Hugging Face's logo

mlc-ai
/
Mistral-7B-Instruct-v0.3-q4f16_1-MLC

MLC-LLM
web-llm
Model card Files Community
Mistral-7B-Instruct-v0.3-q4f16_1-MLC / logs.txt
riczhou's picture
riczhou
Initial commit
294948f verified
raw
history blame contribute delete
211 kB
/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Mistral-7B-Instruct-v0.3 --quantization q4f16_1 --conv-template mistral_default --output /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q4f16_1-MLC
[2024-06-02 06:21:25] INFO auto_config.py:116: Found model configuration: /models/Mistral-7B-Instruct-v0.3/config.json
[2024-06-02 06:21:25] INFO auto_config.py:154: Found model type: mistral. Use `--model-type` to override.
[2024-06-02 06:21:25] INFO mistral_model.py:56: prefill_chunk_size defaults to 2048
[2024-06-02 06:21:25] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-02 06:21:25] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 1
[2024-06-02 06:21:25] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: 2
[2024-06-02 06:21:25] 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-q4f16_1-MLC/tokenizer.model
[2024-06-02 06:21:25] 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-q4f16_1-MLC/tokenizer.json
[2024-06-02 06:21:25] INFO gen_config.py:157: Not found tokenizer config: /models/Mistral-7B-Instruct-v0.3/vocab.json
[2024-06-02 06:21:25] INFO gen_config.py:157: Not found tokenizer config: /models/Mistral-7B-Instruct-v0.3/merges.txt
[2024-06-02 06:21:25] INFO gen_config.py:157: Not found tokenizer config: /models/Mistral-7B-Instruct-v0.3/added_tokens.json
[2024-06-02 06:21:25] 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-q4f16_1-MLC/tokenizer_config.json
[2024-06-02 06:21:25] 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 06:21:25] INFO gen_config.py:32: [System default] Setting pad_token_id: 0
[2024-06-02 06:21:25] INFO gen_config.py:32: [System default] Setting temperature: 1.0
[2024-06-02 06:21:25] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-02 06:21:25] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-02 06:21:25] INFO gen_config.py:32: [System default] Setting repetition_penalty: 1.0
[2024-06-02 06:21:25] INFO gen_config.py:32: [System default] Setting top_p: 1.0
[2024-06-02 06:21:25] INFO gen_config.py:32: [System default] Setting mean_gen_len: 128
[2024-06-02 06:21:25] INFO gen_config.py:32: [System default] Setting max_gen_len: 512
[2024-06-02 06:21:25] INFO gen_config.py:32: [System default] Setting shift_fill_factor: 0.3
[2024-06-02 06:21:25] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q4f16_1-MLC/mlc-chat-config.json
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Mistral-7B-Instruct-v0.3 --quantization q4f16_1 --output /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q4f16_1-MLC
[2024-06-02 06:21:27] INFO auto_config.py:116: Found model configuration: /models/Mistral-7B-Instruct-v0.3/config.json
[2024-06-02 06:21:28] INFO auto_device.py:79: Found device: cuda:0
[2024-06-02 06:21:30] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-02 06:21:31] INFO auto_device.py:88: Not found device: metal:0
[2024-06-02 06:21:33] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-02 06:21:33] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-02 06:21:33] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-02 06:21:33] INFO auto_device.py:79: Found device: vulkan:3
[2024-06-02 06:21:34] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-02 06:21:34] INFO auto_device.py:35: Using device: cuda:0
[2024-06-02 06:21:34] INFO auto_weight.py:71: Finding weights in: /models/Mistral-7B-Instruct-v0.3
[2024-06-02 06:21:34] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-02 06:21:34] 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 06:21:34] 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 06:21:34] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-02 06:21:34] INFO auto_config.py:154: Found model type: mistral. Use `--model-type` to override.
[2024-06-02 06:21:34] 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 GroupQuantize(name='q4f16_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float16', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7)
--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-q4f16_1-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q4f16_1-MLC
0%| | 0/195 [00:00<?, ?it/s] [2024-06-02 06:21:36] 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 06:21:42] INFO group_quantization.py:217: Compiling quantize function for key: ((32768, 4096), float16, cuda, axis=1, output_transpose=False)
0%| | 0/195 [00:05<?, ?it/s] [2024-06-02 06:21:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_weight", shape: (32768, 512), dtype: uint32
0%| | 0/195 [00:06<?, ?it/s] [2024-06-02 06:21:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_scale", shape: (32768, 128), dtype: float16
0%| | 0/195 [00:06<?, ?it/s] 1%| | 1/195 [00:06<21:42, 6.72s/it] [2024-06-02 06:21:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (4096,), dtype: float16
1%| | 1/195 [00:06<21:42, 6.72s/it] [2024-06-02 06:21:43] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 14336), float16, cuda, axis=1, output_transpose=False)
1%| | 1/195 [00:06<21:42, 6.72s/it] [2024-06-02 06:21:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
1%| | 1/195 [00:07<21:42, 6.72s/it] [2024-06-02 06:21:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
1%| | 1/195 [00:07<21:42, 6.72s/it] 2%|▏ | 3/195 [00:07<06:35, 2.06s/it] [2024-06-02 06:21:45] INFO group_quantization.py:217: Compiling quantize function for key: ((28672, 4096), float16, cuda, axis=1, output_transpose=False)
2%|▏ | 3/195 [00:08<06:35, 2.06s/it] [2024-06-02 06:21:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
2%|▏ | 3/195 [00:08<06:35, 2.06s/it] [2024-06-02 06:21:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
2%|▏ | 3/195 [00:08<06:35, 2.06s/it] 2%|▏ | 4/195 [00:08<05:31, 1.74s/it] [2024-06-02 06:21:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (4096,), dtype: float16
2%|▏ | 4/195 [00:08<05:31, 1.74s/it] [2024-06-02 06:21:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (4096,), dtype: float16
2%|▏ | 4/195 [00:08<05:31, 1.74s/it] [2024-06-02 06:21:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
2%|▏ | 4/195 [00:08<05:31, 1.74s/it] [2024-06-02 06:21:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
2%|▏ | 4/195 [00:09<05:31, 1.74s/it] 4%|▎ | 7/195 [00:09<02:22, 1.32it/s] [2024-06-02 06:21:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
4%|▎ | 7/195 [00:09<02:22, 1.32it/s] [2024-06-02 06:21:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
4%|▎ | 7/195 [00:09<02:22, 1.32it/s] 4%|▍ | 8/195 [00:09<02:18, 1.35it/s] [2024-06-02 06:21:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (4096,), dtype: float16
4%|▍ | 8/195 [00:09<02:18, 1.35it/s] [2024-06-02 06:21:46] INFO group_quantization.py:217: Compiling quantize function for key: ((6144, 4096), float16, cuda, axis=1, output_transpose=False)
4%|▍ | 8/195 [00:09<02:18, 1.35it/s] [2024-06-02 06:21:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
4%|▍ | 8/195 [00:10<02:18, 1.35it/s] [2024-06-02 06:21:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
4%|▍ | 8/195 [00:10<02:18, 1.35it/s] 5%|▌ | 10/195 [00:10<01:46, 1.74it/s] [2024-06-02 06:21:47] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 4096), float16, cuda, axis=1, output_transpose=False)
5%|▌ | 10/195 [00:10<01:46, 1.74it/s] [2024-06-02 06:21:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
5%|▌ | 10/195 [00:10<01:46, 1.74it/s] [2024-06-02 06:21:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
5%|▌ | 10/195 [00:10<01:46, 1.74it/s] 6%|▌ | 11/195 [00:10<01:43, 1.77it/s] [2024-06-02 06:21:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (4096,), dtype: float16
6%|▌ | 11/195 [00:10<01:43, 1.77it/s] [2024-06-02 06:21:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
6%|▌ | 11/195 [00:11<01:43, 1.77it/s] [2024-06-02 06:21:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
6%|▌ | 11/195 [00:11<01:43, 1.77it/s] 7%|▋ | 13/195 [00:11<01:14, 2.46it/s] [2024-06-02 06:21:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
7%|▋ | 13/195 [00:11<01:14, 2.46it/s] [2024-06-02 06:21:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
7%|▋ | 13/195 [00:11<01:14, 2.46it/s] 7%|▋ | 14/195 [00:11<01:25, 2.12it/s] [2024-06-02 06:21:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (4096,), dtype: float16
7%|▋ | 14/195 [00:11<01:25, 2.12it/s] [2024-06-02 06:21:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
7%|▋ | 14/195 [00:11<01:25, 2.12it/s] [2024-06-02 06:21:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
7%|▋ | 14/195 [00:11<01:25, 2.12it/s] 8%|▊ | 16/195 [00:11<00:56, 3.18it/s] [2024-06-02 06:21:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
8%|▊ | 16/195 [00:12<00:56, 3.18it/s] [2024-06-02 06:21:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
8%|▊ | 16/195 [00:12<00:56, 3.18it/s] [2024-06-02 06:21:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (4096,), dtype: float16
8%|▊ | 16/195 [00:12<00:56, 3.18it/s] [2024-06-02 06:21:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
8%|▊ | 16/195 [00:12<00:56, 3.18it/s] [2024-06-02 06:21:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
8%|▊ | 16/195 [00:12<00:56, 3.18it/s] 10%|▉ | 19/195 [00:12<00:41, 4.23it/s] [2024-06-02 06:21:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
10%|▉ | 19/195 [00:12<00:41, 4.23it/s] [2024-06-02 06:21:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
10%|▉ | 19/195 [00:13<00:41, 4.23it/s] 10%|█ | 20/195 [00:13<00:53, 3.26it/s] [2024-06-02 06:21:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (4096,), dtype: float16
10%|█ | 20/195 [00:13<00:53, 3.26it/s] [2024-06-02 06:21:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
10%|█ | 20/195 [00:13<00:53, 3.26it/s] [2024-06-02 06:21:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
10%|█ | 20/195 [00:13<00:53, 3.26it/s] 11%|█▏ | 22/195 [00:13<00:38, 4.48it/s] [2024-06-02 06:21:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
11%|█▏ | 22/195 [00:13<00:38, 4.48it/s] [2024-06-02 06:21:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
11%|█▏ | 22/195 [00:13<00:38, 4.48it/s] 12%|█▏ | 23/195 [00:13<00:34, 4.95it/s] [2024-06-02 06:21:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (4096,), dtype: float16
12%|█▏ | 23/195 [00:13<00:34, 4.95it/s] [2024-06-02 06:21:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
12%|█▏ | 23/195 [00:13<00:34, 4.95it/s] [2024-06-02 06:21:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
12%|█▏ | 23/195 [00:13<00:34, 4.95it/s] 13%|█▎ | 25/195 [00:13<00:30, 5.51it/s] [2024-06-02 06:21:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
13%|█▎ | 25/195 [00:14<00:30, 5.51it/s] [2024-06-02 06:21:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
13%|█▎ | 25/195 [00:14<00:30, 5.51it/s] 13%|█▎ | 26/195 [00:14<00:46, 3.64it/s] [2024-06-02 06:21:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (4096,), dtype: float16
13%|█▎ | 26/195 [00:14<00:46, 3.64it/s] [2024-06-02 06:21:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
13%|█▎ | 26/195 [00:14<00:46, 3.64it/s] [2024-06-02 06:21:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
13%|█▎ | 26/195 [00:14<00:46, 3.64it/s] 14%|█▍ | 28/195 [00:14<00:34, 4.85it/s] [2024-06-02 06:21:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
14%|█▍ | 28/195 [00:14<00:34, 4.85it/s] [2024-06-02 06:21:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
14%|█▍ | 28/195 [00:14<00:34, 4.85it/s] [2024-06-02 06:21:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (4096,), dtype: float16
14%|█▍ | 28/195 [00:14<00:34, 4.85it/s] [2024-06-02 06:21:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
14%|█▍ | 28/195 [00:14<00:34, 4.85it/s] [2024-06-02 06:21:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
14%|█▍ | 28/195 [00:14<00:34, 4.85it/s] 16%|█▌ | 31/195 [00:14<00:27, 5.95it/s] [2024-06-02 06:21:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
16%|█▌ | 31/195 [00:15<00:27, 5.95it/s] [2024-06-02 06:21:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
16%|█▌ | 31/195 [00:15<00:27, 5.95it/s] 16%|█▋ | 32/195 [00:15<00:40, 4.00it/s] [2024-06-02 06:21:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (4096,), dtype: float16
16%|█▋ | 32/195 [00:15<00:40, 4.00it/s] [2024-06-02 06:21:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
16%|█▋ | 32/195 [00:15<00:40, 4.00it/s] [2024-06-02 06:21:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
16%|█▋ | 32/195 [00:15<00:40, 4.00it/s] 17%|█▋ | 34/195 [00:15<00:30, 5.20it/s] [2024-06-02 06:21:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
17%|█▋ | 34/195 [00:15<00:30, 5.20it/s] [2024-06-02 06:21:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
17%|█▋ | 34/195 [00:15<00:30, 5.20it/s] [2024-06-02 06:21:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.input_layernorm.weight", shape: (4096,), dtype: float16
17%|█▋ | 34/195 [00:15<00:30, 5.20it/s] [2024-06-02 06:21:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
17%|█▋ | 34/195 [00:15<00:30, 5.20it/s] [2024-06-02 06:21:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
17%|█▋ | 34/195 [00:15<00:30, 5.20it/s] 19%|█▉ | 37/195 [00:15<00:25, 6.14it/s] [2024-06-02 06:21:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
19%|█▉ | 37/195 [00:16<00:25, 6.14it/s] [2024-06-02 06:21:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
19%|█▉ | 37/195 [00:16<00:25, 6.14it/s] 19%|█▉ | 38/195 [00:16<00:39, 3.96it/s] [2024-06-02 06:21:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.post_attention_layernorm.weight", shape: (4096,), dtype: float16
19%|█▉ | 38/195 [00:16<00:39, 3.96it/s] [2024-06-02 06:21:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
19%|█▉ | 38/195 [00:16<00:39, 3.96it/s] [2024-06-02 06:21:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
19%|█▉ | 38/195 [00:16<00:39, 3.96it/s] 21%|██ | 40/195 [00:16<00:29, 5.26it/s] [2024-06-02 06:21:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
21%|██ | 40/195 [00:16<00:29, 5.26it/s] [2024-06-02 06:21:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
21%|██ | 40/195 [00:16<00:29, 5.26it/s] [2024-06-02 06:21:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.input_layernorm.weight", shape: (4096,), dtype: float16
21%|██ | 40/195 [00:16<00:29, 5.26it/s] [2024-06-02 06:21:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
21%|██ | 40/195 [00:16<00:29, 5.26it/s] [2024-06-02 06:21:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
21%|██ | 40/195 [00:17<00:29, 5.26it/s] 22%|██▏ | 43/195 [00:17<00:25, 5.89it/s] [2024-06-02 06:21:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
22%|██▏ | 43/195 [00:17<00:25, 5.89it/s] [2024-06-02 06:21:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
22%|██▏ | 43/195 [00:17<00:25, 5.89it/s] 23%|██▎ | 44/195 [00:17<00:37, 4.02it/s] [2024-06-02 06:21:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.post_attention_layernorm.weight", shape: (4096,), dtype: float16
23%|██▎ | 44/195 [00:17<00:37, 4.02it/s] [2024-06-02 06:21:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
23%|██▎ | 44/195 [00:17<00:37, 4.02it/s] [2024-06-02 06:21:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
23%|██▎ | 44/195 [00:17<00:37, 4.02it/s] 24%|██▎ | 46/195 [00:17<00:27, 5.33it/s] [2024-06-02 06:21:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
24%|██▎ | 46/195 [00:17<00:27, 5.33it/s] [2024-06-02 06:21:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
24%|██▎ | 46/195 [00:17<00:27, 5.33it/s] [2024-06-02 06:21:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.input_layernorm.weight", shape: (4096,), dtype: float16
24%|██▎ | 46/195 [00:17<00:27, 5.33it/s] 25%|██▍ | 48/195 [00:17<00:21, 6.81it/s] [2024-06-02 06:21:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
25%|██▍ | 48/195 [00:18<00:21, 6.81it/s] [2024-06-02 06:21:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
25%|██▍ | 48/195 [00:18<00:21, 6.81it/s] [2024-06-02 06:21:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
25%|██▍ | 48/195 [00:18<00:21, 6.81it/s] [2024-06-02 06:21:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
25%|██▍ | 48/195 [00:18<00:21, 6.81it/s] 26%|██▌ | 50/195 [00:18<00:35, 4.10it/s] [2024-06-02 06:21:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.post_attention_layernorm.weight", shape: (4096,), dtype: float16
26%|██▌ | 50/195 [00:18<00:35, 4.10it/s] [2024-06-02 06:21:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
26%|██▌ | 50/195 [00:19<00:35, 4.10it/s] [2024-06-02 06:21:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
26%|██▌ | 50/195 [00:19<00:35, 4.10it/s] 27%|██▋ | 52/195 [00:19<00:28, 5.11it/s] [2024-06-02 06:21:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
27%|██▋ | 52/195 [00:19<00:28, 5.11it/s] [2024-06-02 06:21:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
27%|██▋ | 52/195 [00:19<00:28, 5.11it/s] [2024-06-02 06:21:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.input_layernorm.weight", shape: (4096,), dtype: float16
27%|██▋ | 52/195 [00:19<00:28, 5.11it/s] [2024-06-02 06:21:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
27%|██▋ | 52/195 [00:19<00:28, 5.11it/s] [2024-06-02 06:21:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
27%|██▋ | 52/195 [00:19<00:28, 5.11it/s] 28%|██▊ | 55/195 [00:19<00:23, 6.07it/s] [2024-06-02 06:21:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
28%|██▊ | 55/195 [00:19<00:23, 6.07it/s] [2024-06-02 06:21:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
28%|██▊ | 55/195 [00:20<00:23, 6.07it/s] 29%|██▊ | 56/195 [00:20<00:33, 4.17it/s] [2024-06-02 06:21:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.post_attention_layernorm.weight", shape: (4096,), dtype: float16
29%|██▊ | 56/195 [00:20<00:33, 4.17it/s] [2024-06-02 06:21:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
29%|██▊ | 56/195 [00:20<00:33, 4.17it/s] [2024-06-02 06:21:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
29%|██▊ | 56/195 [00:20<00:33, 4.17it/s] 30%|██▉ | 58/195 [00:20<00:25, 5.29it/s] [2024-06-02 06:21:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
30%|██▉ | 58/195 [00:20<00:25, 5.29it/s] [2024-06-02 06:21:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
30%|██▉ | 58/195 [00:20<00:25, 5.29it/s] [2024-06-02 06:21:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (4096,), dtype: float16
30%|██▉ | 58/195 [00:20<00:25, 5.29it/s] [2024-06-02 06:21:57] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Mistral-7B-Instruct-v0.3/model-00003-of-00003.safetensors
30%|██▉ | 58/195 [00:20<00:25, 5.29it/s] [2024-06-02 06:21:57] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Mistral-7B-Instruct-v0.3/model-00001-of-00003.safetensors
30%|██▉ | 58/195 [00:20<00:25, 5.29it/s] [2024-06-02 06:22:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (32768, 512), dtype: uint32
30%|██▉ | 58/195 [00:26<00:25, 5.29it/s] [2024-06-02 06:22:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (32768, 128), dtype: float16
30%|██▉ | 58/195 [00:26<00:25, 5.29it/s] 31%|███▏ | 61/195 [00:26<02:01, 1.10it/s] [2024-06-02 06:22:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (4096,), dtype: float16
31%|███▏ | 61/195 [00:26<02:01, 1.10it/s] [2024-06-02 06:22:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
31%|███▏ | 61/195 [00:26<02:01, 1.10it/s] [2024-06-02 06:22:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
31%|███▏ | 61/195 [00:26<02:01, 1.10it/s] 32%|███▏ | 63/195 [00:26<01:33, 1.41it/s] [2024-06-02 06:22:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
32%|███▏ | 63/195 [00:27<01:33, 1.41it/s] [2024-06-02 06:22:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
32%|███▏ | 63/195 [00:27<01:33, 1.41it/s] 33%|███▎ | 64/195 [00:27<01:31, 1.44it/s] [2024-06-02 06:22:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (4096,), dtype: float16
33%|███▎ | 64/195 [00:27<01:31, 1.44it/s] [2024-06-02 06:22:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
33%|███▎ | 64/195 [00:27<01:31, 1.44it/s] [2024-06-02 06:22:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
33%|███▎ | 64/195 [00:27<01:31, 1.44it/s] 34%|███▍ | 66/195 [00:27<01:07, 1.92it/s] [2024-06-02 06:22:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
34%|███▍ | 66/195 [00:27<01:07, 1.92it/s] [2024-06-02 06:22:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
34%|███▍ | 66/195 [00:27<01:07, 1.92it/s] 34%|███▍ | 67/195 [00:27<00:57, 2.24it/s] [2024-06-02 06:22:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (4096,), dtype: float16
34%|███▍ | 67/195 [00:27<00:57, 2.24it/s] [2024-06-02 06:22:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
34%|███▍ | 67/195 [00:27<00:57, 2.24it/s] [2024-06-02 06:22:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
34%|███▍ | 67/195 [00:27<00:57, 2.24it/s] 35%|███▌ | 69/195 [00:27<00:43, 2.92it/s] [2024-06-02 06:22:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
35%|███▌ | 69/195 [00:28<00:43, 2.92it/s] [2024-06-02 06:22:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
35%|███▌ | 69/195 [00:28<00:43, 2.92it/s] 36%|███▌ | 70/195 [00:28<00:50, 2.47it/s] [2024-06-02 06:22:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (4096,), dtype: float16
36%|███▌ | 70/195 [00:28<00:50, 2.47it/s] [2024-06-02 06:22:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
36%|███▌ | 70/195 [00:28<00:50, 2.47it/s] [2024-06-02 06:22:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
36%|███▌ | 70/195 [00:28<00:50, 2.47it/s] 37%|███▋ | 72/195 [00:28<00:39, 3.11it/s] [2024-06-02 06:22:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
37%|███▋ | 72/195 [00:28<00:39, 3.11it/s] [2024-06-02 06:22:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
37%|███▋ | 72/195 [00:28<00:39, 3.11it/s] [2024-06-02 06:22:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
37%|███▋ | 72/195 [00:29<00:39, 3.11it/s] [2024-06-02 06:22:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
37%|███▋ | 72/195 [00:29<00:39, 3.11it/s] 38%|███▊ | 74/195 [00:29<00:40, 2.98it/s] [2024-06-02 06:22:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
38%|███▊ | 74/195 [00:29<00:40, 2.98it/s] [2024-06-02 06:22:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
38%|███▊ | 74/195 [00:29<00:40, 2.98it/s] 38%|███▊ | 75/195 [00:29<00:35, 3.40it/s] [2024-06-02 06:22:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
38%|███▊ | 75/195 [00:29<00:35, 3.40it/s] [2024-06-02 06:22:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
38%|███▊ | 75/195 [00:29<00:35, 3.40it/s] 39%|███▉ | 76/195 [00:29<00:30, 3.87it/s] [2024-06-02 06:22:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (4096,), dtype: float16
39%|███▉ | 76/195 [00:29<00:30, 3.87it/s] [2024-06-02 06:22:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
39%|███▉ | 76/195 [00:30<00:30, 3.87it/s] [2024-06-02 06:22:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
39%|███▉ | 76/195 [00:30<00:30, 3.87it/s] 40%|████ | 78/195 [00:30<00:25, 4.64it/s] [2024-06-02 06:22:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
40%|████ | 78/195 [00:30<00:25, 4.64it/s] [2024-06-02 06:22:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
40%|████ | 78/195 [00:30<00:25, 4.64it/s] 41%|████ | 79/195 [00:30<00:35, 3.23it/s] [2024-06-02 06:22:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (4096,), dtype: float16
41%|████ | 79/195 [00:30<00:35, 3.23it/s] [2024-06-02 06:22:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
41%|████ | 79/195 [00:30<00:35, 3.23it/s] [2024-06-02 06:22:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
41%|████ | 79/195 [00:30<00:35, 3.23it/s] 42%|████▏ | 81/195 [00:31<00:25, 4.39it/s] [2024-06-02 06:22:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
42%|████▏ | 81/195 [00:31<00:25, 4.39it/s] [2024-06-02 06:22:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
42%|████▏ | 81/195 [00:31<00:25, 4.39it/s] [2024-06-02 06:22:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (4096,), dtype: float16
42%|████▏ | 81/195 [00:31<00:25, 4.39it/s] [2024-06-02 06:22:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
42%|████▏ | 81/195 [00:31<00:25, 4.39it/s] [2024-06-02 06:22:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
42%|████▏ | 81/195 [00:31<00:25, 4.39it/s] 43%|████▎ | 84/195 [00:31<00:19, 5.56it/s] [2024-06-02 06:22:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
43%|████▎ | 84/195 [00:31<00:19, 5.56it/s] [2024-06-02 06:22:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
43%|████▎ | 84/195 [00:32<00:19, 5.56it/s] 44%|████▎ | 85/195 [00:32<00:29, 3.79it/s] [2024-06-02 06:22:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (4096,), dtype: float16
44%|████▎ | 85/195 [00:32<00:29, 3.79it/s] [2024-06-02 06:22:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
44%|████▎ | 85/195 [00:32<00:29, 3.79it/s] [2024-06-02 06:22:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
44%|████▎ | 85/195 [00:32<00:29, 3.79it/s] 45%|████▍ | 87/195 [00:32<00:21, 4.95it/s] [2024-06-02 06:22:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
45%|████▍ | 87/195 [00:32<00:21, 4.95it/s] [2024-06-02 06:22:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
45%|████▍ | 87/195 [00:32<00:21, 4.95it/s] [2024-06-02 06:22:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (4096,), dtype: float16
45%|████▍ | 87/195 [00:32<00:21, 4.95it/s] [2024-06-02 06:22:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
45%|████▍ | 87/195 [00:32<00:21, 4.95it/s] [2024-06-02 06:22:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
45%|████▍ | 87/195 [00:32<00:21, 4.95it/s] 46%|████▌ | 90/195 [00:32<00:17, 5.90it/s] [2024-06-02 06:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
46%|████▌ | 90/195 [00:33<00:17, 5.90it/s] [2024-06-02 06:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
46%|████▌ | 90/195 [00:33<00:17, 5.90it/s] 47%|████▋ | 91/195 [00:33<00:26, 3.88it/s] [2024-06-02 06:22:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (4096,), dtype: float16
47%|████▋ | 91/195 [00:33<00:26, 3.88it/s] [2024-06-02 06:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
47%|████▋ | 91/195 [00:33<00:26, 3.88it/s] [2024-06-02 06:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
47%|████▋ | 91/195 [00:33<00:26, 3.88it/s] 48%|████▊ | 93/195 [00:33<00:19, 5.18it/s] [2024-06-02 06:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
48%|████▊ | 93/195 [00:33<00:19, 5.18it/s] [2024-06-02 06:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
48%|████▊ | 93/195 [00:33<00:19, 5.18it/s] [2024-06-02 06:22:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (4096,), dtype: float16
48%|████▊ | 93/195 [00:33<00:19, 5.18it/s] [2024-06-02 06:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
48%|████▊ | 93/195 [00:33<00:19, 5.18it/s] [2024-06-02 06:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
48%|████▊ | 93/195 [00:33<00:19, 5.18it/s] 49%|████▉ | 96/195 [00:33<00:16, 5.86it/s] [2024-06-02 06:22:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
49%|████▉ | 96/195 [00:34<00:16, 5.86it/s] [2024-06-02 06:22:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
49%|████▉ | 96/195 [00:34<00:16, 5.86it/s] 50%|████▉ | 97/195 [00:34<00:28, 3.38it/s] [2024-06-02 06:22:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (4096,), dtype: float16
50%|████▉ | 97/195 [00:34<00:28, 3.38it/s] [2024-06-02 06:22:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
50%|████▉ | 97/195 [00:34<00:28, 3.38it/s] [2024-06-02 06:22:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
50%|████▉ | 97/195 [00:34<00:28, 3.38it/s] 51%|█████ | 99/195 [00:34<00:21, 4.55it/s] [2024-06-02 06:22:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
51%|█████ | 99/195 [00:34<00:21, 4.55it/s] [2024-06-02 06:22:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
51%|█████ | 99/195 [00:34<00:21, 4.55it/s] 51%|█████▏ | 100/195 [00:34<00:19, 4.98it/s] [2024-06-02 06:22:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (4096,), dtype: float16
51%|█████▏ | 100/195 [00:34<00:19, 4.98it/s] [2024-06-02 06:22:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
51%|█████▏ | 100/195 [00:35<00:19, 4.98it/s] [2024-06-02 06:22:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
51%|█████▏ | 100/195 [00:35<00:19, 4.98it/s] 52%|█████▏ | 102/195 [00:35<00:16, 5.50it/s] [2024-06-02 06:22:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
52%|█████▏ | 102/195 [00:35<00:16, 5.50it/s] [2024-06-02 06:22:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
52%|█████▏ | 102/195 [00:36<00:16, 5.50it/s] 53%|█████▎ | 103/195 [00:36<00:28, 3.24it/s] [2024-06-02 06:22:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (4096,), dtype: float16
53%|█████▎ | 103/195 [00:36<00:28, 3.24it/s] [2024-06-02 06:22:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
53%|█████▎ | 103/195 [00:36<00:28, 3.24it/s] [2024-06-02 06:22:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
53%|█████▎ | 103/195 [00:36<00:28, 3.24it/s] 54%|█████▍ | 105/195 [00:36<00:20, 4.35it/s] [2024-06-02 06:22:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
54%|█████▍ | 105/195 [00:36<00:20, 4.35it/s] [2024-06-02 06:22:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
54%|█████▍ | 105/195 [00:36<00:20, 4.35it/s] [2024-06-02 06:22:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (4096,), dtype: float16
54%|█████▍ | 105/195 [00:36<00:20, 4.35it/s] [2024-06-02 06:22:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
54%|█████▍ | 105/195 [00:36<00:20, 4.35it/s] [2024-06-02 06:22:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
54%|█████▍ | 105/195 [00:36<00:20, 4.35it/s] 55%|█████▌ | 108/195 [00:36<00:15, 5.48it/s] [2024-06-02 06:22:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
55%|█████▌ | 108/195 [00:37<00:15, 5.48it/s] [2024-06-02 06:22:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
55%|█████▌ | 108/195 [00:37<00:15, 5.48it/s] 56%|█████▌ | 109/195 [00:37<00:31, 2.74it/s] [2024-06-02 06:22:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (4096,), dtype: float16
56%|█████▌ | 109/195 [00:37<00:31, 2.74it/s] [2024-06-02 06:22:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
56%|█████▌ | 109/195 [00:37<00:31, 2.74it/s] [2024-06-02 06:22:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
56%|█████▌ | 109/195 [00:38<00:31, 2.74it/s] 57%|█████▋ | 111/195 [00:38<00:22, 3.68it/s] [2024-06-02 06:22:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
57%|█████▋ | 111/195 [00:38<00:22, 3.68it/s] [2024-06-02 06:22:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
57%|█████▋ | 111/195 [00:38<00:22, 3.68it/s] [2024-06-02 06:22:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (4096,), dtype: float16
57%|█████▋ | 111/195 [00:38<00:22, 3.68it/s] [2024-06-02 06:22:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
57%|█████▋ | 111/195 [00:38<00:22, 3.68it/s] [2024-06-02 06:22:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
57%|█████▋ | 111/195 [00:38<00:22, 3.68it/s] 58%|█████▊ | 114/195 [00:38<00:17, 4.72it/s] [2024-06-02 06:22:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
58%|█████▊ | 114/195 [00:39<00:17, 4.72it/s] [2024-06-02 06:22:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
58%|█████▊ | 114/195 [00:39<00:17, 4.72it/s] 59%|█████▉ | 115/195 [00:39<00:29, 2.69it/s] [2024-06-02 06:22:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (4096,), dtype: float16
59%|█████▉ | 115/195 [00:39<00:29, 2.69it/s] [2024-06-02 06:22:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
59%|█████▉ | 115/195 [00:39<00:29, 2.69it/s] [2024-06-02 06:22:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
59%|█████▉ | 115/195 [00:39<00:29, 2.69it/s] 60%|██████ | 117/195 [00:39<00:21, 3.70it/s] [2024-06-02 06:22:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
60%|██████ | 117/195 [00:39<00:21, 3.70it/s] [2024-06-02 06:22:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
60%|██████ | 117/195 [00:39<00:21, 3.70it/s] [2024-06-02 06:22:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (4096,), dtype: float16
60%|██████ | 117/195 [00:39<00:21, 3.70it/s] [2024-06-02 06:22:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
60%|██████ | 117/195 [00:40<00:21, 3.70it/s] [2024-06-02 06:22:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
60%|██████ | 117/195 [00:40<00:21, 3.70it/s] 62%|██████▏ | 120/195 [00:40<00:16, 4.52it/s] [2024-06-02 06:22:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
62%|██████▏ | 120/195 [00:40<00:16, 4.52it/s] [2024-06-02 06:22:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
62%|██████▏ | 120/195 [00:41<00:16, 4.52it/s] 62%|██████▏ | 121/195 [00:41<00:24, 3.07it/s] [2024-06-02 06:22:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (4096,), dtype: float16
62%|██████▏ | 121/195 [00:41<00:24, 3.07it/s] [2024-06-02 06:22:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
62%|██████▏ | 121/195 [00:41<00:24, 3.07it/s] [2024-06-02 06:22:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
62%|██████▏ | 121/195 [00:41<00:24, 3.07it/s] 63%|██████▎ | 123/195 [00:41<00:17, 4.13it/s] [2024-06-02 06:22:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
63%|██████▎ | 123/195 [00:41<00:17, 4.13it/s] [2024-06-02 06:22:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
63%|██████▎ | 123/195 [00:41<00:17, 4.13it/s] 64%|██████▎ | 124/195 [00:41<00:15, 4.56it/s] [2024-06-02 06:22:18] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Mistral-7B-Instruct-v0.3/model-00001-of-00003.safetensors
64%|██████▎ | 124/195 [00:41<00:15, 4.56it/s] [2024-06-02 06:22:18] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Mistral-7B-Instruct-v0.3/model-00002-of-00003.safetensors
64%|██████▎ | 124/195 [00:41<00:15, 4.56it/s] [2024-06-02 06:22:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (4096,), dtype: float16
64%|██████▎ | 124/195 [00:46<00:15, 4.56it/s] 64%|██████▍ | 125/195 [00:46<01:25, 1.22s/it] [2024-06-02 06:22:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
64%|██████▍ | 125/195 [00:46<01:25, 1.22s/it] [2024-06-02 06:22:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
64%|██████▍ | 125/195 [00:46<01:25, 1.22s/it] 65%|██████▍ | 126/195 [00:46<01:10, 1.02s/it] [2024-06-02 06:22:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (4096,), dtype: float16
65%|██████▍ | 126/195 [00:46<01:10, 1.02s/it] [2024-06-02 06:22:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (4096,), dtype: float16
65%|██████▍ | 126/195 [00:46<01:10, 1.02s/it] [2024-06-02 06:22:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
65%|██████▍ | 126/195 [00:46<01:10, 1.02s/it] [2024-06-02 06:22:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
65%|██████▍ | 126/195 [00:46<01:10, 1.02s/it] 66%|██████▌ | 129/195 [00:46<00:37, 1.78it/s] [2024-06-02 06:22:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
66%|██████▌ | 129/195 [00:47<00:37, 1.78it/s] [2024-06-02 06:22:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
66%|██████▌ | 129/195 [00:47<00:37, 1.78it/s] 67%|██████▋ | 130/195 [00:47<00:42, 1.54it/s] [2024-06-02 06:22:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (4096,), dtype: float16
67%|██████▋ | 130/195 [00:47<00:42, 1.54it/s] [2024-06-02 06:22:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
67%|██████▋ | 130/195 [00:48<00:42, 1.54it/s] [2024-06-02 06:22:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
67%|██████▋ | 130/195 [00:48<00:42, 1.54it/s] 68%|██████▊ | 132/195 [00:48<00:28, 2.24it/s] [2024-06-02 06:22:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
68%|██████▊ | 132/195 [00:48<00:28, 2.24it/s] [2024-06-02 06:22:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
68%|██████▊ | 132/195 [00:48<00:28, 2.24it/s] [2024-06-02 06:22:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (4096,), dtype: float16
68%|██████▊ | 132/195 [00:48<00:28, 2.24it/s] [2024-06-02 06:22:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
68%|██████▊ | 132/195 [00:48<00:28, 2.24it/s] [2024-06-02 06:22:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
68%|██████▊ | 132/195 [00:48<00:28, 2.24it/s] 69%|██████▉ | 135/195 [00:48<00:18, 3.25it/s] [2024-06-02 06:22:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
69%|██████▉ | 135/195 [00:49<00:18, 3.25it/s] [2024-06-02 06:22:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
69%|██████▉ | 135/195 [00:50<00:18, 3.25it/s] 70%|██████▉ | 136/195 [00:50<00:32, 1.79it/s] [2024-06-02 06:22:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (4096,), dtype: float16
70%|██████▉ | 136/195 [00:50<00:32, 1.79it/s] [2024-06-02 06:22:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
70%|██████▉ | 136/195 [00:50<00:32, 1.79it/s] [2024-06-02 06:22:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
70%|██████▉ | 136/195 [00:50<00:32, 1.79it/s] 71%|███████ | 138/195 [00:50<00:23, 2.41it/s] [2024-06-02 06:22:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
71%|███████ | 138/195 [00:50<00:23, 2.41it/s] [2024-06-02 06:22:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
71%|███████ | 138/195 [00:50<00:23, 2.41it/s] [2024-06-02 06:22:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (4096,), dtype: float16
71%|███████ | 138/195 [00:50<00:23, 2.41it/s] [2024-06-02 06:22:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
71%|███████ | 138/195 [00:50<00:23, 2.41it/s] [2024-06-02 06:22:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
71%|███████ | 138/195 [00:50<00:23, 2.41it/s] 72%|███████▏ | 141/195 [00:50<00:16, 3.28it/s] [2024-06-02 06:22:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
72%|███████▏ | 141/195 [00:52<00:16, 3.28it/s] [2024-06-02 06:22:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
72%|███████▏ | 141/195 [00:52<00:16, 3.28it/s] 73%|███████▎ | 142/195 [00:52<00:26, 2.00it/s] [2024-06-02 06:22:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (4096,), dtype: float16
73%|███████▎ | 142/195 [00:52<00:26, 2.00it/s] [2024-06-02 06:22:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
73%|███████▎ | 142/195 [00:52<00:26, 2.00it/s] [2024-06-02 06:22:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
73%|███████▎ | 142/195 [00:52<00:26, 2.00it/s] 74%|███████▍ | 144/195 [00:52<00:18, 2.78it/s] [2024-06-02 06:22:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
74%|███████▍ | 144/195 [00:52<00:18, 2.78it/s] [2024-06-02 06:22:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
74%|███████▍ | 144/195 [00:52<00:18, 2.78it/s] 74%|███████▍ | 145/195 [00:52<00:15, 3.17it/s] [2024-06-02 06:22:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (4096,), dtype: float16
74%|███████▍ | 145/195 [00:52<00:15, 3.17it/s] [2024-06-02 06:22:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
74%|███████▍ | 145/195 [00:52<00:15, 3.17it/s] [2024-06-02 06:22:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
74%|███████▍ | 145/195 [00:52<00:15, 3.17it/s] 75%|███████▌ | 147/195 [00:52<00:12, 3.87it/s] [2024-06-02 06:22:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
75%|███████▌ | 147/195 [00:53<00:12, 3.87it/s] [2024-06-02 06:22:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
75%|███████▌ | 147/195 [00:53<00:12, 3.87it/s] 76%|███████▌ | 148/195 [00:53<00:19, 2.46it/s] [2024-06-02 06:22:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (4096,), dtype: float16
76%|███████▌ | 148/195 [00:53<00:19, 2.46it/s] [2024-06-02 06:22:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
76%|███████▌ | 148/195 [00:54<00:19, 2.46it/s] [2024-06-02 06:22:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
76%|███████▌ | 148/195 [00:54<00:19, 2.46it/s] 77%|███████▋ | 150/195 [00:54<00:13, 3.40it/s] [2024-06-02 06:22:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
77%|███████▋ | 150/195 [00:54<00:13, 3.40it/s] [2024-06-02 06:22:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
77%|███████▋ | 150/195 [00:54<00:13, 3.40it/s] [2024-06-02 06:22:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (4096,), dtype: float16
77%|███████▋ | 150/195 [00:54<00:13, 3.40it/s] [2024-06-02 06:22:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
77%|███████▋ | 150/195 [00:54<00:13, 3.40it/s] [2024-06-02 06:22:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
77%|███████▋ | 150/195 [00:54<00:13, 3.40it/s] 78%|███████▊ | 153/195 [00:54<00:09, 4.54it/s] [2024-06-02 06:22:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
78%|███████▊ | 153/195 [00:55<00:09, 4.54it/s] [2024-06-02 06:22:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
78%|███████▊ | 153/195 [00:55<00:09, 4.54it/s] 79%|███████▉ | 154/195 [00:55<00:13, 3.13it/s] [2024-06-02 06:22:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (4096,), dtype: float16
79%|███████▉ | 154/195 [00:55<00:13, 3.13it/s] [2024-06-02 06:22:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
79%|███████▉ | 154/195 [00:55<00:13, 3.13it/s] [2024-06-02 06:22:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
79%|███████▉ | 154/195 [00:55<00:13, 3.13it/s] 80%|████████ | 156/195 [00:55<00:09, 4.14it/s] [2024-06-02 06:22:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
80%|████████ | 156/195 [00:55<00:09, 4.14it/s] [2024-06-02 06:22:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
80%|████████ | 156/195 [00:55<00:09, 4.14it/s] [2024-06-02 06:22:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (4096,), dtype: float16
80%|████████ | 156/195 [00:55<00:09, 4.14it/s] [2024-06-02 06:22:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
80%|████████ | 156/195 [00:55<00:09, 4.14it/s] [2024-06-02 06:22:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
80%|████████ | 156/195 [00:55<00:09, 4.14it/s] 82%|████████▏ | 159/195 [00:55<00:07, 5.07it/s] [2024-06-02 06:22:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
82%|████████▏ | 159/195 [00:56<00:07, 5.07it/s] [2024-06-02 06:22:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
82%|████████▏ | 159/195 [00:56<00:07, 5.07it/s] 82%|████████▏ | 160/195 [00:56<00:10, 3.37it/s] [2024-06-02 06:22:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (4096,), dtype: float16
82%|████████▏ | 160/195 [00:56<00:10, 3.37it/s] [2024-06-02 06:22:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
82%|████████▏ | 160/195 [00:56<00:10, 3.37it/s] [2024-06-02 06:22:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
82%|████████▏ | 160/195 [00:56<00:10, 3.37it/s] 83%|████████▎ | 162/195 [00:56<00:07, 4.55it/s] [2024-06-02 06:22:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
83%|████████▎ | 162/195 [00:56<00:07, 4.55it/s] [2024-06-02 06:22:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
83%|████████▎ | 162/195 [00:56<00:07, 4.55it/s] [2024-06-02 06:22:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (4096,), dtype: float16
83%|████████▎ | 162/195 [00:56<00:07, 4.55it/s] [2024-06-02 06:22:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
83%|████████▎ | 162/195 [00:57<00:07, 4.55it/s] [2024-06-02 06:22:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
83%|████████▎ | 162/195 [00:57<00:07, 4.55it/s] 85%|████████▍ | 165/195 [00:57<00:05, 5.28it/s] [2024-06-02 06:22:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
85%|████████▍ | 165/195 [00:57<00:05, 5.28it/s] [2024-06-02 06:22:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
85%|████████▍ | 165/195 [00:57<00:05, 5.28it/s] 85%|████████▌ | 166/195 [00:57<00:07, 3.77it/s] [2024-06-02 06:22:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (4096,), dtype: float16
85%|████████▌ | 166/195 [00:57<00:07, 3.77it/s] [2024-06-02 06:22:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
85%|████████▌ | 166/195 [00:58<00:07, 3.77it/s] [2024-06-02 06:22:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
85%|████████▌ | 166/195 [00:58<00:07, 3.77it/s] 86%|████████▌ | 168/195 [00:58<00:05, 5.01it/s] [2024-06-02 06:22:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
86%|████████▌ | 168/195 [00:58<00:05, 5.01it/s] [2024-06-02 06:22:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
86%|████████▌ | 168/195 [00:58<00:05, 5.01it/s] 87%|████████▋ | 169/195 [00:58<00:04, 5.43it/s] [2024-06-02 06:22:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (4096,), dtype: float16
87%|████████▋ | 169/195 [00:58<00:04, 5.43it/s] [2024-06-02 06:22:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
87%|████████▋ | 169/195 [00:58<00:04, 5.43it/s] [2024-06-02 06:22:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
87%|████████▋ | 169/195 [00:58<00:04, 5.43it/s] 88%|████████▊ | 171/195 [00:58<00:04, 5.79it/s] [2024-06-02 06:22:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
88%|████████▊ | 171/195 [00:58<00:04, 5.79it/s] [2024-06-02 06:22:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
88%|████████▊ | 171/195 [00:59<00:04, 5.79it/s] 88%|████████▊ | 172/195 [00:59<00:06, 3.71it/s] [2024-06-02 06:22:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (4096,), dtype: float16
88%|████████▊ | 172/195 [00:59<00:06, 3.71it/s] [2024-06-02 06:22:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
88%|████████▊ | 172/195 [00:59<00:06, 3.71it/s] [2024-06-02 06:22:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
88%|████████▊ | 172/195 [00:59<00:06, 3.71it/s] 89%|████████▉ | 174/195 [00:59<00:04, 4.84it/s] [2024-06-02 06:22:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
89%|████████▉ | 174/195 [00:59<00:04, 4.84it/s] [2024-06-02 06:22:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
89%|████████▉ | 174/195 [00:59<00:04, 4.84it/s] [2024-06-02 06:22:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (4096,), dtype: float16
89%|████████▉ | 174/195 [00:59<00:04, 4.84it/s] [2024-06-02 06:22:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
89%|████████▉ | 174/195 [00:59<00:04, 4.84it/s] [2024-06-02 06:22:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
89%|████████▉ | 174/195 [00:59<00:04, 4.84it/s] 91%|█████████ | 177/195 [00:59<00:03, 5.87it/s] [2024-06-02 06:22:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
91%|█████████ | 177/195 [01:00<00:03, 5.87it/s] [2024-06-02 06:22:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
91%|█████████ | 177/195 [01:00<00:03, 5.87it/s] 91%|█████████▏| 178/195 [01:00<00:04, 3.89it/s] [2024-06-02 06:22:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (4096,), dtype: float16
91%|█████████▏| 178/195 [01:00<00:04, 3.89it/s] [2024-06-02 06:22:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
91%|█████████▏| 178/195 [01:00<00:04, 3.89it/s] [2024-06-02 06:22:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
91%|█████████▏| 178/195 [01:00<00:04, 3.89it/s] 92%|█████████▏| 180/195 [01:00<00:02, 5.03it/s] [2024-06-02 06:22:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
92%|█████████▏| 180/195 [01:00<00:02, 5.03it/s] [2024-06-02 06:22:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
92%|█████████▏| 180/195 [01:00<00:02, 5.03it/s] [2024-06-02 06:22:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (4096,), dtype: float16
92%|█████████▏| 180/195 [01:00<00:02, 5.03it/s] [2024-06-02 06:22:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
92%|█████████▏| 180/195 [01:00<00:02, 5.03it/s] [2024-06-02 06:22:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
92%|█████████▏| 180/195 [01:00<00:02, 5.03it/s] 94%|█████████▍| 183/195 [01:00<00:02, 5.94it/s] [2024-06-02 06:22:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
94%|█████████▍| 183/195 [01:01<00:02, 5.94it/s] [2024-06-02 06:22:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
94%|█████████▍| 183/195 [01:01<00:02, 5.94it/s] 94%|█████████▍| 184/195 [01:01<00:02, 3.81it/s] [2024-06-02 06:22:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (4096,), dtype: float16
94%|█████████▍| 184/195 [01:01<00:02, 3.81it/s] [2024-06-02 06:22:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
94%|█████████▍| 184/195 [01:01<00:02, 3.81it/s] [2024-06-02 06:22:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
94%|█████████▍| 184/195 [01:01<00:02, 3.81it/s] 95%|█████████▌| 186/195 [01:01<00:01, 5.09it/s] [2024-06-02 06:22:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
95%|█████████▌| 186/195 [01:01<00:01, 5.09it/s] [2024-06-02 06:22:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
95%|█████████▌| 186/195 [01:01<00:01, 5.09it/s] [2024-06-02 06:22:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (4096,), dtype: float16
95%|█████████▌| 186/195 [01:01<00:01, 5.09it/s] [2024-06-02 06:22:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
95%|█████████▌| 186/195 [01:02<00:01, 5.09it/s] [2024-06-02 06:22:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
95%|█████████▌| 186/195 [01:02<00:01, 5.09it/s] 97%|█████████▋| 189/195 [01:02<00:01, 5.68it/s] [2024-06-02 06:22:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
97%|█████████▋| 189/195 [01:02<00:01, 5.68it/s] [2024-06-02 06:22:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
97%|█████████▋| 189/195 [01:02<00:01, 5.68it/s] 97%|█████████▋| 190/195 [01:02<00:01, 3.96it/s] [2024-06-02 06:22:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (4096,), dtype: float16
97%|█████████▋| 190/195 [01:02<00:01, 3.96it/s] [2024-06-02 06:22:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
97%|█████████▋| 190/195 [01:02<00:01, 3.96it/s] [2024-06-02 06:22:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
97%|█████████▋| 190/195 [01:02<00:01, 3.96it/s] 98%|█████████▊| 192/195 [01:02<00:00, 5.23it/s] [2024-06-02 06:22:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
98%|█████████▊| 192/195 [01:02<00:00, 5.23it/s] [2024-06-02 06:22:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
98%|█████████▊| 192/195 [01:03<00:00, 5.23it/s] 99%|█████████▉| 193/195 [01:03<00:00, 5.64it/s] [2024-06-02 06:22:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
99%|█████████▉| 193/195 [01:03<00:00, 5.64it/s] [2024-06-02 06:22:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
99%|█████████▉| 193/195 [01:03<00:00, 5.64it/s] 99%|█████████▉| 194/195 [01:03<00:00, 6.08it/s] [2024-06-02 06:22:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
99%|█████████▉| 194/195 [01:03<00:00, 6.08it/s] [2024-06-02 06:22:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
99%|█████████▉| 194/195 [01:03<00:00, 6.08it/s] 100%|██████████| 195/195 [01:03<00:00, 3.08it/s]
[2024-06-02 06:22:40] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Mistral-7B-Instruct-v0.3/model-00002-of-00003.safetensors
[2024-06-02 06:22:40] INFO stats.py:77: Time usage: HF loading: 15.603 sec; Pre-quantization mapping: 33.218 sec; Quantization: 3.086 sec
[2024-06-02 06:22:40] INFO stats.py:91: RAM usage: Peak RAM: 9.313 GB. Total bytes loaded from disk: 27.001 GB
[2024-06-02 06:22:40] INFO convert_weight.py:155: Parameter size after quantization: 3.797 GB
[2024-06-02 06:22:40] INFO convert_weight.py:160: Total parameters: 7,248,023,552
[2024-06-02 06:22:40] INFO convert_weight.py:161: Bits per parameter: 4.500
[2024-06-02 06:22:40] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q4f16_1-MLC
All finished, 106 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q4f16_1-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 q4f16_1 --conv-template mistral_default --output /ssd2/models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q4f16_1-MLC
[2024-06-02 04:13:33] INFO auto_config.py:115: Found model configuration: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/config.json
[2024-06-02 04:13:33] INFO auto_config.py:153: Found model type: mistral. Use `--model-type` to override.
[2024-06-02 04:13:33] INFO mistral_model.py:56: prefill_chunk_size defaults to 2048
[2024-06-02 04:13:33] INFO config.py:106: Overriding max_batch_size from 1 to 80
[2024-06-02 04:13:33] INFO gen_config.py:142: [generation_config.json] Setting bos_token_id: 1
[2024-06-02 04:13:33] INFO gen_config.py:142: [generation_config.json] Setting eos_token_id: 2
[2024-06-02 04:13:33] 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-q4f16_1-MLC/tokenizer.model
[2024-06-02 04:13:33] 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-q4f16_1-MLC/tokenizer.json
[2024-06-02 04:13:33] INFO gen_config.py:156: Not found tokenizer config: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/vocab.json
[2024-06-02 04:13:33] INFO gen_config.py:156: Not found tokenizer config: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/merges.txt
[2024-06-02 04:13:33] INFO gen_config.py:156: Not found tokenizer config: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/added_tokens.json
[2024-06-02 04:13:33] 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-q4f16_1-MLC/tokenizer_config.json
[2024-06-02 04:13:33] 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 04:13:33] INFO gen_config.py:31: [System default] Setting pad_token_id: 0
[2024-06-02 04:13:33] INFO gen_config.py:31: [System default] Setting temperature: 1.0
[2024-06-02 04:13:33] INFO gen_config.py:31: [System default] Setting presence_penalty: 0.0
[2024-06-02 04:13:33] INFO gen_config.py:31: [System default] Setting frequency_penalty: 0.0
[2024-06-02 04:13:33] INFO gen_config.py:31: [System default] Setting repetition_penalty: 1.0
[2024-06-02 04:13:33] INFO gen_config.py:31: [System default] Setting top_p: 1.0
[2024-06-02 04:13:33] INFO gen_config.py:31: [System default] Setting mean_gen_len: 128
[2024-06-02 04:13:33] INFO gen_config.py:31: [System default] Setting max_gen_len: 512
[2024-06-02 04:13:33] INFO gen_config.py:31: [System default] Setting shift_fill_factor: 0.3
[2024-06-02 04:13:33] INFO gen_config.py:222: Dumping configuration file to: /ssd2/models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q4f16_1-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 q4f16_1 --output /ssd2/models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q4f16_1-MLC
[2024-06-02 04:13:34] INFO auto_config.py:115: Found model configuration: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/config.json
[2024-06-02 04:13:35] INFO auto_device.py:79: Found device: cuda:0
[2024-06-02 04:13:35] INFO auto_device.py:79: Found device: cuda:1
[2024-06-02 04:13:36] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-02 04:13:37] INFO auto_device.py:88: Not found device: metal:0
[2024-06-02 04:13:38] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-02 04:13:38] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-02 04:13:38] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-02 04:13:39] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-02 04:13:39] INFO auto_device.py:35: Using device: cuda:0
[2024-06-02 04:13:39] INFO auto_weight.py:70: Finding weights in: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3
[2024-06-02 04:13:39] INFO auto_weight.py:136: Not found Huggingface PyTorch
[2024-06-02 04:13:39] 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 04:13:39] 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 04:13:39] INFO auto_weight.py:110: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-02 04:13:39] INFO auto_config.py:153: Found model type: mistral. Use `--model-type` to override.
[2024-06-02 04:13:39] 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 GroupQuantize(name='q4f16_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float16', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7)
--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-q4f16_1-MLC
Start storing to cache /ssd2/models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q4f16_1-MLC
0%| | 0/195 [00:00<?, ?it/s] [2024-06-02 04:13:43] 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 04:13:45] INFO group_quantization.py:217: Compiling quantize function for key: ((32768, 4096), float16, cuda, axis=1, output_transpose=False)
0%| | 0/195 [00:02<?, ?it/s] [2024-06-02 04:13:46] INFO huggingface_loader.py:166: [Quantized] Parameter: "lm_head.q_weight", shape: (32768, 512), dtype: uint32
0%| | 0/195 [00:03<?, ?it/s] [2024-06-02 04:13:46] INFO huggingface_loader.py:166: [Quantized] Parameter: "lm_head.q_scale", shape: (32768, 128), dtype: float16
0%| | 0/195 [00:03<?, ?it/s] 1%| | 1/195 [00:03<11:53, 3.68s/it] [2024-06-02 04:13:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (4096,), dtype: float16
1%| | 1/195 [00:03<11:53, 3.68s/it] [2024-06-02 04:13:47] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 14336), float16, cuda, axis=1, output_transpose=False)
1%| | 1/195 [00:03<11:53, 3.68s/it] [2024-06-02 04:13:47] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
1%| | 1/195 [00:04<11:53, 3.68s/it] [2024-06-02 04:13:47] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
1%| | 1/195 [00:04<11:53, 3.68s/it] 2%|▏ | 3/195 [00:04<03:54, 1.22s/it] [2024-06-02 04:13:48] INFO group_quantization.py:217: Compiling quantize function for key: ((28672, 4096), float16, cuda, axis=1, output_transpose=False)
2%|▏ | 3/195 [00:04<03:54, 1.22s/it] [2024-06-02 04:13:48] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
2%|▏ | 3/195 [00:05<03:54, 1.22s/it] [2024-06-02 04:13:48] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
2%|▏ | 3/195 [00:05<03:54, 1.22s/it] 2%|▏ | 4/195 [00:05<03:45, 1.18s/it] [2024-06-02 04:13:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (4096,), dtype: float16
2%|▏ | 4/195 [00:05<03:45, 1.18s/it] [2024-06-02 04:13:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (4096,), dtype: float16
2%|▏ | 4/195 [00:05<03:45, 1.18s/it] [2024-06-02 04:13:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
2%|▏ | 4/195 [00:05<03:45, 1.18s/it] [2024-06-02 04:13:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
2%|▏ | 4/195 [00:05<03:45, 1.18s/it] 4%|▎ | 7/195 [00:05<01:42, 1.84it/s] [2024-06-02 04:13:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
4%|▎ | 7/195 [00:06<01:42, 1.84it/s] [2024-06-02 04:13:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
4%|▎ | 7/195 [00:06<01:42, 1.84it/s] 4%|▍ | 8/195 [00:06<01:49, 1.70it/s] [2024-06-02 04:13:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (4096,), dtype: float16
4%|▍ | 8/195 [00:06<01:49, 1.70it/s] [2024-06-02 04:13:50] INFO group_quantization.py:217: Compiling quantize function for key: ((6144, 4096), float16, cuda, axis=1, output_transpose=False)
4%|▍ | 8/195 [00:06<01:49, 1.70it/s] [2024-06-02 04:13:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
4%|▍ | 8/195 [00:07<01:49, 1.70it/s] [2024-06-02 04:13:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
4%|▍ | 8/195 [00:07<01:49, 1.70it/s] 5%|▌ | 10/195 [00:07<01:27, 2.10it/s] [2024-06-02 04:13:50] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 4096), float16, cuda, axis=1, output_transpose=False)
5%|▌ | 10/195 [00:07<01:27, 2.10it/s] [2024-06-02 04:13:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
5%|▌ | 10/195 [00:07<01:27, 2.10it/s] [2024-06-02 04:13:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
5%|▌ | 10/195 [00:07<01:27, 2.10it/s] 6%|▌ | 11/195 [00:07<01:25, 2.15it/s] [2024-06-02 04:13:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (4096,), dtype: float16
6%|▌ | 11/195 [00:07<01:25, 2.15it/s] [2024-06-02 04:13:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
6%|▌ | 11/195 [00:07<01:25, 2.15it/s] [2024-06-02 04:13:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
6%|▌ | 11/195 [00:07<01:25, 2.15it/s] 7%|▋ | 13/195 [00:07<01:04, 2.83it/s] [2024-06-02 04:13:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
7%|▋ | 13/195 [00:08<01:04, 2.83it/s] [2024-06-02 04:13:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
7%|▋ | 13/195 [00:08<01:04, 2.83it/s] 7%|▋ | 14/195 [00:08<01:23, 2.18it/s] [2024-06-02 04:13:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (4096,), dtype: float16
7%|▋ | 14/195 [00:08<01:23, 2.18it/s] [2024-06-02 04:13:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
7%|▋ | 14/195 [00:08<01:23, 2.18it/s] [2024-06-02 04:13:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
7%|▋ | 14/195 [00:08<01:23, 2.18it/s] 8%|▊ | 16/195 [00:08<00:54, 3.29it/s] [2024-06-02 04:13:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
8%|▊ | 16/195 [00:08<00:54, 3.29it/s] [2024-06-02 04:13:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
8%|▊ | 16/195 [00:08<00:54, 3.29it/s] [2024-06-02 04:13:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (4096,), dtype: float16
8%|▊ | 16/195 [00:08<00:54, 3.29it/s] [2024-06-02 04:13:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
8%|▊ | 16/195 [00:09<00:54, 3.29it/s] [2024-06-02 04:13:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
8%|▊ | 16/195 [00:09<00:54, 3.29it/s] 10%|▉ | 19/195 [00:09<00:43, 4.09it/s] [2024-06-02 04:13:53] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
10%|▉ | 19/195 [00:09<00:43, 4.09it/s] [2024-06-02 04:13:53] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
10%|▉ | 19/195 [00:10<00:43, 4.09it/s] 10%|█ | 20/195 [00:10<00:57, 3.02it/s] [2024-06-02 04:13:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (4096,), dtype: float16
10%|█ | 20/195 [00:10<00:57, 3.02it/s] [2024-06-02 04:13:53] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
10%|█ | 20/195 [00:10<00:57, 3.02it/s] [2024-06-02 04:13:53] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
10%|█ | 20/195 [00:10<00:57, 3.02it/s] 11%|█▏ | 22/195 [00:10<00:41, 4.17it/s] [2024-06-02 04:13:53] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
11%|█▏ | 22/195 [00:10<00:41, 4.17it/s] [2024-06-02 04:13:53] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
11%|█▏ | 22/195 [00:10<00:41, 4.17it/s] 12%|█▏ | 23/195 [00:10<00:38, 4.51it/s] [2024-06-02 04:13:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (4096,), dtype: float16
12%|█▏ | 23/195 [00:10<00:38, 4.51it/s] [2024-06-02 04:13:53] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
12%|█▏ | 23/195 [00:10<00:38, 4.51it/s] [2024-06-02 04:13:54] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
12%|█▏ | 23/195 [00:10<00:38, 4.51it/s] 13%|█▎ | 25/195 [00:10<00:34, 4.93it/s] [2024-06-02 04:13:54] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
13%|█▎ | 25/195 [00:11<00:34, 4.93it/s] [2024-06-02 04:13:54] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
13%|█▎ | 25/195 [00:11<00:34, 4.93it/s] 13%|█▎ | 26/195 [00:11<00:52, 3.23it/s] [2024-06-02 04:13:54] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (4096,), dtype: float16
13%|█▎ | 26/195 [00:11<00:52, 3.23it/s] [2024-06-02 04:13:54] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
13%|█▎ | 26/195 [00:11<00:52, 3.23it/s] [2024-06-02 04:13:54] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
13%|█▎ | 26/195 [00:11<00:52, 3.23it/s] 14%|█▍ | 28/195 [00:11<00:39, 4.18it/s] [2024-06-02 04:13:55] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
14%|█▍ | 28/195 [00:11<00:39, 4.18it/s] [2024-06-02 04:13:55] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
14%|█▍ | 28/195 [00:11<00:39, 4.18it/s] [2024-06-02 04:13:55] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (4096,), dtype: float16
14%|█▍ | 28/195 [00:11<00:39, 4.18it/s] [2024-06-02 04:13:55] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
14%|█▍ | 28/195 [00:11<00:39, 4.18it/s] [2024-06-02 04:13:55] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
14%|█▍ | 28/195 [00:12<00:39, 4.18it/s] 16%|█▌ | 31/195 [00:12<00:31, 5.21it/s] [2024-06-02 04:13:55] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
16%|█▌ | 31/195 [00:12<00:31, 5.21it/s] [2024-06-02 04:13:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
16%|█▌ | 31/195 [00:12<00:31, 5.21it/s] 16%|█▋ | 32/195 [00:12<00:45, 3.56it/s] [2024-06-02 04:13:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (4096,), dtype: float16
16%|█▋ | 32/195 [00:12<00:45, 3.56it/s] [2024-06-02 04:13:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
16%|█▋ | 32/195 [00:12<00:45, 3.56it/s] [2024-06-02 04:13:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
16%|█▋ | 32/195 [00:12<00:45, 3.56it/s] 17%|█▋ | 34/195 [00:12<00:34, 4.61it/s] [2024-06-02 04:13:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
17%|█▋ | 34/195 [00:13<00:34, 4.61it/s] [2024-06-02 04:13:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
17%|█▋ | 34/195 [00:13<00:34, 4.61it/s] [2024-06-02 04:13:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.28.input_layernorm.weight", shape: (4096,), dtype: float16
17%|█▋ | 34/195 [00:13<00:34, 4.61it/s] [2024-06-02 04:13:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
17%|█▋ | 34/195 [00:13<00:34, 4.61it/s] [2024-06-02 04:13:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
17%|█▋ | 34/195 [00:13<00:34, 4.61it/s] 19%|█▉ | 37/195 [00:13<00:28, 5.51it/s] [2024-06-02 04:13:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
19%|█▉ | 37/195 [00:13<00:28, 5.51it/s] [2024-06-02 04:13:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
19%|█▉ | 37/195 [00:14<00:28, 5.51it/s] 19%|█▉ | 38/195 [00:14<00:45, 3.46it/s] [2024-06-02 04:13:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.28.post_attention_layernorm.weight", shape: (4096,), dtype: float16
19%|█▉ | 38/195 [00:14<00:45, 3.46it/s] [2024-06-02 04:13:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
19%|█▉ | 38/195 [00:14<00:45, 3.46it/s] [2024-06-02 04:13:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
19%|█▉ | 38/195 [00:14<00:45, 3.46it/s] 21%|██ | 40/195 [00:14<00:33, 4.69it/s] [2024-06-02 04:13:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
21%|██ | 40/195 [00:14<00:33, 4.69it/s] [2024-06-02 04:13:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
21%|██ | 40/195 [00:14<00:33, 4.69it/s] [2024-06-02 04:13:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.29.input_layernorm.weight", shape: (4096,), dtype: float16
21%|██ | 40/195 [00:14<00:33, 4.69it/s] [2024-06-02 04:13:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
21%|██ | 40/195 [00:14<00:33, 4.69it/s] [2024-06-02 04:13:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
21%|██ | 40/195 [00:14<00:33, 4.69it/s] 22%|██▏ | 43/195 [00:14<00:29, 5.08it/s] [2024-06-02 04:13:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
22%|██▏ | 43/195 [00:15<00:29, 5.08it/s] [2024-06-02 04:13:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
22%|██▏ | 43/195 [00:15<00:29, 5.08it/s] 23%|██▎ | 44/195 [00:15<00:42, 3.56it/s] [2024-06-02 04:13:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.29.post_attention_layernorm.weight", shape: (4096,), dtype: float16
23%|██▎ | 44/195 [00:15<00:42, 3.56it/s] [2024-06-02 04:13:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
23%|██▎ | 44/195 [00:15<00:42, 3.56it/s] [2024-06-02 04:13:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
23%|██▎ | 44/195 [00:15<00:42, 3.56it/s] 24%|██▎ | 46/195 [00:15<00:31, 4.80it/s] [2024-06-02 04:13:59] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
24%|██▎ | 46/195 [00:15<00:31, 4.80it/s] [2024-06-02 04:13:59] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
24%|██▎ | 46/195 [00:15<00:31, 4.80it/s] [2024-06-02 04:13:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.30.input_layernorm.weight", shape: (4096,), dtype: float16
24%|██▎ | 46/195 [00:15<00:31, 4.80it/s] 25%|██▍ | 48/195 [00:15<00:24, 6.02it/s] [2024-06-02 04:13:59] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
25%|██▍ | 48/195 [00:16<00:24, 6.02it/s] [2024-06-02 04:13:59] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
25%|██▍ | 48/195 [00:16<00:24, 6.02it/s] [2024-06-02 04:13:59] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
25%|██▍ | 48/195 [00:16<00:24, 6.02it/s] [2024-06-02 04:14:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
25%|██▍ | 48/195 [00:16<00:24, 6.02it/s] 26%|██▌ | 50/195 [00:16<00:40, 3.56it/s] [2024-06-02 04:14:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.30.post_attention_layernorm.weight", shape: (4096,), dtype: float16
26%|██▌ | 50/195 [00:16<00:40, 3.56it/s] [2024-06-02 04:14:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
26%|██▌ | 50/195 [00:16<00:40, 3.56it/s] [2024-06-02 04:14:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
26%|██▌ | 50/195 [00:16<00:40, 3.56it/s] 27%|██▋ | 52/195 [00:17<00:32, 4.36it/s] [2024-06-02 04:14:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
27%|██▋ | 52/195 [00:17<00:32, 4.36it/s] [2024-06-02 04:14:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
27%|██▋ | 52/195 [00:17<00:32, 4.36it/s] [2024-06-02 04:14:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.31.input_layernorm.weight", shape: (4096,), dtype: float16
27%|██▋ | 52/195 [00:17<00:32, 4.36it/s] [2024-06-02 04:14:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
27%|██▋ | 52/195 [00:17<00:32, 4.36it/s] [2024-06-02 04:14:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
27%|██▋ | 52/195 [00:17<00:32, 4.36it/s] 28%|██▊ | 55/195 [00:17<00:26, 5.24it/s] [2024-06-02 04:14:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
28%|██▊ | 55/195 [00:17<00:26, 5.24it/s] [2024-06-02 04:14:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
28%|██▊ | 55/195 [00:18<00:26, 5.24it/s] 29%|██▊ | 56/195 [00:18<00:38, 3.62it/s] [2024-06-02 04:14:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.31.post_attention_layernorm.weight", shape: (4096,), dtype: float16
29%|██▊ | 56/195 [00:18<00:38, 3.62it/s] [2024-06-02 04:14:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
29%|██▊ | 56/195 [00:18<00:38, 3.62it/s] [2024-06-02 04:14:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
29%|██▊ | 56/195 [00:18<00:38, 3.62it/s] 30%|██▉ | 58/195 [00:18<00:29, 4.60it/s] [2024-06-02 04:14:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
30%|██▉ | 58/195 [00:18<00:29, 4.60it/s] [2024-06-02 04:14:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
30%|██▉ | 58/195 [00:18<00:29, 4.60it/s] [2024-06-02 04:14:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.norm.weight", shape: (4096,), dtype: float16
30%|██▉ | 58/195 [00:18<00:29, 4.60it/s] [2024-06-02 04:14:01] INFO huggingface_loader.py:196: Unloading HF weight file: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/model-00003-of-00003.safetensors
30%|██▉ | 58/195 [00:18<00:29, 4.60it/s] [2024-06-02 04:14:02] INFO huggingface_loader.py:184: Loading HF parameters from: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/model-00001-of-00003.safetensors
30%|██▉ | 58/195 [00:18<00:29, 4.60it/s] [2024-06-02 04:14:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (32768, 512), dtype: uint32
30%|██▉ | 58/195 [00:20<00:29, 4.60it/s] [2024-06-02 04:14:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (32768, 128), dtype: float16
30%|██▉ | 58/195 [00:20<00:29, 4.60it/s] 31%|███▏ | 61/195 [00:20<00:54, 2.45it/s] [2024-06-02 04:14:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (4096,), dtype: float16
31%|███▏ | 61/195 [00:20<00:54, 2.45it/s] [2024-06-02 04:14:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
31%|███▏ | 61/195 [00:20<00:54, 2.45it/s] [2024-06-02 04:14:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
31%|███▏ | 61/195 [00:20<00:54, 2.45it/s] 32%|███▏ | 63/195 [00:20<00:47, 2.79it/s] [2024-06-02 04:14:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
32%|███▏ | 63/195 [00:21<00:47, 2.79it/s] [2024-06-02 04:14:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
32%|███▏ | 63/195 [00:21<00:47, 2.79it/s] 33%|███▎ | 64/195 [00:21<00:54, 2.39it/s] [2024-06-02 04:14:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (4096,), dtype: float16
33%|███▎ | 64/195 [00:21<00:54, 2.39it/s] [2024-06-02 04:14:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
33%|███▎ | 64/195 [00:21<00:54, 2.39it/s] [2024-06-02 04:14:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
33%|███▎ | 64/195 [00:21<00:54, 2.39it/s] 34%|███▍ | 66/195 [00:21<00:42, 3.05it/s] [2024-06-02 04:14:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
34%|███▍ | 66/195 [00:22<00:42, 3.05it/s] [2024-06-02 04:14:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
34%|███▍ | 66/195 [00:22<00:42, 3.05it/s] 34%|███▍ | 67/195 [00:22<00:37, 3.40it/s] [2024-06-02 04:14:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (4096,), dtype: float16
34%|███▍ | 67/195 [00:22<00:37, 3.40it/s] [2024-06-02 04:14:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
34%|███▍ | 67/195 [00:22<00:37, 3.40it/s] [2024-06-02 04:14:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
34%|███▍ | 67/195 [00:22<00:37, 3.40it/s] 35%|███▌ | 69/195 [00:22<00:31, 4.00it/s] [2024-06-02 04:14:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
35%|███▌ | 69/195 [00:22<00:31, 4.00it/s] [2024-06-02 04:14:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
35%|███▌ | 69/195 [00:23<00:31, 4.00it/s] 36%|███▌ | 70/195 [00:23<00:42, 2.92it/s] [2024-06-02 04:14:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (4096,), dtype: float16
36%|███▌ | 70/195 [00:23<00:42, 2.92it/s] [2024-06-02 04:14:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
36%|███▌ | 70/195 [00:23<00:42, 2.92it/s] [2024-06-02 04:14:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
36%|███▌ | 70/195 [00:23<00:42, 2.92it/s] 37%|███▋ | 72/195 [00:23<00:35, 3.49it/s] [2024-06-02 04:14:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
37%|███▋ | 72/195 [00:23<00:35, 3.49it/s] [2024-06-02 04:14:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
37%|███▋ | 72/195 [00:23<00:35, 3.49it/s] [2024-06-02 04:14:07] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
37%|███▋ | 72/195 [00:24<00:35, 3.49it/s] [2024-06-02 04:14:07] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
37%|███▋ | 72/195 [00:24<00:35, 3.49it/s] 38%|███▊ | 74/195 [00:24<00:38, 3.11it/s] [2024-06-02 04:14:07] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
38%|███▊ | 74/195 [00:24<00:38, 3.11it/s] [2024-06-02 04:14:07] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
38%|███▊ | 74/195 [00:24<00:38, 3.11it/s] 38%|███▊ | 75/195 [00:24<00:33, 3.57it/s] [2024-06-02 04:14:07] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
38%|███▊ | 75/195 [00:24<00:33, 3.57it/s] [2024-06-02 04:14:07] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
38%|███▊ | 75/195 [00:24<00:33, 3.57it/s] 39%|███▉ | 76/195 [00:24<00:30, 3.89it/s] [2024-06-02 04:14:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (4096,), dtype: float16
39%|███▉ | 76/195 [00:24<00:30, 3.89it/s] [2024-06-02 04:14:08] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
39%|███▉ | 76/195 [00:24<00:30, 3.89it/s] [2024-06-02 04:14:08] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
39%|███▉ | 76/195 [00:24<00:30, 3.89it/s] 40%|████ | 78/195 [00:24<00:25, 4.52it/s] [2024-06-02 04:14:08] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
40%|████ | 78/195 [00:25<00:25, 4.52it/s] [2024-06-02 04:14:08] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
40%|████ | 78/195 [00:25<00:25, 4.52it/s] 41%|████ | 79/195 [00:25<00:38, 3.05it/s] [2024-06-02 04:14:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (4096,), dtype: float16
41%|████ | 79/195 [00:25<00:38, 3.05it/s] [2024-06-02 04:14:09] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
41%|████ | 79/195 [00:25<00:38, 3.05it/s] [2024-06-02 04:14:09] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
41%|████ | 79/195 [00:25<00:38, 3.05it/s] 42%|████▏ | 81/195 [00:25<00:28, 4.06it/s] [2024-06-02 04:14:09] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
42%|████▏ | 81/195 [00:25<00:28, 4.06it/s] [2024-06-02 04:14:09] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
42%|████▏ | 81/195 [00:25<00:28, 4.06it/s] [2024-06-02 04:14:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (4096,), dtype: float16
42%|████▏ | 81/195 [00:25<00:28, 4.06it/s] [2024-06-02 04:14:09] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
42%|████▏ | 81/195 [00:26<00:28, 4.06it/s] [2024-06-02 04:14:09] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
42%|████▏ | 81/195 [00:26<00:28, 4.06it/s] 43%|████▎ | 84/195 [00:26<00:21, 5.14it/s] [2024-06-02 04:14:10] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
43%|████▎ | 84/195 [00:26<00:21, 5.14it/s] [2024-06-02 04:14:10] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
43%|████▎ | 84/195 [00:26<00:21, 5.14it/s] 44%|████▎ | 85/195 [00:26<00:31, 3.49it/s] [2024-06-02 04:14:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (4096,), dtype: float16
44%|████▎ | 85/195 [00:26<00:31, 3.49it/s] [2024-06-02 04:14:10] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
44%|████▎ | 85/195 [00:27<00:31, 3.49it/s] [2024-06-02 04:14:10] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
44%|████▎ | 85/195 [00:27<00:31, 3.49it/s] 45%|████▍ | 87/195 [00:27<00:23, 4.53it/s] [2024-06-02 04:14:10] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
45%|████▍ | 87/195 [00:27<00:23, 4.53it/s] [2024-06-02 04:14:10] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
45%|████▍ | 87/195 [00:27<00:23, 4.53it/s] [2024-06-02 04:14:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (4096,), dtype: float16
45%|████▍ | 87/195 [00:27<00:23, 4.53it/s] [2024-06-02 04:14:10] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
45%|████▍ | 87/195 [00:27<00:23, 4.53it/s] [2024-06-02 04:14:10] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
45%|████▍ | 87/195 [00:27<00:23, 4.53it/s] 46%|████▌ | 90/195 [00:27<00:19, 5.40it/s] [2024-06-02 04:14:11] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
46%|████▌ | 90/195 [00:28<00:19, 5.40it/s] [2024-06-02 04:14:11] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
46%|████▌ | 90/195 [00:28<00:19, 5.40it/s] 47%|████▋ | 91/195 [00:28<00:30, 3.40it/s] [2024-06-02 04:14:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (4096,), dtype: float16
47%|████▋ | 91/195 [00:28<00:30, 3.40it/s] [2024-06-02 04:14:11] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
47%|████▋ | 91/195 [00:28<00:30, 3.40it/s] [2024-06-02 04:14:11] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
47%|████▋ | 91/195 [00:28<00:30, 3.40it/s] 48%|████▊ | 93/195 [00:28<00:22, 4.62it/s] [2024-06-02 04:14:11] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
48%|████▊ | 93/195 [00:28<00:22, 4.62it/s] [2024-06-02 04:14:11] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
48%|████▊ | 93/195 [00:28<00:22, 4.62it/s] [2024-06-02 04:14:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (4096,), dtype: float16
48%|████▊ | 93/195 [00:28<00:22, 4.62it/s] [2024-06-02 04:14:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
48%|████▊ | 93/195 [00:28<00:22, 4.62it/s] [2024-06-02 04:14:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
48%|████▊ | 93/195 [00:28<00:22, 4.62it/s] 49%|████▉ | 96/195 [00:29<00:19, 5.01it/s] [2024-06-02 04:14:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
49%|████▉ | 96/195 [00:29<00:19, 5.01it/s] [2024-06-02 04:14:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
49%|████▉ | 96/195 [00:29<00:19, 5.01it/s] 50%|████▉ | 97/195 [00:29<00:27, 3.51it/s] [2024-06-02 04:14:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (4096,), dtype: float16
50%|████▉ | 97/195 [00:29<00:27, 3.51it/s] [2024-06-02 04:14:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
50%|████▉ | 97/195 [00:29<00:27, 3.51it/s] [2024-06-02 04:14:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
50%|████▉ | 97/195 [00:29<00:27, 3.51it/s] 51%|█████ | 99/195 [00:29<00:20, 4.74it/s] [2024-06-02 04:14:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
51%|█████ | 99/195 [00:29<00:20, 4.74it/s] [2024-06-02 04:14:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
51%|█████ | 99/195 [00:30<00:20, 4.74it/s] [2024-06-02 04:14:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (4096,), dtype: float16
51%|█████ | 99/195 [00:30<00:20, 4.74it/s] 52%|█████▏ | 101/195 [00:30<00:16, 5.87it/s] [2024-06-02 04:14:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
52%|█████▏ | 101/195 [00:30<00:16, 5.87it/s] [2024-06-02 04:14:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
52%|█████▏ | 101/195 [00:30<00:16, 5.87it/s] [2024-06-02 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
52%|█████▏ | 101/195 [00:30<00:16, 5.87it/s] [2024-06-02 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
52%|█████▏ | 101/195 [00:31<00:16, 5.87it/s] 53%|█████▎ | 103/195 [00:31<00:25, 3.58it/s] [2024-06-02 04:14:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (4096,), dtype: float16
53%|█████▎ | 103/195 [00:31<00:25, 3.58it/s] [2024-06-02 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
53%|█████▎ | 103/195 [00:31<00:25, 3.58it/s] [2024-06-02 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
53%|█████▎ | 103/195 [00:31<00:25, 3.58it/s] 54%|█████▍ | 105/195 [00:31<00:20, 4.40it/s] [2024-06-02 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
54%|█████▍ | 105/195 [00:31<00:20, 4.40it/s] [2024-06-02 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
54%|█████▍ | 105/195 [00:31<00:20, 4.40it/s] [2024-06-02 04:14:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (4096,), dtype: float16
54%|█████▍ | 105/195 [00:31<00:20, 4.40it/s] [2024-06-02 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
54%|█████▍ | 105/195 [00:31<00:20, 4.40it/s] [2024-06-02 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
54%|█████▍ | 105/195 [00:31<00:20, 4.40it/s] 55%|█████▌ | 108/195 [00:31<00:16, 5.25it/s] [2024-06-02 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
55%|█████▌ | 108/195 [00:32<00:16, 5.25it/s] [2024-06-02 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
55%|█████▌ | 108/195 [00:32<00:16, 5.25it/s] 56%|█████▌ | 109/195 [00:32<00:23, 3.64it/s] [2024-06-02 04:14:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (4096,), dtype: float16
56%|█████▌ | 109/195 [00:32<00:23, 3.64it/s] [2024-06-02 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
56%|█████▌ | 109/195 [00:32<00:23, 3.64it/s] [2024-06-02 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
56%|█████▌ | 109/195 [00:32<00:23, 3.64it/s] 57%|█████▋ | 111/195 [00:32<00:18, 4.56it/s] [2024-06-02 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
57%|█████▋ | 111/195 [00:32<00:18, 4.56it/s] [2024-06-02 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
57%|█████▋ | 111/195 [00:32<00:18, 4.56it/s] [2024-06-02 04:14:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (4096,), dtype: float16
57%|█████▋ | 111/195 [00:32<00:18, 4.56it/s] [2024-06-02 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
57%|█████▋ | 111/195 [00:32<00:18, 4.56it/s] [2024-06-02 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
57%|█████▋ | 111/195 [00:32<00:18, 4.56it/s] 58%|█████▊ | 114/195 [00:33<00:15, 5.36it/s] [2024-06-02 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
58%|█████▊ | 114/195 [00:33<00:15, 5.36it/s] [2024-06-02 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
58%|█████▊ | 114/195 [00:33<00:15, 5.36it/s] 59%|█████▉ | 115/195 [00:33<00:23, 3.40it/s] [2024-06-02 04:14:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (4096,), dtype: float16
59%|█████▉ | 115/195 [00:33<00:23, 3.40it/s] [2024-06-02 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
59%|█████▉ | 115/195 [00:33<00:23, 3.40it/s] [2024-06-02 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
59%|█████▉ | 115/195 [00:33<00:23, 3.40it/s] 60%|██████ | 117/195 [00:33<00:17, 4.57it/s] [2024-06-02 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
60%|██████ | 117/195 [00:34<00:17, 4.57it/s] [2024-06-02 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
60%|██████ | 117/195 [00:34<00:17, 4.57it/s] [2024-06-02 04:14:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (4096,), dtype: float16
60%|██████ | 117/195 [00:34<00:17, 4.57it/s] [2024-06-02 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
60%|██████ | 117/195 [00:34<00:17, 4.57it/s] [2024-06-02 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
60%|██████ | 117/195 [00:34<00:17, 4.57it/s] 62%|██████▏ | 120/195 [00:34<00:15, 4.99it/s] [2024-06-02 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
62%|██████▏ | 120/195 [00:34<00:15, 4.99it/s] [2024-06-02 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
62%|██████▏ | 120/195 [00:35<00:15, 4.99it/s] 62%|██████▏ | 121/195 [00:35<00:21, 3.51it/s] [2024-06-02 04:14:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (4096,), dtype: float16
62%|██████▏ | 121/195 [00:35<00:21, 3.51it/s] [2024-06-02 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
62%|██████▏ | 121/195 [00:35<00:21, 3.51it/s] [2024-06-02 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
62%|██████▏ | 121/195 [00:35<00:21, 3.51it/s] 63%|██████▎ | 123/195 [00:35<00:15, 4.72it/s] [2024-06-02 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
63%|██████▎ | 123/195 [00:35<00:15, 4.72it/s] [2024-06-02 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
63%|██████▎ | 123/195 [00:35<00:15, 4.72it/s] [2024-06-02 04:14:18] INFO huggingface_loader.py:196: Unloading HF weight file: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/model-00001-of-00003.safetensors
63%|██████▎ | 123/195 [00:35<00:15, 4.72it/s] [2024-06-02 04:14:19] INFO huggingface_loader.py:184: Loading HF parameters from: /ssd1/rickzhou/models/Mistral-7B-Instruct-v0.3/model-00002-of-00003.safetensors
63%|██████▎ | 123/195 [00:35<00:15, 4.72it/s] [2024-06-02 04:14:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (4096,), dtype: float16
63%|██████▎ | 123/195 [00:36<00:15, 4.72it/s] 64%|██████▍ | 125/195 [00:36<00:22, 3.06it/s] [2024-06-02 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
64%|██████▍ | 125/195 [00:36<00:22, 3.06it/s] [2024-06-02 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
64%|██████▍ | 125/195 [00:36<00:22, 3.06it/s] 65%|██████▍ | 126/195 [00:36<00:22, 3.02it/s] [2024-06-02 04:14:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (4096,), dtype: float16
65%|██████▍ | 126/195 [00:36<00:22, 3.02it/s] [2024-06-02 04:14:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (4096,), dtype: float16
65%|██████▍ | 126/195 [00:36<00:22, 3.02it/s] [2024-06-02 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
65%|██████▍ | 126/195 [00:37<00:22, 3.02it/s] [2024-06-02 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
65%|██████▍ | 126/195 [00:37<00:22, 3.02it/s] 66%|██████▌ | 129/195 [00:37<00:15, 4.26it/s] [2024-06-02 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
66%|██████▌ | 129/195 [00:37<00:15, 4.26it/s] [2024-06-02 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
66%|██████▌ | 129/195 [00:37<00:15, 4.26it/s] 67%|██████▋ | 130/195 [00:37<00:20, 3.13it/s] [2024-06-02 04:14:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (4096,), dtype: float16
67%|██████▋ | 130/195 [00:37<00:20, 3.13it/s] [2024-06-02 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
67%|██████▋ | 130/195 [00:38<00:20, 3.13it/s] [2024-06-02 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
67%|██████▋ | 130/195 [00:38<00:20, 3.13it/s] 68%|██████▊ | 132/195 [00:38<00:15, 4.09it/s] [2024-06-02 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
68%|██████▊ | 132/195 [00:38<00:15, 4.09it/s] [2024-06-02 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
68%|██████▊ | 132/195 [00:38<00:15, 4.09it/s] [2024-06-02 04:14:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (4096,), dtype: float16
68%|██████▊ | 132/195 [00:38<00:15, 4.09it/s] [2024-06-02 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
68%|██████▊ | 132/195 [00:38<00:15, 4.09it/s] [2024-06-02 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
68%|██████▊ | 132/195 [00:38<00:15, 4.09it/s] 69%|██████▉ | 135/195 [00:38<00:11, 5.00it/s] [2024-06-02 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
69%|██████▉ | 135/195 [00:38<00:11, 5.00it/s] [2024-06-02 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
69%|██████▉ | 135/195 [00:39<00:11, 5.00it/s] 70%|██████▉ | 136/195 [00:39<00:18, 3.26it/s] [2024-06-02 04:14:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (4096,), dtype: float16
70%|██████▉ | 136/195 [00:39<00:18, 3.26it/s] [2024-06-02 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
70%|██████▉ | 136/195 [00:39<00:18, 3.26it/s] [2024-06-02 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
70%|██████▉ | 136/195 [00:39<00:18, 3.26it/s] 71%|███████ | 138/195 [00:39<00:12, 4.42it/s] [2024-06-02 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
71%|███████ | 138/195 [00:39<00:12, 4.42it/s] [2024-06-02 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
71%|███████ | 138/195 [00:39<00:12, 4.42it/s] [2024-06-02 04:14:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (4096,), dtype: float16
71%|███████ | 138/195 [00:39<00:12, 4.42it/s] [2024-06-02 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
71%|███████ | 138/195 [00:39<00:12, 4.42it/s] [2024-06-02 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
71%|███████ | 138/195 [00:39<00:12, 4.42it/s] 72%|███████▏ | 141/195 [00:39<00:11, 4.86it/s] [2024-06-02 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
72%|███████▏ | 141/195 [00:40<00:11, 4.86it/s] [2024-06-02 04:14:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
72%|███████▏ | 141/195 [00:40<00:11, 4.86it/s] 73%|███████▎ | 142/195 [00:40<00:15, 3.42it/s] [2024-06-02 04:14:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (4096,), dtype: float16
73%|███████▎ | 142/195 [00:40<00:15, 3.42it/s] [2024-06-02 04:14:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
73%|███████▎ | 142/195 [00:40<00:15, 3.42it/s] [2024-06-02 04:14:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
73%|███████▎ | 142/195 [00:40<00:15, 3.42it/s] 74%|███████▍ | 144/195 [00:40<00:11, 4.62it/s] [2024-06-02 04:14:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
74%|███████▍ | 144/195 [00:40<00:11, 4.62it/s] [2024-06-02 04:14:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
74%|███████▍ | 144/195 [00:40<00:11, 4.62it/s] [2024-06-02 04:14:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (4096,), dtype: float16
74%|███████▍ | 144/195 [00:40<00:11, 4.62it/s] 75%|███████▍ | 146/195 [00:40<00:08, 5.72it/s] [2024-06-02 04:14:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
75%|███████▍ | 146/195 [00:41<00:08, 5.72it/s] [2024-06-02 04:14:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
75%|███████▍ | 146/195 [00:41<00:08, 5.72it/s] [2024-06-02 04:14:25] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
75%|███████▍ | 146/195 [00:41<00:08, 5.72it/s] [2024-06-02 04:14:25] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
75%|███████▍ | 146/195 [00:42<00:08, 5.72it/s] 76%|███████▌ | 148/195 [00:42<00:13, 3.51it/s] [2024-06-02 04:14:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (4096,), dtype: float16
76%|███████▌ | 148/195 [00:42<00:13, 3.51it/s] [2024-06-02 04:14:25] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
76%|███████▌ | 148/195 [00:42<00:13, 3.51it/s] [2024-06-02 04:14:25] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
76%|███████▌ | 148/195 [00:42<00:13, 3.51it/s] 77%|███████▋ | 150/195 [00:42<00:10, 4.26it/s] [2024-06-02 04:14:25] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
77%|███████▋ | 150/195 [00:42<00:10, 4.26it/s] [2024-06-02 04:14:25] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
77%|███████▋ | 150/195 [00:42<00:10, 4.26it/s] [2024-06-02 04:14:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (4096,), dtype: float16
77%|███████▋ | 150/195 [00:42<00:10, 4.26it/s] [2024-06-02 04:14:25] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
77%|███████▋ | 150/195 [00:42<00:10, 4.26it/s] [2024-06-02 04:14:26] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
77%|███████▋ | 150/195 [00:42<00:10, 4.26it/s] 78%|███████▊ | 153/195 [00:42<00:08, 5.15it/s] [2024-06-02 04:14:26] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
78%|███████▊ | 153/195 [00:43<00:08, 5.15it/s] [2024-06-02 04:14:26] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
78%|███████▊ | 153/195 [00:43<00:08, 5.15it/s] 79%|███████▉ | 154/195 [00:43<00:11, 3.57it/s] [2024-06-02 04:14:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (4096,), dtype: float16
79%|███████▉ | 154/195 [00:43<00:11, 3.57it/s] [2024-06-02 04:14:26] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
79%|███████▉ | 154/195 [00:43<00:11, 3.57it/s] [2024-06-02 04:14:26] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
79%|███████▉ | 154/195 [00:43<00:11, 3.57it/s] 80%|████████ | 156/195 [00:43<00:08, 4.49it/s] [2024-06-02 04:14:27] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
80%|████████ | 156/195 [00:43<00:08, 4.49it/s] [2024-06-02 04:14:27] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
80%|████████ | 156/195 [00:43<00:08, 4.49it/s] [2024-06-02 04:14:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (4096,), dtype: float16
80%|████████ | 156/195 [00:43<00:08, 4.49it/s] [2024-06-02 04:14:27] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
80%|████████ | 156/195 [00:43<00:08, 4.49it/s] [2024-06-02 04:14:27] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
80%|████████ | 156/195 [00:44<00:08, 4.49it/s] 82%|████████▏ | 159/195 [00:44<00:06, 5.31it/s] [2024-06-02 04:14:27] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
82%|████████▏ | 159/195 [00:44<00:06, 5.31it/s] [2024-06-02 04:14:28] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
82%|████████▏ | 159/195 [00:44<00:06, 5.31it/s] 82%|████████▏ | 160/195 [00:44<00:10, 3.41it/s] [2024-06-02 04:14:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (4096,), dtype: float16
82%|████████▏ | 160/195 [00:44<00:10, 3.41it/s] [2024-06-02 04:14:28] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
82%|████████▏ | 160/195 [00:44<00:10, 3.41it/s] [2024-06-02 04:14:28] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
82%|████████▏ | 160/195 [00:44<00:10, 3.41it/s] 83%|████████▎ | 162/195 [00:44<00:07, 4.59it/s] [2024-06-02 04:14:28] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
83%|████████▎ | 162/195 [00:45<00:07, 4.59it/s] [2024-06-02 04:14:28] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
83%|████████▎ | 162/195 [00:45<00:07, 4.59it/s] [2024-06-02 04:14:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (4096,), dtype: float16
83%|████████▎ | 162/195 [00:45<00:07, 4.59it/s] [2024-06-02 04:14:28] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
83%|████████▎ | 162/195 [00:45<00:07, 4.59it/s] [2024-06-02 04:14:28] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
83%|████████▎ | 162/195 [00:45<00:07, 4.59it/s] 85%|████████▍ | 165/195 [00:45<00:06, 4.98it/s] [2024-06-02 04:14:29] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
85%|████████▍ | 165/195 [00:45<00:06, 4.98it/s] [2024-06-02 04:14:29] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
85%|████████▍ | 165/195 [00:46<00:06, 4.98it/s] 85%|████████▌ | 166/195 [00:46<00:08, 3.53it/s] [2024-06-02 04:14:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (4096,), dtype: float16
85%|████████▌ | 166/195 [00:46<00:08, 3.53it/s] [2024-06-02 04:14:29] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
85%|████████▌ | 166/195 [00:46<00:08, 3.53it/s] [2024-06-02 04:14:29] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
85%|████████▌ | 166/195 [00:46<00:08, 3.53it/s] 86%|████████▌ | 168/195 [00:46<00:05, 4.75it/s] [2024-06-02 04:14:29] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
86%|████████▌ | 168/195 [00:46<00:05, 4.75it/s] [2024-06-02 04:14:29] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
86%|████████▌ | 168/195 [00:46<00:05, 4.75it/s] [2024-06-02 04:14:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (4096,), dtype: float16
86%|████████▌ | 168/195 [00:46<00:05, 4.75it/s] 87%|████████▋ | 170/195 [00:46<00:04, 5.84it/s] [2024-06-02 04:14:30] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
87%|████████▋ | 170/195 [00:46<00:04, 5.84it/s] [2024-06-02 04:14:30] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
87%|████████▋ | 170/195 [00:46<00:04, 5.84it/s] [2024-06-02 04:14:30] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
87%|████████▋ | 170/195 [00:47<00:04, 5.84it/s] [2024-06-02 04:14:30] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
87%|████████▋ | 170/195 [00:47<00:04, 5.84it/s] 88%|████████▊ | 172/195 [00:47<00:06, 3.57it/s] [2024-06-02 04:14:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (4096,), dtype: float16
88%|████████▊ | 172/195 [00:47<00:06, 3.57it/s] [2024-06-02 04:14:30] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
88%|████████▊ | 172/195 [00:47<00:06, 3.57it/s] [2024-06-02 04:14:30] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
88%|████████▊ | 172/195 [00:47<00:06, 3.57it/s] 89%|████████▉ | 174/195 [00:47<00:04, 4.33it/s] [2024-06-02 04:14:31] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
89%|████████▉ | 174/195 [00:47<00:04, 4.33it/s] [2024-06-02 04:14:31] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
89%|████████▉ | 174/195 [00:47<00:04, 4.33it/s] [2024-06-02 04:14:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (4096,), dtype: float16
89%|████████▉ | 174/195 [00:47<00:04, 4.33it/s] [2024-06-02 04:14:31] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
89%|████████▉ | 174/195 [00:48<00:04, 4.33it/s] [2024-06-02 04:14:31] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
89%|████████▉ | 174/195 [00:48<00:04, 4.33it/s] 91%|█████████ | 177/195 [00:48<00:03, 5.21it/s] [2024-06-02 04:14:31] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
91%|█████████ | 177/195 [00:48<00:03, 5.21it/s] [2024-06-02 04:14:32] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
91%|█████████ | 177/195 [00:48<00:03, 5.21it/s] 91%|█████████▏| 178/195 [00:48<00:04, 3.60it/s] [2024-06-02 04:14:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (4096,), dtype: float16
91%|█████████▏| 178/195 [00:48<00:04, 3.60it/s] [2024-06-02 04:14:32] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
91%|█████████▏| 178/195 [00:49<00:04, 3.60it/s] [2024-06-02 04:14:32] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
91%|█████████▏| 178/195 [00:49<00:04, 3.60it/s] 92%|█████████▏| 180/195 [00:49<00:03, 4.52it/s] [2024-06-02 04:14:32] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
92%|█████████▏| 180/195 [00:49<00:03, 4.52it/s] [2024-06-02 04:14:32] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
92%|█████████▏| 180/195 [00:49<00:03, 4.52it/s] [2024-06-02 04:14:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (4096,), dtype: float16
92%|█████████▏| 180/195 [00:49<00:03, 4.52it/s] [2024-06-02 04:14:32] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
92%|█████████▏| 180/195 [00:49<00:03, 4.52it/s] [2024-06-02 04:14:32] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
92%|█████████▏| 180/195 [00:49<00:03, 4.52it/s] 94%|█████████▍| 183/195 [00:49<00:02, 5.34it/s] [2024-06-02 04:14:33] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
94%|█████████▍| 183/195 [00:49<00:02, 5.34it/s] [2024-06-02 04:14:33] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
94%|█████████▍| 183/195 [00:50<00:02, 5.34it/s] 94%|█████████▍| 184/195 [00:50<00:03, 3.39it/s] [2024-06-02 04:14:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (4096,), dtype: float16
94%|█████████▍| 184/195 [00:50<00:03, 3.39it/s] [2024-06-02 04:14:33] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
94%|█████████▍| 184/195 [00:50<00:03, 3.39it/s] [2024-06-02 04:14:33] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
94%|█████████▍| 184/195 [00:50<00:03, 3.39it/s] 95%|█████████▌| 186/195 [00:50<00:01, 4.56it/s] [2024-06-02 04:14:33] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
95%|█████████▌| 186/195 [00:50<00:01, 4.56it/s] [2024-06-02 04:14:33] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
95%|█████████▌| 186/195 [00:50<00:01, 4.56it/s] [2024-06-02 04:14:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (4096,), dtype: float16
95%|█████████▌| 186/195 [00:50<00:01, 4.56it/s] [2024-06-02 04:14:34] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
95%|█████████▌| 186/195 [00:50<00:01, 4.56it/s] [2024-06-02 04:14:34] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float16
95%|█████████▌| 186/195 [00:50<00:01, 4.56it/s] 97%|█████████▋| 189/195 [00:51<00:01, 4.94it/s] [2024-06-02 04:14:34] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
97%|█████████▋| 189/195 [00:51<00:01, 4.94it/s] [2024-06-02 04:14:35] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float16
97%|█████████▋| 189/195 [00:51<00:01, 4.94it/s] 97%|█████████▋| 190/195 [00:51<00:01, 3.51it/s] [2024-06-02 04:14:35] INFO huggingface_loader.py:174: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (4096,), dtype: float16
97%|█████████▋| 190/195 [00:51<00:01, 3.51it/s] [2024-06-02 04:14:35] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
97%|█████████▋| 190/195 [00:51<00:01, 3.51it/s] [2024-06-02 04:14:35] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
97%|█████████▋| 190/195 [00:51<00:01, 3.51it/s] 98%|█████████▊| 192/195 [00:51<00:00, 4.72it/s] [2024-06-02 04:14:35] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
98%|█████████▊| 192/195 [00:51<00:00, 4.72it/s] [2024-06-02 04:14:35] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
98%|█████████▊| 192/195 [00:51<00:00, 4.72it/s] [2024-06-02 04:14:35] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
98%|█████████▊| 192/195 [00:52<00:00, 4.72it/s] [2024-06-02 04:14:35] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float16
98%|█████████▊| 192/195 [00:52<00:00, 4.72it/s] 99%|█████████▉| 194/195 [00:52<00:00, 5.41it/s] [2024-06-02 04:14:35] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
99%|█████████▉| 194/195 [00:52<00:00, 5.41it/s] [2024-06-02 04:14:35] INFO huggingface_loader.py:166: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
99%|█████████▉| 194/195 [00:52<00:00, 5.41it/s] 100%|██████████| 195/195 [00:52<00:00, 3.74it/s]
[2024-06-02 04:14:35] 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 04:14:35] INFO stats.py:76: Time usage: HF loading: 3.920 sec; Pre-quantization mapping: 27.399 sec; Quantization: 2.817 sec
[2024-06-02 04:14:35] INFO stats.py:90: RAM usage: Peak RAM: 9.313 GB. Total bytes loaded from disk: 27.001 GB
[2024-06-02 04:14:35] INFO convert_weight.py:155: Parameter size after quantization: 3.797 GB
[2024-06-02 04:14:35] INFO convert_weight.py:160: Total parameters: 7,248,023,552
[2024-06-02 04:14:35] INFO convert_weight.py:161: Bits per parameter: 4.500
[2024-06-02 04:14:35] INFO convert_weight.py:166: Saved to directory: /ssd2/models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q4f16_1-MLC
All finished, 106 total shards committed, record saved to /ssd2/models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q4f16_1-MLC/ndarray-cache.json