  2.19it/s]
                                                 
[2024-06-02 04:10:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 63%|██████▎   | 123/195 [01:04<00:32,  2.19it/s]
 64%|██████▎   | 124/195 [01:04<00:28,  2.47it/s]
                                                 
[2024-06-02 04:10:26] INFO huggingface_loader.py:196: Unloading HF weight file: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/model-00001-of-00003.safetensors
+
 64%|██████▎   | 124/195 [01:04<00:28,  2.47it/s]
                                                 
[2024-06-02 04:10:27] INFO huggingface_loader.py:184: Loading HF parameters from: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/model-00002-of-00003.safetensors
+
 64%|██████▎   | 124/195 [01:05<00:28,  2.47it/s]
                                                 
[2024-06-02 04:10:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (4096,), dtype: float16
+
 64%|██████▎   | 124/195 [01:05<00:28,  2.47it/s]
 64%|██████▍   | 125/195 [01:05<00:37,  1.89it/s]
                                                 
[2024-06-02 04:10:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 64%|██████▍   | 125/195 [01:05<00:37,  1.89it/s]
 65%|██████▍   | 126/195 [01:06<00:40,  1.72it/s]
                                                 
[2024-06-02 04:10:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 65%|██████▍   | 126/195 [01:06<00:40,  1.72it/s]
                                                 
[2024-06-02 04:10:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (4096,), dtype: float16
+
 65%|██████▍   | 126/195 [01:06<00:40,  1.72it/s]
                                                 
[2024-06-02 04:10:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 65%|██████▍   | 126/195 [01:06<00:40,  1.72it/s]
 66%|██████▌   | 129/195 [01:07<00:26,  2.45it/s]
                                                 
[2024-06-02 04:10:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 66%|██████▌   | 129/195 [01:07<00:26,  2.45it/s]
 67%|██████▋   | 130/195 [01:08<00:40,  1.59it/s]
                                                 
[2024-06-02 04:10:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 67%|██████▋   | 130/195 [01:08<00:40,  1.59it/s]
                                                 
[2024-06-02 04:10:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 67%|██████▋   | 130/195 [01:08<00:40,  1.59it/s]
 68%|██████▊   | 132/195 [01:08<00:29,  2.16it/s]
                                                 
[2024-06-02 04:10:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 68%|██████▊   | 132/195 [01:09<00:29,  2.16it/s]
 68%|██████▊   | 133/195 [01:09<00:25,  2.42it/s]
                                                 
[2024-06-02 04:10:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (4096,), dtype: float16
+
 68%|██████▊   | 133/195 [01:09<00:25,  2.42it/s]
                                                 
[2024-06-02 04:10:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 68%|██████▊   | 133/195 [01:09<00:25,  2.42it/s]
 69%|██████▉   | 135/195 [01:09<00:23,  2.51it/s]
                                                 
[2024-06-02 04:10:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 69%|██████▉   | 135/195 [01:10<00:23,  2.51it/s]
 70%|██████▉   | 136/195 [01:11<00:37,  1.57it/s]
                                                 
[2024-06-02 04:10:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 70%|██████▉   | 136/195 [01:11<00:37,  1.57it/s]
                                                 
[2024-06-02 04:10:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 70%|██████▉   | 136/195 [01:11<00:37,  1.57it/s]
 71%|███████   | 138/195 [01:11<00:26,  2.18it/s]
                                                 
[2024-06-02 04:10:34] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 71%|███████   | 138/195 [01:11<00:26,  2.18it/s]
 71%|███████▏  | 139/195 [01:12<00:22,  2.44it/s]
                                                 
[2024-06-02 04:10:34] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (4096,), dtype: float16
+
 71%|███████▏  | 139/195 [01:12<00:22,  2.44it/s]
                                                 
[2024-06-02 04:10:34] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 71%|███████▏  | 139/195 [01:12<00:22,  2.44it/s]
 72%|███████▏  | 141/195 [01:12<00:21,  2.53it/s]
                                                 
[2024-06-02 04:10:35] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 72%|███████▏  | 141/195 [01:13<00:21,  2.53it/s]
 73%|███████▎  | 142/195 [01:14<00:33,  1.57it/s]
                                                 
[2024-06-02 04:10:36] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 73%|███████▎  | 142/195 [01:14<00:33,  1.57it/s]
                                                 
[2024-06-02 04:10:36] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 73%|███████▎  | 142/195 [01:14<00:33,  1.57it/s]
 74%|██��████▍  | 144/195 [01:14<00:23,  2.16it/s]
                                                 
[2024-06-02 04:10:37] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 74%|███████▍  | 144/195 [01:14<00:23,  2.16it/s]
 74%|███████▍  | 145/195 [01:14<00:20,  2.44it/s]
                                                 
[2024-06-02 04:10:37] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (4096,), dtype: float16
+
 74%|███████▍  | 145/195 [01:14<00:20,  2.44it/s]
                                                 
[2024-06-02 04:10:37] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 74%|███████▍  | 145/195 [01:15<00:20,  2.44it/s]
 75%|███████▌  | 147/195 [01:15<00:18,  2.54it/s]
                                                 
[2024-06-02 04:10:38] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 75%|███████▌  | 147/195 [01:16<00:18,  2.54it/s]
 76%|███████▌  | 148/195 [01:17<00:29,  1.58it/s]
                                                 
[2024-06-02 04:10:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 76%|███████▌  | 148/195 [01:17<00:29,  1.58it/s]
                                                 
[2024-06-02 04:10:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 76%|███████▌  | 148/195 [01:17<00:29,  1.58it/s]
 77%|███████▋  | 150/195 [01:17<00:20,  2.17it/s]
                                                 
[2024-06-02 04:10:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 77%|███████▋  | 150/195 [01:17<00:20,  2.17it/s]
 77%|███████▋  | 151/195 [01:17<00:17,  2.46it/s]
                                                 
[2024-06-02 04:10:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (4096,), dtype: float16
+
 77%|███████▋  | 151/195 [01:17<00:17,  2.46it/s]
                                                 
[2024-06-02 04:10:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 77%|███████▋  | 151/195 [01:17<00:17,  2.46it/s]
 78%|███████▊  | 153/195 [01:18<00:16,  2.55it/s]
                                                 
[2024-06-02 04:10:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 78%|███████▊  | 153/195 [01:18<00:16,  2.55it/s]
 79%|███████▉  | 154/195 [01:19<00:25,  1.58it/s]
                                                 
[2024-06-02 04:10:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 79%|███████▉  | 154/195 [01:19<00:25,  1.58it/s]
                                                 
[2024-06-02 04:10:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 79%|███████▉  | 154/195 [01:20<00:25,  1.58it/s]
 80%|████████  | 156/195 [01:20<00:17,  2.17it/s]
                                                 
[2024-06-02 04:10:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 80%|████████  | 156/195 [01:20<00:17,  2.17it/s]
 81%|████████  | 157/195 [01:20<00:15,  2.46it/s]
                                                 
[2024-06-02 04:10:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (4096,), dtype: float16
+
 81%|████████  | 157/195 [01:20<00:15,  2.46it/s]
                                                 
[2024-06-02 04:10:43] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 81%|████████  | 157/195 [01:20<00:15,  2.46it/s]
 82%|████████▏ | 159/195 [01:21<00:14,  2.55it/s]
                                                 
[2024-06-02 04:10:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 82%|████████▏ | 159/195 [01:21<00:14,  2.55it/s]
 82%|████████▏ | 160/195 [01:22<00:22,  1.59it/s]
                                                 
[2024-06-02 04:10:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 82%|████████▏ | 160/195 [01:22<00:22,  1.59it/s]
                                                 
[2024-06-02 04:10:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 82%|████████▏ | 160/195 [01:22<00:22,  1.59it/s]
 83%|████████▎ | 162/195 [01:23<00:15,  2.20it/s]
                                                 
[2024-06-02 04:10:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 83%|████████▎ | 162/195 [01:23<00:15,  2.20it/s]
 84%|████████▎ | 163/195 [01:23<00:12,  2.47it/s]
                                                 
[2024-06-02 04:10:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (4096,), dtype: float16
+
 84%|████████▎ | 163/195 [01:23<00:12,  2.47it/s]
                                                 
[2024-06-02 04:10:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 84%|████████▎ | 163/195 [01:23<00:12,  2.47it/s]
 85%|████████▍ | 165/195 [01:24<00:11,  2.56it/s]
                                                 
[2024-06-02 04:10:46] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 85%|████████▍ | 165/195 [01:24<00:11,  2.56it/s]
 85%|████████▌ | 166/195 [01:25<00:18,  1.58it/s]
                                                 
[2024-06-02 04:10:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 85%|████████▌ | 166/195 [01:25<00:18,  1.58it/s]
                                                 
[2024-06-02 04:10:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 85%|████████▌ | 166/195 [01:25<00:18,  1.58it/s]
 86%|████████▌ | 168/195 [01:25<00:12,  2.18it/s]
                                                 
[2024-06-02 04:10:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 86%|████████▌ | 168/195 [01:25<00:12,  2.18it/s]
 87%|████████▋ | 169/195 [01:26<00:10,  2.45it/s]
                                                 
[2024-06-02 04:10:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (4096,), dtype: float16
+
 87%|████████▋ | 169/195 [01:26<00:10,  2.45it/s]
                                                 
[2024-06-02 04:10:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 87%|████████▋ | 169/195 [01:26<00:10,  2.45it/s]
 88%|████████▊ | 171/195 [01:26<00:09,  2.55it/s]
                                                 
[2024-06-02 04:10:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 88%|████████▊ | 171/195 [01:27<00:09,  2.55it/s]
 88%|████████▊ | 172/195 [01:28<00:14,  1.57it/s]
                                                 
[2024-06-02 04:10:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 88%|████████▊ | 172/195 [01:28<00:14,  1.57it/s]
                                                 
[2024-06-02 04:10:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 88%|████████▊ | 172/195 [01:28<00:14,  1.57it/s]
 89%|████████▉ | 174/195 [01:28<00:09,  2.17it/s]
                                                 
[2024-06-02 04:10:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 89%|██████��█▉ | 174/195 [01:28<00:09,  2.17it/s]
 90%|████████▉ | 175/195 [01:28<00:08,  2.44it/s]
                                                 
[2024-06-02 04:10:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (4096,), dtype: float16
+
 90%|████████▉ | 175/195 [01:28<00:08,  2.44it/s]
                                                 
[2024-06-02 04:10:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 90%|████████▉ | 175/195 [01:29<00:08,  2.44it/s]
 91%|█████████ | 177/195 [01:29<00:07,  2.53it/s]
                                                 
[2024-06-02 04:10:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 91%|█████████ | 177/195 [01:30<00:07,  2.53it/s]
 91%|█████████▏| 178/195 [01:31<00:10,  1.57it/s]
                                                 
[2024-06-02 04:10:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 91%|█████████▏| 178/195 [01:31<00:10,  1.57it/s]
                                                 
[2024-06-02 04:10:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 91%|█████████▏| 178/195 [01:31<00:10,  1.57it/s]
 92%|█████████▏| 180/195 [01:31<00:06,  2.17it/s]
                                                 
[2024-06-02 04:10:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 92%|█████████▏| 180/195 [01:31<00:06,  2.17it/s]
 93%|█████████▎| 181/195 [01:31<00:05,  2.44it/s]
                                                 
[2024-06-02 04:10:54] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (4096,), dtype: float16
+
 93%|█████████▎| 181/195 [01:31<00:05,  2.44it/s]
                                                 
[2024-06-02 04:10:54] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 93%|█████████▎| 181/195 [01:32<00:05,  2.44it/s]
 94%|█████████▍| 183/195 [01:32<00:04,  2.52it/s]
                                                 
[2024-06-02 04:10:55] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 94%|█████████▍| 183/195 [01:33<00:04,  2.52it/s]
 94%|█████████▍| 184/195 [01:34<00:07,  1.57it/s]
                                                 
[2024-06-02 04:10:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 94%|█████████▍| 184/195 [01:34<00:07,  1.57it/s]
                                                 
[2024-06-02 04:10:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 94%|█████████▍| 184/195 [01:34<00:07,  1.57it/s]
 95%|█████████▌| 186/195 [01:34<00:04,  2.17it/s]
                                                 
[2024-06-02 04:10:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 95%|█████████▌| 186/195 [01:34<00:04,  2.17it/s]
 96%|█████████▌| 187/195 [01:34<00:03,  2.44it/s]
                                                 
[2024-06-02 04:10:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (4096,), dtype: float16
+
 96%|█████████▌| 187/195 [01:34<00:03,  2.44it/s]
                                                 
[2024-06-02 04:10:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.mlp.down_proj.weight", shape: (4096, 14336), dtype: float16
+
 96%|█████████▌| 187/195 [01:34<00:03,  2.44it/s]
 97%|█████████▋| 189/195 [01:35<00:02,  2.52it/s]
                                                 
[2024-06-02 04:10:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.mlp.gate_up_proj.weight", shape: (28672, 4096), dtype: float16
+
 97%|█████████▋| 189/195 [01:35<00:02,  2.52it/s]
 97%|█████████▋| 190/195 [01:36<00:03,  1.56it/s]
                                                 
[2024-06-02 04:10:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 97%|█████████▋| 190/195 [01:36<00:03,  1.56it/s]
                                                 
[2024-06-02 04:10:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 97%|█████████▋| 190/195 [01:37<00:03,  1.56it/s]
 98%|█████████▊| 192/195 [01:37<00:01,  2.16it/s]
                                                 
[2024-06-02 04:10:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 98%|█████████▊| 192/195 [01:37<00:01,  2.16it/s]
 99%|█████████▉| 193/195 [01:37<00:00,  2.42it/s]
                                                 
[2024-06-02 04:10:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.self_attn.qkv_proj.weight", shape: (6144, 4096), dtype: float16
+
 99%|█████████▉| 193/195 [01:37<00:00,  2.42it/s]
 99%|█████████▉| 194/195 [01:37<00:00,  2.54it/s]
                                                 
[2024-06-02 04:11:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.self_attn.o_proj.weight", shape: (4096, 4096), dtype: float16
+
 99%|█████████▉| 194/195 [01:37<00:00,  2.54it/s]
100%|██████████| 195/195 [01:38<00:00,  2.85it/s]
100%|██████████| 195/195 [01:38<00:00,  1.99it/s]
+[2024-06-02 04:11:00] INFO huggingface_loader.py:196: Unloading HF weight file: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/model-00002-of-00003.safetensors
+[2024-06-02 04:11:00] INFO stats.py:76: Time usage: HF loading: 3.723 sec; Pre-quantization mapping: 27.572 sec; Quantization: 0.000 sec
+[2024-06-02 04:11:00] INFO stats.py:90: RAM usage: Peak RAM: 9.313 GB. Total bytes loaded from disk: 27.001 GB
+[2024-06-02 04:11:00] INFO convert_weight.py:155: Parameter size after quantization: 13.500 GB
+[2024-06-02 04:11:00] INFO convert_weight.py:160: Total parameters: 7,248,023,552
+[2024-06-02 04:11:00] INFO convert_weight.py:161: Bits per parameter: 16.000
+[2024-06-02 04:11:00] INFO convert_weight.py:166: Saved to directory: /ssd2/models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC
+
+All finished, 131 total shards committed, record saved to /ssd2/models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q0f16-MLC/ndarray-cache.json