Hugging Face's logo

mlc-ai
/
Mistral-7B-Instruct-v0.3-q3f16_1-MLC

MLC-LLM
web-llm
Model card Files Community
Mistral-7B-Instruct-v0.3-q3f16_1-MLC / logs.txt
riczhou's picture
riczhou
Initial commit
dcd8eb8 verified
raw
history blame contribute delete
105 kB
 /opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Mistral-7B-Instruct-v0.3 --quantization q3f16_1 --conv-template mistral_default --output /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q3f16_1-MLC
[2024-06-06 21:59:28] INFO auto_config.py:116: Found model configuration: /models/Mistral-7B-Instruct-v0.3/config.json
[2024-06-06 21:59:28] INFO auto_config.py:154: Found model type: mistral. Use `--model-type` to override.
[2024-06-06 21:59:28] INFO mistral_model.py:59: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-06 21:59:28] INFO mistral_model.py:88: prefill_chunk_size defaults to 2048
[2024-06-06 21:59:28] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-06 21:59:28] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 1
[2024-06-06 21:59:28] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: 2
[2024-06-06 21:59:28] 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-q3f16_1-MLC/tokenizer.model
[2024-06-06 21:59:28] 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-q3f16_1-MLC/tokenizer.json
[2024-06-06 21:59:28] INFO gen_config.py:157: Not found tokenizer config: /models/Mistral-7B-Instruct-v0.3/vocab.json
[2024-06-06 21:59:28] INFO gen_config.py:157: Not found tokenizer config: /models/Mistral-7B-Instruct-v0.3/merges.txt
[2024-06-06 21:59:28] INFO gen_config.py:157: Not found tokenizer config: /models/Mistral-7B-Instruct-v0.3/added_tokens.json
[2024-06-06 21:59:28] 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-q3f16_1-MLC/tokenizer_config.json
[2024-06-06 21:59:28] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_fallback', 'prepend_space_in_encode': False, 'strip_space_in_decode': True}
[2024-06-06 21:59:28] INFO gen_config.py:32: [System default] Setting pad_token_id: 0
[2024-06-06 21:59:28] INFO gen_config.py:32: [System default] Setting temperature: 1.0
[2024-06-06 21:59:28] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-06 21:59:28] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-06 21:59:28] INFO gen_config.py:32: [System default] Setting repetition_penalty: 1.0
[2024-06-06 21:59:28] INFO gen_config.py:32: [System default] Setting top_p: 1.0
[2024-06-06 21:59:28] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q3f16_1-MLC/mlc-chat-config.json
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Mistral-7B-Instruct-v0.3 --quantization q3f16_1 --output /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q3f16_1-MLC
[2024-06-06 21:59:30] INFO auto_config.py:116: Found model configuration: /models/Mistral-7B-Instruct-v0.3/config.json
[2024-06-06 21:59:31] INFO auto_device.py:79: Found device: cuda:0
[2024-06-06 21:59:33] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-06 21:59:34] INFO auto_device.py:88: Not found device: metal:0
[2024-06-06 21:59:36] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-06 21:59:36] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-06 21:59:36] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-06 21:59:36] INFO auto_device.py:79: Found device: vulkan:3
[2024-06-06 21:59:38] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-06 21:59:38] INFO auto_device.py:35: Using device: cuda:0
[2024-06-06 21:59:38] INFO auto_weight.py:71: Finding weights in: /models/Mistral-7B-Instruct-v0.3
[2024-06-06 21:59:38] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-06 21:59:38] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /models/Mistral-7B-Instruct-v0.3/model.safetensors.index.json
[2024-06-06 21:59:38] INFO auto_weight.py:107: Using source weight configuration: /models/Mistral-7B-Instruct-v0.3/model.safetensors.index.json. Use `--source` to override.
[2024-06-06 21:59:38] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-06 21:59:38] INFO auto_config.py:154: Found model type: mistral. Use `--model-type` to override.
[2024-06-06 21:59:38] INFO mistral_model.py:59: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-06 21:59:38] INFO mistral_model.py:88: prefill_chunk_size defaults to 2048
Weight conversion with arguments:
--config /models/Mistral-7B-Instruct-v0.3/config.json
--quantization GroupQuantize(name='q3f16_1', kind='group-quant', group_size=40, quantize_dtype='int3', storage_dtype='uint32', model_dtype='float16', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=10, num_storage_per_group=4, max_int_value=3)
--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-q3f16_1-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q3f16_1-MLC
0%| | 0/195 [00:00<?, ?it/s] [2024-06-06 21:59:40] 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] [2024-06-06 21:59:50] INFO group_quantization.py:217: Compiling quantize function for key: ((32768, 4096), float16, cuda, axis=1, output_transpose=False)
0%| | 0/195 [00:10<?, ?it/s] [2024-06-06 21:59:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_weight", shape: (32768, 412), dtype: uint32
0%| | 0/195 [00:11<?, ?it/s] [2024-06-06 21:59:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_scale", shape: (32768, 103), dtype: float16
0%| | 0/195 [00:11<?, ?it/s] 1%| | 1/195 [00:11<37:48, 11.69s/it] [2024-06-06 21:59:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (4096,), dtype: float16
1%| | 1/195 [00:11<37:48, 11.69s/it] [2024-06-06 21:59:52] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 14336), float16, cuda, axis=1, output_transpose=False)
1%| | 1/195 [00:12<37:48, 11.69s/it] [2024-06-06 21:59:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
1%| | 1/195 [00:12<37:48, 11.69s/it] [2024-06-06 21:59:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
1%| | 1/195 [00:12<37:48, 11.69s/it] 2%|▏ | 3/195 [00:12<11:11, 3.50s/it] [2024-06-06 21:59:54] INFO group_quantization.py:217: Compiling quantize function for key: ((28672, 4096), float16, cuda, axis=1, output_transpose=False)
2%|▏ | 3/195 [00:14<11:11, 3.50s/it] [2024-06-06 21:59:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
2%|▏ | 3/195 [00:15<11:11, 3.50s/it] [2024-06-06 21:59:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
2%|▏ | 3/195 [00:15<11:11, 3.50s/it] 2%|▏ | 4/195 [00:15<09:52, 3.10s/it] [2024-06-06 21:59:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (4096,), dtype: float16
2%|▏ | 4/195 [00:15<09:52, 3.10s/it] [2024-06-06 21:59:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (4096,), dtype: float16
2%|▏ | 4/195 [00:15<09:52, 3.10s/it] [2024-06-06 21:59:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
2%|▏ | 4/195 [00:15<09:52, 3.10s/it] [2024-06-06 21:59:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
2%|▏ | 4/195 [00:15<09:52, 3.10s/it] 4%|▎ | 7/195 [00:15<04:05, 1.30s/it] [2024-06-06 21:59:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
4%|▎ | 7/195 [00:16<04:05, 1.30s/it] [2024-06-06 21:59:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
4%|▎ | 7/195 [00:16<04:05, 1.30s/it] 4%|▍ | 8/195 [00:16<04:06, 1.32s/it] [2024-06-06 21:59:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (4096,), dtype: float16
4%|▍ | 8/195 [00:16<04:06, 1.32s/it] [2024-06-06 21:59:57] INFO group_quantization.py:217: Compiling quantize function for key: ((6144, 4096), float16, cuda, axis=1, output_transpose=False)
4%|▍ | 8/195 [00:17<04:06, 1.32s/it] [2024-06-06 21:59:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
4%|▍ | 8/195 [00:17<04:06, 1.32s/it] [2024-06-06 21:59:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
4%|▍ | 8/195 [00:17<04:06, 1.32s/it] 5%|▌ | 10/195 [00:17<02:52, 1.07it/s] [2024-06-06 21:59:57] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 4096), float16, cuda, axis=1, output_transpose=False)
5%|▌ | 10/195 [00:17<02:52, 1.07it/s] [2024-06-06 21:59:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
5%|▌ | 10/195 [00:18<02:52, 1.07it/s] [2024-06-06 21:59:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
5%|▌ | 10/195 [00:18<02:52, 1.07it/s] 6%|▌ | 11/195 [00:18<02:36, 1.17it/s] [2024-06-06 21:59:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (4096,), dtype: float16
6%|▌ | 11/195 [00:18<02:36, 1.17it/s] [2024-06-06 21:59:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
6%|▌ | 11/195 [00:18<02:36, 1.17it/s] [2024-06-06 21:59:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
6%|▌ | 11/195 [00:18<02:36, 1.17it/s] 7%|▋ | 13/195 [00:18<01:46, 1.71it/s] [2024-06-06 21:59:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
7%|▋ | 13/195 [00:19<01:46, 1.71it/s] [2024-06-06 21:59:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
7%|▋ | 13/195 [00:19<01:46, 1.71it/s] 7%|▋ | 14/195 [00:19<01:54, 1.58it/s] [2024-06-06 21:59:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (4096,), dtype: float16
7%|▋ | 14/195 [00:19<01:54, 1.58it/s] [2024-06-06 21:59:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
7%|▋ | 14/195 [00:19<01:54, 1.58it/s] [2024-06-06 21:59:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
7%|▋ | 14/195 [00:19<01:54, 1.58it/s] 8%|▊ | 16/195 [00:19<01:14, 2.40it/s] [2024-06-06 21:59:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
8%|▊ | 16/195 [00:19<01:14, 2.40it/s] [2024-06-06 21:59:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
8%|▊ | 16/195 [00:19<01:14, 2.40it/s] [2024-06-06 21:59:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (4096,), dtype: float16
8%|▊ | 16/195 [00:19<01:14, 2.40it/s] [2024-06-06 21:59:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
8%|▊ | 16/195 [00:19<01:14, 2.40it/s] [2024-06-06 21:59:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
8%|▊ | 16/195 [00:19<01:14, 2.40it/s] 10%|▉ | 19/195 [00:19<00:50, 3.48it/s] [2024-06-06 22:00:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
10%|▉ | 19/195 [00:20<00:50, 3.48it/s] [2024-06-06 22:00:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
10%|▉ | 19/195 [00:20<00:50, 3.48it/s] 10%|█ | 20/195 [00:20<01:04, 2.72it/s] [2024-06-06 22:00:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (4096,), dtype: float16
10%|█ | 20/195 [00:20<01:04, 2.72it/s] [2024-06-06 22:00:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
10%|█ | 20/195 [00:20<01:04, 2.72it/s] [2024-06-06 22:00:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
10%|█ | 20/195 [00:20<01:04, 2.72it/s] 11%|█▏ | 22/195 [00:20<00:45, 3.77it/s] [2024-06-06 22:00:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
11%|█▏ | 22/195 [00:20<00:45, 3.77it/s] [2024-06-06 22:00:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
11%|█▏ | 22/195 [00:20<00:45, 3.77it/s] [2024-06-06 22:00:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (4096,), dtype: float16
11%|█▏ | 22/195 [00:20<00:45, 3.77it/s] [2024-06-06 22:00:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
11%|█▏ | 22/195 [00:20<00:45, 3.77it/s] [2024-06-06 22:00:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
11%|█▏ | 22/195 [00:21<00:45, 3.77it/s] 13%|█▎ | 25/195 [00:21<00:34, 4.89it/s] [2024-06-06 22:00:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
13%|█▎ | 25/195 [00:21<00:34, 4.89it/s] [2024-06-06 22:00:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
13%|█▎ | 25/195 [00:21<00:34, 4.89it/s] 13%|█▎ | 26/195 [00:21<00:48, 3.50it/s] [2024-06-06 22:00:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (4096,), dtype: float16
13%|█▎ | 26/195 [00:21<00:48, 3.50it/s] [2024-06-06 22:00:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
13%|█▎ | 26/195 [00:21<00:48, 3.50it/s] [2024-06-06 22:00:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
13%|█▎ | 26/195 [00:21<00:48, 3.50it/s] 14%|█▍ | 28/195 [00:21<00:35, 4.71it/s] [2024-06-06 22:00:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
14%|█▍ | 28/195 [00:21<00:35, 4.71it/s] [2024-06-06 22:00:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
14%|█▍ | 28/195 [00:21<00:35, 4.71it/s] [2024-06-06 22:00:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (4096,), dtype: float16
14%|█▍ | 28/195 [00:21<00:35, 4.71it/s] [2024-06-06 22:00:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
14%|█▍ | 28/195 [00:22<00:35, 4.71it/s] [2024-06-06 22:00:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
14%|█▍ | 28/195 [00:22<00:35, 4.71it/s] 16%|█▌ | 31/195 [00:22<00:28, 5.80it/s] [2024-06-06 22:00:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
16%|█▌ | 31/195 [00:22<00:28, 5.80it/s] [2024-06-06 22:00:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
16%|█▌ | 31/195 [00:22<00:28, 5.80it/s] 16%|█▋ | 32/195 [00:22<00:41, 3.88it/s] [2024-06-06 22:00:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (4096,), dtype: float16
16%|█▋ | 32/195 [00:22<00:41, 3.88it/s] [2024-06-06 22:00:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
16%|█▋ | 32/195 [00:22<00:41, 3.88it/s] [2024-06-06 22:00:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
16%|█▋ | 32/195 [00:22<00:41, 3.88it/s] 17%|█▋ | 34/195 [00:22<00:31, 5.17it/s] [2024-06-06 22:00:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
17%|█▋ | 34/195 [00:23<00:31, 5.17it/s] [2024-06-06 22:00:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
17%|█▋ | 34/195 [00:23<00:31, 5.17it/s] [2024-06-06 22:00:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.input_layernorm.weight", shape: (4096,), dtype: float16
17%|█▋ | 34/195 [00:23<00:31, 5.17it/s] [2024-06-06 22:00:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
17%|█▋ | 34/195 [00:23<00:31, 5.17it/s] [2024-06-06 22:00:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
17%|█▋ | 34/195 [00:23<00:31, 5.17it/s] 19%|█▉ | 37/195 [00:23<00:25, 6.16it/s] [2024-06-06 22:00:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
19%|█▉ | 37/195 [00:23<00:25, 6.16it/s] [2024-06-06 22:00:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
19%|█▉ | 37/195 [00:23<00:25, 6.16it/s] 19%|█▉ | 38/195 [00:24<00:39, 3.96it/s] [2024-06-06 22:00:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.post_attention_layernorm.weight", shape: (4096,), dtype: float16
19%|█▉ | 38/195 [00:24<00:39, 3.96it/s] [2024-06-06 22:00:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
19%|█▉ | 38/195 [00:24<00:39, 3.96it/s] [2024-06-06 22:00:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
19%|█▉ | 38/195 [00:24<00:39, 3.96it/s] 21%|██ | 40/195 [00:24<00:29, 5.24it/s] [2024-06-06 22:00:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
21%|██ | 40/195 [00:24<00:29, 5.24it/s] [2024-06-06 22:00:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
21%|██ | 40/195 [00:24<00:29, 5.24it/s] [2024-06-06 22:00:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.input_layernorm.weight", shape: (4096,), dtype: float16
21%|██ | 40/195 [00:24<00:29, 5.24it/s] [2024-06-06 22:00:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
21%|██ | 40/195 [00:24<00:29, 5.24it/s] [2024-06-06 22:00:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
21%|██ | 40/195 [00:24<00:29, 5.24it/s] 22%|██▏ | 43/195 [00:24<00:24, 6.10it/s] [2024-06-06 22:00:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
22%|██▏ | 43/195 [00:25<00:24, 6.10it/s] [2024-06-06 22:00:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
22%|██▏ | 43/195 [00:25<00:24, 6.10it/s] 23%|██▎ | 44/195 [00:25<00:38, 3.91it/s] [2024-06-06 22:00:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.post_attention_layernorm.weight", shape: (4096,), dtype: float16
23%|██▎ | 44/195 [00:25<00:38, 3.91it/s] [2024-06-06 22:00:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
23%|██▎ | 44/195 [00:25<00:38, 3.91it/s] [2024-06-06 22:00:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
23%|██▎ | 44/195 [00:25<00:38, 3.91it/s] 24%|██▎ | 46/195 [00:25<00:28, 5.18it/s] [2024-06-06 22:00:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
24%|██▎ | 46/195 [00:25<00:28, 5.18it/s] [2024-06-06 22:00:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
24%|██▎ | 46/195 [00:25<00:28, 5.18it/s] [2024-06-06 22:00:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.input_layernorm.weight", shape: (4096,), dtype: float16
24%|██▎ | 46/195 [00:25<00:28, 5.18it/s] [2024-06-06 22:00:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
24%|██▎ | 46/195 [00:25<00:28, 5.18it/s] [2024-06-06 22:00:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
24%|██▎ | 46/195 [00:25<00:28, 5.18it/s] 25%|██▌ | 49/195 [00:25<00:23, 6.14it/s] [2024-06-06 22:00:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
25%|██▌ | 49/195 [00:26<00:23, 6.14it/s] [2024-06-06 22:00:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
25%|██▌ | 49/195 [00:26<00:23, 6.14it/s] 26%|██▌ | 50/195 [00:26<00:39, 3.67it/s] [2024-06-06 22:00:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.post_attention_layernorm.weight", shape: (4096,), dtype: float16
26%|██▌ | 50/195 [00:26<00:39, 3.67it/s] [2024-06-06 22:00:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
26%|██▌ | 50/195 [00:26<00:39, 3.67it/s] [2024-06-06 22:00:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
26%|██▌ | 50/195 [00:26<00:39, 3.67it/s] 27%|██▋ | 52/195 [00:26<00:29, 4.87it/s] [2024-06-06 22:00:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
27%|██▋ | 52/195 [00:26<00:29, 4.87it/s] [2024-06-06 22:00:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
27%|██▋ | 52/195 [00:26<00:29, 4.87it/s] [2024-06-06 22:00:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.input_layernorm.weight", shape: (4096,), dtype: float16
27%|██▋ | 52/195 [00:26<00:29, 4.87it/s] [2024-06-06 22:00:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
27%|██▋ | 52/195 [00:26<00:29, 4.87it/s] [2024-06-06 22:00:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
27%|██▋ | 52/195 [00:27<00:29, 4.87it/s] 28%|██▊ | 55/195 [00:27<00:23, 5.86it/s] [2024-06-06 22:00:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
28%|██▊ | 55/195 [00:27<00:23, 5.86it/s] [2024-06-06 22:00:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
28%|██▊ | 55/195 [00:27<00:23, 5.86it/s] 29%|██▊ | 56/195 [00:27<00:38, 3.57it/s] [2024-06-06 22:00:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.post_attention_layernorm.weight", shape: (4096,), dtype: float16
29%|██▊ | 56/195 [00:27<00:38, 3.57it/s] [2024-06-06 22:00:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
29%|██▊ | 56/195 [00:28<00:38, 3.57it/s] [2024-06-06 22:00:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
29%|██▊ | 56/195 [00:28<00:38, 3.57it/s] 30%|██▉ | 58/195 [00:28<00:28, 4.77it/s] [2024-06-06 22:00:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
30%|██▉ | 58/195 [00:28<00:28, 4.77it/s] [2024-06-06 22:00:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
30%|██▉ | 58/195 [00:28<00:28, 4.77it/s] [2024-06-06 22:00:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (4096,), dtype: float16
30%|██▉ | 58/195 [00:28<00:28, 4.77it/s] [2024-06-06 22:00:08] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Mistral-7B-Instruct-v0.3/model-00003-of-00003.safetensors
30%|██▉ | 58/195 [00:28<00:28, 4.77it/s] [2024-06-06 22:00:08] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Mistral-7B-Instruct-v0.3/model-00001-of-00003.safetensors
30%|██▉ | 58/195 [00:28<00:28, 4.77it/s] [2024-06-06 22:00:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (32768, 412), dtype: uint32
30%|██▉ | 58/195 [00:35<00:28, 4.77it/s] [2024-06-06 22:00:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (32768, 103), dtype: float16
30%|██▉ | 58/195 [00:35<00:28, 4.77it/s] 31%|███▏ | 61/195 [00:35<02:34, 1.15s/it] [2024-06-06 22:00:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (4096,), dtype: float16
31%|███▏ | 61/195 [00:35<02:34, 1.15s/it] [2024-06-06 22:00:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
31%|███▏ | 61/195 [00:35<02:34, 1.15s/it] [2024-06-06 22:00:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
31%|███▏ | 61/195 [00:35<02:34, 1.15s/it] 32%|███▏ | 63/195 [00:36<01:57, 1.13it/s] [2024-06-06 22:00:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
32%|███▏ | 63/195 [00:37<01:57, 1.13it/s] [2024-06-06 22:00:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
32%|███▏ | 63/195 [00:37<01:57, 1.13it/s] 33%|███▎ | 64/195 [00:37<02:09, 1.01it/s] [2024-06-06 22:00:17] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (4096,), dtype: float16
33%|███▎ | 64/195 [00:37<02:09, 1.01it/s] [2024-06-06 22:00:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
33%|███▎ | 64/195 [00:37<02:09, 1.01it/s] [2024-06-06 22:00:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
33%|███▎ | 64/195 [00:37<02:09, 1.01it/s] 34%|███▍ | 66/195 [00:37<01:35, 1.35it/s] [2024-06-06 22:00:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
34%|███▍ | 66/195 [00:38<01:35, 1.35it/s] [2024-06-06 22:00:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
34%|███▍ | 66/195 [00:38<01:35, 1.35it/s] [2024-06-06 22:00:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (4096,), dtype: float16
34%|███▍ | 66/195 [00:38<01:35, 1.35it/s] [2024-06-06 22:00:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
34%|███▍ | 66/195 [00:38<01:35, 1.35it/s] [2024-06-06 22:00:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
34%|███▍ | 66/195 [00:38<01:35, 1.35it/s] 35%|███▌ | 69/195 [00:38<01:01, 2.05it/s] [2024-06-06 22:00:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
35%|███▌ | 69/195 [00:39<01:01, 2.05it/s] [2024-06-06 22:00:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
35%|███▌ | 69/195 [00:39<01:01, 2.05it/s] 36%|███▌ | 70/195 [00:39<01:19, 1.57it/s] [2024-06-06 22:00:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (4096,), dtype: float16
36%|███▌ | 70/195 [00:39<01:19, 1.57it/s] [2024-06-06 22:00:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
36%|███▌ | 70/195 [00:40<01:19, 1.57it/s] [2024-06-06 22:00:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
36%|███▌ | 70/195 [00:40<01:19, 1.57it/s] 37%|███▋ | 72/195 [00:40<00:58, 2.09it/s] [2024-06-06 22:00:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
37%|███▋ | 72/195 [00:40<00:58, 2.09it/s] [2024-06-06 22:00:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
37%|███▋ | 72/195 [00:40<00:58, 2.09it/s] [2024-06-06 22:00:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
37%|███▋ | 72/195 [00:41<00:58, 2.09it/s] [2024-06-06 22:00:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
37%|███▋ | 72/195 [00:41<00:58, 2.09it/s] 38%|███▊ | 74/195 [00:41<01:08, 1.77it/s] [2024-06-06 22:00:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
38%|███▊ | 74/195 [00:41<01:08, 1.77it/s] [2024-06-06 22:00:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
38%|███▊ | 74/195 [00:41<01:08, 1.77it/s] 38%|███▊ | 75/195 [00:41<00:59, 2.01it/s] [2024-06-06 22:00:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
38%|███▊ | 75/195 [00:41<00:59, 2.01it/s] [2024-06-06 22:00:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
38%|███▊ | 75/195 [00:41<00:59, 2.01it/s] [2024-06-06 22:00:21] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (4096,), dtype: float16
38%|███▊ | 75/195 [00:41<00:59, 2.01it/s] [2024-06-06 22:00:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
38%|███▊ | 75/195 [00:42<00:59, 2.01it/s] [2024-06-06 22:00:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
38%|███▊ | 75/195 [00:42<00:59, 2.01it/s] 40%|████ | 78/195 [00:42<00:38, 3.02it/s] [2024-06-06 22:00:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
40%|████ | 78/195 [00:42<00:38, 3.02it/s] [2024-06-06 22:00:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
40%|████ | 78/195 [00:43<00:38, 3.02it/s] 41%|████ | 79/195 [00:43<00:51, 2.26it/s] [2024-06-06 22:00:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (4096,), dtype: float16
41%|████ | 79/195 [00:43<00:51, 2.26it/s] [2024-06-06 22:00:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
41%|████ | 79/195 [00:43<00:51, 2.26it/s] [2024-06-06 22:00:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
41%|████ | 79/195 [00:43<00:51, 2.26it/s] 42%|████▏ | 81/195 [00:43<00:37, 3.08it/s] [2024-06-06 22:00:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
42%|████▏ | 81/195 [00:43<00:37, 3.08it/s] [2024-06-06 22:00:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
42%|████▏ | 81/195 [00:43<00:37, 3.08it/s] [2024-06-06 22:00:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (4096,), dtype: float16
42%|████▏ | 81/195 [00:43<00:37, 3.08it/s] [2024-06-06 22:00:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
42%|████▏ | 81/195 [00:43<00:37, 3.08it/s] [2024-06-06 22:00:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
42%|████▏ | 81/195 [00:43<00:37, 3.08it/s] 43%|████▎ | 84/195 [00:43<00:26, 4.17it/s] [2024-06-06 22:00:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
43%|████▎ | 84/195 [00:44<00:26, 4.17it/s] [2024-06-06 22:00:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
43%|████▎ | 84/195 [00:44<00:26, 4.17it/s] 44%|████▎ | 85/195 [00:44<00:33, 3.25it/s] [2024-06-06 22:00:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (4096,), dtype: float16
44%|████▎ | 85/195 [00:44<00:33, 3.25it/s] [2024-06-06 22:00:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
44%|████▎ | 85/195 [00:44<00:33, 3.25it/s] [2024-06-06 22:00:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
44%|████▎ | 85/195 [00:44<00:33, 3.25it/s] 45%|████▍ | 87/195 [00:44<00:25, 4.20it/s] [2024-06-06 22:00:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
45%|████▍ | 87/195 [00:44<00:25, 4.20it/s] [2024-06-06 22:00:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
45%|████▍ | 87/195 [00:44<00:25, 4.20it/s] [2024-06-06 22:00:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (4096,), dtype: float16
45%|████▍ | 87/195 [00:44<00:25, 4.20it/s] [2024-06-06 22:00:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
45%|████▍ | 87/195 [00:44<00:25, 4.20it/s] [2024-06-06 22:00:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
45%|████▍ | 87/195 [00:44<00:25, 4.20it/s] 46%|████▌ | 90/195 [00:44<00:19, 5.28it/s] [2024-06-06 22:00:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
46%|████▌ | 90/195 [00:45<00:19, 5.28it/s] [2024-06-06 22:00:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
46%|████▌ | 90/195 [00:45<00:19, 5.28it/s] 47%|████▋ | 91/195 [00:45<00:27, 3.79it/s] [2024-06-06 22:00:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (4096,), dtype: float16
47%|████▋ | 91/195 [00:45<00:27, 3.79it/s] [2024-06-06 22:00:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
47%|████▋ | 91/195 [00:45<00:27, 3.79it/s] [2024-06-06 22:00:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
47%|████▋ | 91/195 [00:45<00:27, 3.79it/s] 48%|████▊ | 93/195 [00:45<00:21, 4.81it/s] [2024-06-06 22:00:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
48%|████▊ | 93/195 [00:45<00:21, 4.81it/s] [2024-06-06 22:00:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
48%|████▊ | 93/195 [00:45<00:21, 4.81it/s] [2024-06-06 22:00:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (4096,), dtype: float16
48%|████▊ | 93/195 [00:45<00:21, 4.81it/s] [2024-06-06 22:00:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
48%|████▊ | 93/195 [00:45<00:21, 4.81it/s] [2024-06-06 22:00:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
48%|████▊ | 93/195 [00:45<00:21, 4.81it/s] 49%|████▉ | 96/195 [00:45<00:17, 5.80it/s] [2024-06-06 22:00:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
49%|████▉ | 96/195 [00:46<00:17, 5.80it/s] [2024-06-06 22:00:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
49%|████▉ | 96/195 [00:46<00:17, 5.80it/s] 50%|████▉ | 97/195 [00:46<00:24, 3.97it/s] [2024-06-06 22:00:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (4096,), dtype: float16
50%|████▉ | 97/195 [00:46<00:24, 3.97it/s] [2024-06-06 22:00:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
50%|████▉ | 97/195 [00:46<00:24, 3.97it/s] [2024-06-06 22:00:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
50%|████▉ | 97/195 [00:46<00:24, 3.97it/s] 51%|█████ | 99/195 [00:46<00:19, 4.98it/s] [2024-06-06 22:00:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
51%|█████ | 99/195 [00:46<00:19, 4.98it/s] [2024-06-06 22:00:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
51%|█████ | 99/195 [00:46<00:19, 4.98it/s] [2024-06-06 22:00:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (4096,), dtype: float16
51%|█████ | 99/195 [00:46<00:19, 4.98it/s] [2024-06-06 22:00:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
51%|█████ | 99/195 [00:47<00:19, 4.98it/s] [2024-06-06 22:00:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
51%|█████ | 99/195 [00:47<00:19, 4.98it/s] 52%|█████▏ | 102/195 [00:47<00:15, 5.87it/s] [2024-06-06 22:00:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
52%|█████▏ | 102/195 [00:47<00:15, 5.87it/s] [2024-06-06 22:00:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
52%|█████▏ | 102/195 [00:47<00:15, 5.87it/s] 53%|█████▎ | 103/195 [00:47<00:23, 3.98it/s] [2024-06-06 22:00:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (4096,), dtype: float16
53%|█████▎ | 103/195 [00:47<00:23, 3.98it/s] [2024-06-06 22:00:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
53%|█████▎ | 103/195 [00:47<00:23, 3.98it/s] [2024-06-06 22:00:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
53%|█████▎ | 103/195 [00:48<00:23, 3.98it/s] 54%|█████▍ | 105/195 [00:48<00:17, 5.00it/s] [2024-06-06 22:00:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
54%|█████▍ | 105/195 [00:48<00:17, 5.00it/s] [2024-06-06 22:00:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
54%|█████▍ | 105/195 [00:48<00:17, 5.00it/s] [2024-06-06 22:00:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (4096,), dtype: float16
54%|█████▍ | 105/195 [00:48<00:17, 5.00it/s] [2024-06-06 22:00:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
54%|█████▍ | 105/195 [00:48<00:17, 5.00it/s] [2024-06-06 22:00:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
54%|█████▍ | 105/195 [00:48<00:17, 5.00it/s] 55%|█████▌ | 108/195 [00:48<00:14, 5.86it/s] [2024-06-06 22:00:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
55%|█████▌ | 108/195 [00:48<00:14, 5.86it/s] [2024-06-06 22:00:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
55%|█████▌ | 108/195 [00:49<00:14, 5.86it/s] 56%|█████▌ | 109/195 [00:49<00:21, 4.00it/s] [2024-06-06 22:00:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (4096,), dtype: float16
56%|█████▌ | 109/195 [00:49<00:21, 4.00it/s] [2024-06-06 22:00:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
56%|█████▌ | 109/195 [00:49<00:21, 4.00it/s] [2024-06-06 22:00:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
56%|█████▌ | 109/195 [00:49<00:21, 4.00it/s] 57%|█████▋ | 111/195 [00:49<00:16, 5.06it/s] [2024-06-06 22:00:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
57%|█████▋ | 111/195 [00:49<00:16, 5.06it/s] [2024-06-06 22:00:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
57%|█████▋ | 111/195 [00:49<00:16, 5.06it/s] [2024-06-06 22:00:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (4096,), dtype: float16
57%|█████▋ | 111/195 [00:49<00:16, 5.06it/s] [2024-06-06 22:00:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
57%|█████▋ | 111/195 [00:49<00:16, 5.06it/s] [2024-06-06 22:00:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
57%|█████▋ | 111/195 [00:49<00:16, 5.06it/s] 58%|█████▊ | 114/195 [00:49<00:13, 6.02it/s] [2024-06-06 22:00:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
58%|█████▊ | 114/195 [00:50<00:13, 6.02it/s] [2024-06-06 22:00:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
58%|█████▊ | 114/195 [00:50<00:13, 6.02it/s] 59%|█████▉ | 115/195 [00:50<00:19, 4.06it/s] [2024-06-06 22:00:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (4096,), dtype: float16
59%|█████▉ | 115/195 [00:50<00:19, 4.06it/s] [2024-06-06 22:00:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
59%|█████▉ | 115/195 [00:50<00:19, 4.06it/s] [2024-06-06 22:00:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
59%|█████▉ | 115/195 [00:50<00:19, 4.06it/s] 60%|██████ | 117/195 [00:50<00:15, 5.07it/s] [2024-06-06 22:00:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
60%|██████ | 117/195 [00:50<00:15, 5.07it/s] [2024-06-06 22:00:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
60%|██████ | 117/195 [00:50<00:15, 5.07it/s] [2024-06-06 22:00:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (4096,), dtype: float16
60%|██████ | 117/195 [00:50<00:15, 5.07it/s] [2024-06-06 22:00:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
60%|██████ | 117/195 [00:50<00:15, 5.07it/s] [2024-06-06 22:00:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
60%|██████ | 117/195 [00:50<00:15, 5.07it/s] 62%|██████▏ | 120/195 [00:50<00:12, 6.05it/s] [2024-06-06 22:00:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
62%|██████▏ | 120/195 [00:51<00:12, 6.05it/s] [2024-06-06 22:00:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
62%|██████▏ | 120/195 [00:51<00:12, 6.05it/s] 62%|██████▏ | 121/195 [00:51<00:18, 4.07it/s] [2024-06-06 22:00:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (4096,), dtype: float16
62%|██████▏ | 121/195 [00:51<00:18, 4.07it/s] [2024-06-06 22:00:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
62%|██████▏ | 121/195 [00:51<00:18, 4.07it/s] [2024-06-06 22:00:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
62%|██████▏ | 121/195 [00:51<00:18, 4.07it/s] 63%|██████▎ | 123/195 [00:51<00:14, 5.10it/s] [2024-06-06 22:00:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
63%|██████▎ | 123/195 [00:51<00:14, 5.10it/s] [2024-06-06 22:00:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
63%|██████▎ | 123/195 [00:51<00:14, 5.10it/s] [2024-06-06 22:00:31] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Mistral-7B-Instruct-v0.3/model-00001-of-00003.safetensors
63%|██████▎ | 123/195 [00:51<00:14, 5.10it/s] [2024-06-06 22:00:32] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Mistral-7B-Instruct-v0.3/model-00002-of-00003.safetensors
63%|██████▎ | 123/195 [00:52<00:14, 5.10it/s] [2024-06-06 22:00:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (4096,), dtype: float16
63%|██████▎ | 123/195 [00:57<00:14, 5.10it/s] 64%|██████▍ | 125/195 [00:57<01:13, 1.06s/it] [2024-06-06 22:00:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
64%|██████▍ | 125/195 [00:57<01:13, 1.06s/it] [2024-06-06 22:00:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
64%|██████▍ | 125/195 [00:57<01:13, 1.06s/it] 65%|██████▍ | 126/195 [00:57<01:03, 1.08it/s] [2024-06-06 22:00:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (4096,), dtype: float16
65%|██████▍ | 126/195 [00:57<01:03, 1.08it/s] [2024-06-06 22:00:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (4096,), dtype: float16
65%|██████▍ | 126/195 [00:57<01:03, 1.08it/s] [2024-06-06 22:00:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
65%|██████▍ | 126/195 [00:58<01:03, 1.08it/s] [2024-06-06 22:00:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
65%|██████▍ | 126/195 [00:58<01:03, 1.08it/s] 66%|██████▌ | 129/195 [00:58<00:37, 1.74it/s] [2024-06-06 22:00:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
66%|██████▌ | 129/195 [00:58<00:37, 1.74it/s] [2024-06-06 22:00:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
66%|██████▌ | 129/195 [00:58<00:37, 1.74it/s] 67%|██████▋ | 130/195 [00:58<00:38, 1.69it/s] [2024-06-06 22:00:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (4096,), dtype: float16
67%|██████▋ | 130/195 [00:58<00:38, 1.69it/s] [2024-06-06 22:00:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
67%|██████▋ | 130/195 [00:59<00:38, 1.69it/s] [2024-06-06 22:00:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
67%|██████▋ | 130/195 [00:59<00:38, 1.69it/s] 68%|██████▊ | 132/195 [00:59<00:26, 2.35it/s] [2024-06-06 22:00:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
68%|██████▊ | 132/195 [00:59<00:26, 2.35it/s] [2024-06-06 22:00:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
68%|██████▊ | 132/195 [00:59<00:26, 2.35it/s] [2024-06-06 22:00:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (4096,), dtype: float16
68%|██████▊ | 132/195 [00:59<00:26, 2.35it/s] [2024-06-06 22:00:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
68%|██████▊ | 132/195 [00:59<00:26, 2.35it/s] [2024-06-06 22:00:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
68%|██████▊ | 132/195 [00:59<00:26, 2.35it/s] 69%|██████▉ | 135/195 [00:59<00:18, 3.32it/s] [2024-06-06 22:00:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
69%|██████▉ | 135/195 [01:00<00:18, 3.32it/s] [2024-06-06 22:00:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
69%|██████▉ | 135/195 [01:00<00:18, 3.32it/s] 70%|██████▉ | 136/195 [01:00<00:21, 2.77it/s] [2024-06-06 22:00:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (4096,), dtype: float16
70%|██████▉ | 136/195 [01:00<00:21, 2.77it/s] [2024-06-06 22:00:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
70%|██████▉ | 136/195 [01:00<00:21, 2.77it/s] [2024-06-06 22:00:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
70%|██████▉ | 136/195 [01:00<00:21, 2.77it/s] 71%|███████ | 138/195 [01:00<00:15, 3.68it/s] [2024-06-06 22:00:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
71%|███████ | 138/195 [01:00<00:15, 3.68it/s] [2024-06-06 22:00:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
71%|███████ | 138/195 [01:00<00:15, 3.68it/s] [2024-06-06 22:00:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (4096,), dtype: float16
71%|███████ | 138/195 [01:00<00:15, 3.68it/s] [2024-06-06 22:00:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
71%|███████ | 138/195 [01:00<00:15, 3.68it/s] [2024-06-06 22:00:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
71%|███████ | 138/195 [01:00<00:15, 3.68it/s] 72%|███████▏ | 141/195 [01:00<00:11, 4.74it/s] [2024-06-06 22:00:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
72%|███████▏ | 141/195 [01:01<00:11, 4.74it/s] [2024-06-06 22:00:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
72%|███████▏ | 141/195 [01:01<00:11, 4.74it/s] 73%|███████▎ | 142/195 [01:01<00:14, 3.56it/s] [2024-06-06 22:00:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (4096,), dtype: float16
73%|███████▎ | 142/195 [01:01<00:14, 3.56it/s] [2024-06-06 22:00:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
73%|███████▎ | 142/195 [01:01<00:14, 3.56it/s] [2024-06-06 22:00:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
73%|███████▎ | 142/195 [01:01<00:14, 3.56it/s] 74%|███████▍ | 144/195 [01:01<00:11, 4.59it/s] [2024-06-06 22:00:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
74%|███████▍ | 144/195 [01:01<00:11, 4.59it/s] [2024-06-06 22:00:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
74%|███████▍ | 144/195 [01:01<00:11, 4.59it/s] [2024-06-06 22:00:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (4096,), dtype: float16
74%|███████▍ | 144/195 [01:01<00:11, 4.59it/s] [2024-06-06 22:00:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
74%|███████▍ | 144/195 [01:01<00:11, 4.59it/s] [2024-06-06 22:00:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
74%|███████▍ | 144/195 [01:01<00:11, 4.59it/s] 75%|███████▌ | 147/195 [01:01<00:08, 5.56it/s] [2024-06-06 22:00:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
75%|███████▌ | 147/195 [01:02<00:08, 5.56it/s] [2024-06-06 22:00:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
75%|███████▌ | 147/195 [01:02<00:08, 5.56it/s] 76%|███████▌ | 148/195 [01:02<00:12, 3.89it/s] [2024-06-06 22:00:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (4096,), dtype: float16
76%|███████▌ | 148/195 [01:02<00:12, 3.89it/s] [2024-06-06 22:00:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
76%|███████▌ | 148/195 [01:02<00:12, 3.89it/s] [2024-06-06 22:00:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
76%|███████▌ | 148/195 [01:02<00:12, 3.89it/s] 77%|███████▋ | 150/195 [01:02<00:09, 4.87it/s] [2024-06-06 22:00:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
77%|███████▋ | 150/195 [01:02<00:09, 4.87it/s] [2024-06-06 22:00:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
77%|███████▋ | 150/195 [01:02<00:09, 4.87it/s] [2024-06-06 22:00:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (4096,), dtype: float16
77%|███████▋ | 150/195 [01:02<00:09, 4.87it/s] [2024-06-06 22:00:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
77%|███████▋ | 150/195 [01:03<00:09, 4.87it/s] [2024-06-06 22:00:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
77%|███████▋ | 150/195 [01:03<00:09, 4.87it/s] 78%|███████▊ | 153/195 [01:03<00:07, 5.79it/s] [2024-06-06 22:00:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
78%|███████▊ | 153/195 [01:03<00:07, 5.79it/s] [2024-06-06 22:00:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
78%|███████▊ | 153/195 [01:03<00:07, 5.79it/s] 79%|███████▉ | 154/195 [01:03<00:10, 3.97it/s] [2024-06-06 22:00:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (4096,), dtype: float16
79%|███████▉ | 154/195 [01:03<00:10, 3.97it/s] [2024-06-06 22:00:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
79%|███████▉ | 154/195 [01:03<00:10, 3.97it/s] [2024-06-06 22:00:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
79%|███████▉ | 154/195 [01:03<00:10, 3.97it/s] 80%|████████ | 156/195 [01:03<00:07, 4.99it/s] [2024-06-06 22:00:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
80%|████████ | 156/195 [01:04<00:07, 4.99it/s] [2024-06-06 22:00:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
80%|████████ | 156/195 [01:04<00:07, 4.99it/s] [2024-06-06 22:00:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (4096,), dtype: float16
80%|████████ | 156/195 [01:04<00:07, 4.99it/s] [2024-06-06 22:00:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
80%|████████ | 156/195 [01:04<00:07, 4.99it/s] [2024-06-06 22:00:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
80%|████████ | 156/195 [01:04<00:07, 4.99it/s] 82%|████████▏ | 159/195 [01:04<00:06, 5.91it/s] [2024-06-06 22:00:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
82%|████████▏ | 159/195 [01:04<00:06, 5.91it/s] [2024-06-06 22:00:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
82%|████████▏ | 159/195 [01:04<00:06, 5.91it/s] 82%|████████▏ | 160/195 [01:05<00:08, 3.94it/s] [2024-06-06 22:00:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (4096,), dtype: float16
82%|████████▏ | 160/195 [01:05<00:08, 3.94it/s] [2024-06-06 22:00:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
82%|████████▏ | 160/195 [01:05<00:08, 3.94it/s] [2024-06-06 22:00:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
82%|████████▏ | 160/195 [01:05<00:08, 3.94it/s] 83%|████████▎ | 162/195 [01:05<00:06, 4.96it/s] [2024-06-06 22:00:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
83%|████████▎ | 162/195 [01:05<00:06, 4.96it/s] [2024-06-06 22:00:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
83%|████████▎ | 162/195 [01:05<00:06, 4.96it/s] [2024-06-06 22:00:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (4096,), dtype: float16
83%|████████▎ | 162/195 [01:05<00:06, 4.96it/s] [2024-06-06 22:00:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
83%|████████▎ | 162/195 [01:05<00:06, 4.96it/s] [2024-06-06 22:00:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
83%|████████▎ | 162/195 [01:05<00:06, 4.96it/s] 85%|████████▍ | 165/195 [01:05<00:05, 5.73it/s] [2024-06-06 22:00:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
85%|████████▍ | 165/195 [01:06<00:05, 5.73it/s] [2024-06-06 22:00:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
85%|████████▍ | 165/195 [01:06<00:05, 5.73it/s] 85%|████████▌ | 166/195 [01:06<00:07, 3.97it/s] [2024-06-06 22:00:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (4096,), dtype: float16
85%|████████▌ | 166/195 [01:06<00:07, 3.97it/s] [2024-06-06 22:00:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
85%|████████▌ | 166/195 [01:06<00:07, 3.97it/s] [2024-06-06 22:00:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
85%|████████▌ | 166/195 [01:06<00:07, 3.97it/s] 86%|████████▌ | 168/195 [01:06<00:05, 5.00it/s] [2024-06-06 22:00:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
86%|████████▌ | 168/195 [01:06<00:05, 5.00it/s] [2024-06-06 22:00:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
86%|████████▌ | 168/195 [01:06<00:05, 5.00it/s] [2024-06-06 22:00:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (4096,), dtype: float16
86%|████████▌ | 168/195 [01:06<00:05, 5.00it/s] [2024-06-06 22:00:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
86%|████████▌ | 168/195 [01:06<00:05, 5.00it/s] [2024-06-06 22:00:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
86%|████████▌ | 168/195 [01:06<00:05, 5.00it/s] 88%|████████▊ | 171/195 [01:06<00:04, 5.92it/s] [2024-06-06 22:00:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
88%|████████▊ | 171/195 [01:07<00:04, 5.92it/s] [2024-06-06 22:00:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
88%|████████▊ | 171/195 [01:07<00:04, 5.92it/s] 88%|████████▊ | 172/195 [01:07<00:05, 4.06it/s] [2024-06-06 22:00:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (4096,), dtype: float16
88%|████████▊ | 172/195 [01:07<00:05, 4.06it/s] [2024-06-06 22:00:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
88%|████████▊ | 172/195 [01:07<00:05, 4.06it/s] [2024-06-06 22:00:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
88%|████████▊ | 172/195 [01:07<00:05, 4.06it/s] 89%|████████▉ | 174/195 [01:07<00:04, 5.08it/s] [2024-06-06 22:00:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
89%|████████▉ | 174/195 [01:07<00:04, 5.08it/s] [2024-06-06 22:00:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
89%|████████▉ | 174/195 [01:07<00:04, 5.08it/s] [2024-06-06 22:00:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (4096,), dtype: float16
89%|████████▉ | 174/195 [01:07<00:04, 5.08it/s] [2024-06-06 22:00:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
89%|████████▉ | 174/195 [01:07<00:04, 5.08it/s] [2024-06-06 22:00:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
89%|████████▉ | 174/195 [01:07<00:04, 5.08it/s] 91%|█████████ | 177/195 [01:07<00:03, 5.92it/s] [2024-06-06 22:00:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
91%|█████████ | 177/195 [01:08<00:03, 5.92it/s] [2024-06-06 22:00:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
91%|█████████ | 177/195 [01:08<00:03, 5.92it/s] 91%|█████████▏| 178/195 [01:08<00:04, 4.05it/s] [2024-06-06 22:00:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (4096,), dtype: float16
91%|█████████▏| 178/195 [01:08<00:04, 4.05it/s] [2024-06-06 22:00:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
91%|█████████▏| 178/195 [01:08<00:04, 4.05it/s] [2024-06-06 22:00:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
91%|█████████▏| 178/195 [01:08<00:04, 4.05it/s] 92%|█████████▏| 180/195 [01:08<00:02, 5.08it/s] [2024-06-06 22:00:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
92%|█████████▏| 180/195 [01:08<00:02, 5.08it/s] [2024-06-06 22:00:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
92%|█████████▏| 180/195 [01:08<00:02, 5.08it/s] [2024-06-06 22:00:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (4096,), dtype: float16
92%|█████████▏| 180/195 [01:08<00:02, 5.08it/s] [2024-06-06 22:00:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
92%|█████████▏| 180/195 [01:09<00:02, 5.08it/s] [2024-06-06 22:00:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
92%|█████████▏| 180/195 [01:09<00:02, 5.08it/s] 94%|█████████▍| 183/195 [01:09<00:02, 5.96it/s] [2024-06-06 22:00:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
94%|█████████▍| 183/195 [01:09<00:02, 5.96it/s] [2024-06-06 22:00:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
94%|█████████▍| 183/195 [01:09<00:02, 5.96it/s] 94%|█████████▍| 184/195 [01:09<00:02, 4.03it/s] [2024-06-06 22:00:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (4096,), dtype: float16
94%|█████████▍| 184/195 [01:09<00:02, 4.03it/s] [2024-06-06 22:00:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
94%|█████████▍| 184/195 [01:09<00:02, 4.03it/s] [2024-06-06 22:00:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
94%|█████████▍| 184/195 [01:10<00:02, 4.03it/s] 95%|█████████▌| 186/195 [01:10<00:01, 5.08it/s] [2024-06-06 22:00:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
95%|█████████▌| 186/195 [01:10<00:01, 5.08it/s] [2024-06-06 22:00:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
95%|█████████▌| 186/195 [01:10<00:01, 5.08it/s] [2024-06-06 22:00:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (4096,), dtype: float16
95%|█████████▌| 186/195 [01:10<00:01, 5.08it/s] [2024-06-06 22:00:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
95%|█████████▌| 186/195 [01:10<00:01, 5.08it/s] [2024-06-06 22:00:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
95%|█████████▌| 186/195 [01:10<00:01, 5.08it/s] 97%|█████████▋| 189/195 [01:10<00:01, 6.00it/s] [2024-06-06 22:00:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
97%|█████████▋| 189/195 [01:10<00:01, 6.00it/s] [2024-06-06 22:00:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
97%|█████████▋| 189/195 [01:11<00:01, 6.00it/s] 97%|█████████▋| 190/195 [01:11<00:01, 4.10it/s] [2024-06-06 22:00:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (4096,), dtype: float16
97%|█████████▋| 190/195 [01:11<00:01, 4.10it/s] [2024-06-06 22:00:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
97%|█████████▋| 190/195 [01:11<00:01, 4.10it/s] [2024-06-06 22:00:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
97%|█████████▋| 190/195 [01:11<00:01, 4.10it/s] 98%|█████████▊| 192/195 [01:11<00:00, 5.18it/s] [2024-06-06 22:00:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
98%|█████████▊| 192/195 [01:11<00:00, 5.18it/s] [2024-06-06 22:00:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
98%|█████████▊| 192/195 [01:11<00:00, 5.18it/s] [2024-06-06 22:00:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
98%|█████████▊| 192/195 [01:11<00:00, 5.18it/s] [2024-06-06 22:00:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
98%|█████████▊| 192/195 [01:11<00:00, 5.18it/s] 99%|█████████▉| 194/195 [01:11<00:00, 6.20it/s] [2024-06-06 22:00:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
99%|█████████▉| 194/195 [01:11<00:00, 6.20it/s] [2024-06-06 22:00:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
99%|█████████▉| 194/195 [01:11<00:00, 6.20it/s] 100%|██████████| 195/195 [01:11<00:00, 6.45it/s] 100%|██████████| 195/195 [01:11<00:00, 2.73it/s]
[2024-06-06 22:00:51] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Mistral-7B-Instruct-v0.3/model-00002-of-00003.safetensors
[2024-06-06 22:00:52] INFO stats.py:77: Time usage: HF loading: 21.882 sec; Pre-quantization mapping: 36.046 sec; Quantization: 3.279 sec
[2024-06-06 22:00:52] INFO stats.py:91: RAM usage: Peak RAM: 9.313 GB. Total bytes loaded from disk: 27.001 GB
[2024-06-06 22:00:52] INFO convert_weight.py:155: Parameter size after quantization: 3.052 GB
[2024-06-06 22:00:52] INFO convert_weight.py:160: Total parameters: 7,248,023,552
[2024-06-06 22:00:52] INFO convert_weight.py:161: Bits per parameter: 3.618
[2024-06-06 22:00:52] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q3f16_1-MLC
All finished, 98 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Mistral-7B-Instruct-v0.3-q3f16_1-MLC/ndarray-cache.json