Hugging Face's logo

mlc-ai
/
Qwen2-7B-Instruct-q4f16_1-MLC

MLC-LLM
web-llm
Model card Files
xet
Community
1
Qwen2-7B-Instruct-q4f16_1-MLC / logs.txt
riczhou's picture
riczhou
Initial commit
68ca2f2 verified
raw
history blame contribute delete
101 kB
 /opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Qwen2-7B-Instruct --quantization q4f16_1 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen2-7B-Instruct-q4f16_1-MLC
[2024-06-06 23:42:10] INFO auto_config.py:116: Found model configuration: /models/Qwen2-7B-Instruct/config.json
[2024-06-06 23:42:10] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
[2024-06-06 23:42:10] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-06 23:42:10] INFO qwen2_model.py:66: prefill_chunk_size defaults to 2048
[2024-06-06 23:42:10] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-06 23:42:10] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 151643
[2024-06-06 23:42:10] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 151643
[2024-06-06 23:42:10] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [151645, 151643]
[2024-06-06 23:42:10] INFO gen_config.py:143: [generation_config.json] Setting repetition_penalty: 1.05
[2024-06-06 23:42:10] INFO gen_config.py:143: [generation_config.json] Setting temperature: 0.7
[2024-06-06 23:42:10] INFO gen_config.py:143: [generation_config.json] Setting top_p: 0.8
[2024-06-06 23:42:10] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen2-7B-Instruct/tokenizer.model
[2024-06-06 23:42:10] INFO gen_config.py:155: Found tokenizer config: /models/Qwen2-7B-Instruct/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen2-7B-Instruct-q4f16_1-MLC/tokenizer.json
[2024-06-06 23:42:10] INFO gen_config.py:155: Found tokenizer config: /models/Qwen2-7B-Instruct/vocab.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen2-7B-Instruct-q4f16_1-MLC/vocab.json
[2024-06-06 23:42:10] INFO gen_config.py:155: Found tokenizer config: /models/Qwen2-7B-Instruct/merges.txt. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen2-7B-Instruct-q4f16_1-MLC/merges.txt
[2024-06-06 23:42:10] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen2-7B-Instruct/added_tokens.json
[2024-06-06 23:42:10] INFO gen_config.py:155: Found tokenizer config: /models/Qwen2-7B-Instruct/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen2-7B-Instruct-q4f16_1-MLC/tokenizer_config.json
[2024-06-06 23:42:10] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_level', 'prepend_space_in_encode': False, 'strip_space_in_decode': False}
[2024-06-06 23:42:10] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-06 23:42:10] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-06 23:42:10] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Qwen2-7B-Instruct-q4f16_1-MLC/mlc-chat-config.json
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Qwen2-7B-Instruct --quantization q4f16_1 --output /models/mlc-delivery/hf/mlc-ai/Qwen2-7B-Instruct-q4f16_1-MLC
[2024-06-06 23:42:12] INFO auto_config.py:116: Found model configuration: /models/Qwen2-7B-Instruct/config.json
[2024-06-06 23:42:14] INFO auto_device.py:79: Found device: cuda:0
[2024-06-06 23:42:15] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-06 23:42:16] INFO auto_device.py:88: Not found device: metal:0
[2024-06-06 23:42:18] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-06 23:42:18] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-06 23:42:18] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-06 23:42:18] INFO auto_device.py:79: Found device: vulkan:3
[2024-06-06 23:42:20] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-06 23:42:20] INFO auto_device.py:35: Using device: cuda:0
[2024-06-06 23:42:20] INFO auto_weight.py:71: Finding weights in: /models/Qwen2-7B-Instruct
[2024-06-06 23:42:20] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-06 23:42:20] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /models/Qwen2-7B-Instruct/model.safetensors.index.json
[2024-06-06 23:42:20] INFO auto_weight.py:107: Using source weight configuration: /models/Qwen2-7B-Instruct/model.safetensors.index.json. Use `--source` to override.
[2024-06-06 23:42:20] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-06 23:42:20] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
[2024-06-06 23:42:20] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-06 23:42:20] INFO qwen2_model.py:66: prefill_chunk_size defaults to 2048
Weight conversion with arguments:
--config /models/Qwen2-7B-Instruct/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 qwen2
--device cuda:0
--source /models/Qwen2-7B-Instruct/model.safetensors.index.json
--source-format huggingface-safetensor
--output /models/mlc-delivery/hf/mlc-ai/Qwen2-7B-Instruct-q4f16_1-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen2-7B-Instruct-q4f16_1-MLC
0%| | 0/199 [00:00<?, ?it/s] [2024-06-06 23:42:22] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Qwen2-7B-Instruct/model-00004-of-00004.safetensors
0%| | 0/199 [00:00<?, ?it/s] [2024-06-06 23:42:30] INFO group_quantization.py:217: Compiling quantize function for key: ((152064, 3584), float16, cuda, axis=1, output_transpose=False)
0%| | 0/199 [00:07<?, ?it/s] [2024-06-06 23:42:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_weight", shape: (152064, 448), dtype: uint32
0%| | 0/199 [00:08<?, ?it/s] [2024-06-06 23:42:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_scale", shape: (152064, 112), dtype: float16
0%| | 0/199 [00:09<?, ?it/s] 1%| | 1/199 [00:09<32:17, 9.78s/it] [2024-06-06 23:42:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (3584,), dtype: float16
1%| | 1/199 [00:09<32:17, 9.78s/it] [2024-06-06 23:42:32] INFO group_quantization.py:217: Compiling quantize function for key: ((3584, 18944), float16, cuda, axis=1, output_transpose=False)
1%| | 1/199 [00:10<32:17, 9.78s/it] [2024-06-06 23:42:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
1%| | 1/199 [00:10<32:17, 9.78s/it] [2024-06-06 23:42:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
1%| | 1/199 [00:10<32:17, 9.78s/it] 2%|▏ | 3/199 [00:10<09:21, 2.87s/it] [2024-06-06 23:42:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (3584,), dtype: float16
2%|▏ | 3/199 [00:10<09:21, 2.87s/it] [2024-06-06 23:42:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (3584,), dtype: float16
2%|▏ | 3/199 [00:10<09:21, 2.87s/it] [2024-06-06 23:42:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
2%|▏ | 3/199 [00:10<09:21, 2.87s/it] [2024-06-06 23:42:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
2%|▏ | 3/199 [00:11<09:21, 2.87s/it] 3%|▎ | 6/199 [00:11<03:48, 1.19s/it] [2024-06-06 23:42:34] INFO group_quantization.py:217: Compiling quantize function for key: ((37888, 3584), float16, cuda, axis=1, output_transpose=False)
3%|▎ | 6/199 [00:11<03:48, 1.19s/it] [2024-06-06 23:42:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
3%|▎ | 6/199 [00:12<03:48, 1.19s/it] [2024-06-06 23:42:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
3%|▎ | 6/199 [00:12<03:48, 1.19s/it] 4%|▎ | 7/199 [00:12<04:02, 1.26s/it] [2024-06-06 23:42:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (3584,), dtype: float16
4%|▎ | 7/199 [00:12<04:02, 1.26s/it] [2024-06-06 23:42:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.c_attn.bias", shape: (4608,), dtype: float16
4%|▎ | 7/199 [00:12<04:02, 1.26s/it] [2024-06-06 23:42:34] INFO group_quantization.py:217: Compiling quantize function for key: ((4608, 3584), float16, cuda, axis=1, output_transpose=False)
4%|▎ | 7/199 [00:12<04:02, 1.26s/it] [2024-06-06 23:42:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
4%|▎ | 7/199 [00:13<04:02, 1.26s/it] [2024-06-06 23:42:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
4%|▎ | 7/199 [00:13<04:02, 1.26s/it] 5%|▌ | 10/199 [00:13<02:18, 1.36it/s] [2024-06-06 23:42:35] INFO group_quantization.py:217: Compiling quantize function for key: ((3584, 3584), float16, cuda, axis=1, output_transpose=False)
5%|▌ | 10/199 [00:13<02:18, 1.36it/s] [2024-06-06 23:42:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
5%|▌ | 10/199 [00:13<02:18, 1.36it/s] [2024-06-06 23:42:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
5%|▌ | 10/199 [00:13<02:18, 1.36it/s] 6%|▌ | 11/199 [00:13<02:10, 1.44it/s] [2024-06-06 23:42:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (3584,), dtype: float16
6%|▌ | 11/199 [00:13<02:10, 1.44it/s] [2024-06-06 23:42:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
6%|▌ | 11/199 [00:13<02:10, 1.44it/s] [2024-06-06 23:42:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
6%|▌ | 11/199 [00:13<02:10, 1.44it/s] 7%|▋ | 13/199 [00:14<01:36, 1.93it/s] [2024-06-06 23:42:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
7%|▋ | 13/199 [00:15<01:36, 1.93it/s] [2024-06-06 23:42:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
7%|▋ | 13/199 [00:15<01:36, 1.93it/s] 7%|▋ | 14/199 [00:15<02:05, 1.48it/s] [2024-06-06 23:42:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (3584,), dtype: float16
7%|▋ | 14/199 [00:15<02:05, 1.48it/s] [2024-06-06 23:42:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.self_attn.c_attn.bias", shape: (4608,), dtype: float16
7%|▋ | 14/199 [00:15<02:05, 1.48it/s] [2024-06-06 23:42:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
7%|▋ | 14/199 [00:15<02:05, 1.48it/s] [2024-06-06 23:42:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
7%|▋ | 14/199 [00:15<02:05, 1.48it/s] [2024-06-06 23:42:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
7%|▋ | 14/199 [00:15<02:05, 1.48it/s] [2024-06-06 23:42:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
7%|▋ | 14/199 [00:15<02:05, 1.48it/s] 9%|▉ | 18/199 [00:15<01:00, 3.00it/s] [2024-06-06 23:42:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (3584,), dtype: float16
9%|▉ | 18/199 [00:15<01:00, 3.00it/s] [2024-06-06 23:42:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
9%|▉ | 18/199 [00:15<01:00, 3.00it/s] [2024-06-06 23:42:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
9%|▉ | 18/199 [00:15<01:00, 3.00it/s] 10%|█ | 20/199 [00:15<00:52, 3.43it/s] [2024-06-06 23:42:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
10%|█ | 20/199 [00:16<00:52, 3.43it/s] [2024-06-06 23:42:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
10%|█ | 20/199 [00:17<00:52, 3.43it/s] 11%|█ | 21/199 [00:17<01:22, 2.16it/s] [2024-06-06 23:42:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (3584,), dtype: float16
11%|█ | 21/199 [00:17<01:22, 2.16it/s] [2024-06-06 23:42:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.self_attn.c_attn.bias", shape: (4608,), dtype: float16
11%|█ | 21/199 [00:17<01:22, 2.16it/s] [2024-06-06 23:42:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
11%|█ | 21/199 [00:17<01:22, 2.16it/s] [2024-06-06 23:42:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
11%|█ | 21/199 [00:17<01:22, 2.16it/s] [2024-06-06 23:42:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
11%|█ | 21/199 [00:17<01:22, 2.16it/s] [2024-06-06 23:42:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
11%|█ | 21/199 [00:17<01:22, 2.16it/s] 13%|█▎ | 25/199 [00:17<00:44, 3.93it/s] [2024-06-06 23:42:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (3584,), dtype: float16
13%|█▎ | 25/199 [00:17<00:44, 3.93it/s] [2024-06-06 23:42:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
13%|█▎ | 25/199 [00:17<00:44, 3.93it/s] [2024-06-06 23:42:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
13%|█▎ | 25/199 [00:17<00:44, 3.93it/s] 14%|█▎ | 27/199 [00:17<00:40, 4.27it/s] [2024-06-06 23:42:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
14%|█▎ | 27/199 [00:18<00:40, 4.27it/s] [2024-06-06 23:42:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
14%|█▎ | 27/199 [00:18<00:40, 4.27it/s] [2024-06-06 23:42:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (3584,), dtype: float16
14%|█▎ | 27/199 [00:18<00:40, 4.27it/s] 15%|█▍ | 29/199 [00:18<00:57, 2.96it/s] [2024-06-06 23:42:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.self_attn.c_attn.bias", shape: (4608,), dtype: float16
15%|█▍ | 29/199 [00:18<00:57, 2.96it/s] [2024-06-06 23:42:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
15%|█▍ | 29/199 [00:18<00:57, 2.96it/s] [2024-06-06 23:42:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
15%|█▍ | 29/199 [00:18<00:57, 2.96it/s] [2024-06-06 23:42:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
15%|█▍ | 29/199 [00:19<00:57, 2.96it/s] [2024-06-06 23:42:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
15%|█▍ | 29/199 [00:19<00:57, 2.96it/s] 16%|█▌ | 32/199 [00:19<00:38, 4.37it/s] [2024-06-06 23:42:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (3584,), dtype: float16
16%|█▌ | 32/199 [00:19<00:38, 4.37it/s] [2024-06-06 23:42:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
16%|█▌ | 32/199 [00:19<00:38, 4.37it/s] [2024-06-06 23:42:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
16%|█▌ | 32/199 [00:19<00:38, 4.37it/s] 17%|█▋ | 34/199 [00:19<00:35, 4.67it/s] [2024-06-06 23:42:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
17%|█▋ | 34/199 [00:20<00:35, 4.67it/s] [2024-06-06 23:42:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
17%|█▋ | 34/199 [00:20<00:35, 4.67it/s] [2024-06-06 23:42:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (3584,), dtype: float16
17%|█▋ | 34/199 [00:20<00:35, 4.67it/s] 18%|█▊ | 36/199 [00:20<00:50, 3.25it/s] [2024-06-06 23:42:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.self_attn.c_attn.bias", shape: (4608,), dtype: float16
18%|█▊ | 36/199 [00:20<00:50, 3.25it/s] [2024-06-06 23:42:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
18%|█▊ | 36/199 [00:20<00:50, 3.25it/s] [2024-06-06 23:42:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
18%|█▊ | 36/199 [00:20<00:50, 3.25it/s] [2024-06-06 23:42:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
18%|█▊ | 36/199 [00:20<00:50, 3.25it/s] [2024-06-06 23:42:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
18%|█▊ | 36/199 [00:20<00:50, 3.25it/s] 20%|█▉ | 39/199 [00:20<00:33, 4.76it/s] [2024-06-06 23:42:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (3584,), dtype: float16
20%|█▉ | 39/199 [00:20<00:33, 4.76it/s] [2024-06-06 23:42:42] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Qwen2-7B-Instruct/model-00004-of-00004.safetensors
20%|█▉ | 39/199 [00:20<00:33, 4.76it/s] [2024-06-06 23:42:43] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Qwen2-7B-Instruct/model-00001-of-00004.safetensors
20%|█▉ | 39/199 [00:21<00:33, 4.76it/s] [2024-06-06 23:42:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (152064, 448), dtype: uint32
20%|█▉ | 39/199 [00:28<00:33, 4.76it/s] [2024-06-06 23:42:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (152064, 112), dtype: float16
20%|█▉ | 39/199 [00:29<00:33, 4.76it/s] 21%|██ | 41/199 [00:29<03:25, 1.30s/it] [2024-06-06 23:42:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (3584,), dtype: float16
21%|██ | 41/199 [00:29<03:25, 1.30s/it] [2024-06-06 23:42:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
21%|██ | 41/199 [00:29<03:25, 1.30s/it] [2024-06-06 23:42:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
21%|██ | 41/199 [00:29<03:25, 1.30s/it] 22%|██▏ | 43/199 [00:29<02:38, 1.02s/it] [2024-06-06 23:42:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
22%|██▏ | 43/199 [00:31<02:38, 1.02s/it] [2024-06-06 23:42:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
22%|██▏ | 43/199 [00:31<02:38, 1.02s/it] 22%|██▏ | 44/199 [00:31<02:55, 1.13s/it] [2024-06-06 23:42:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (3584,), dtype: float16
22%|██▏ | 44/199 [00:31<02:55, 1.13s/it] [2024-06-06 23:42:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.c_attn.bias", shape: (4608,), dtype: float16
22%|██▏ | 44/199 [00:31<02:55, 1.13s/it] [2024-06-06 23:42:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
22%|██▏ | 44/199 [00:31<02:55, 1.13s/it] [2024-06-06 23:42:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
22%|██▏ | 44/199 [00:31<02:55, 1.13s/it] [2024-06-06 23:42:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
22%|██▏ | 44/199 [00:31<02:55, 1.13s/it] [2024-06-06 23:42:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
22%|██▏ | 44/199 [00:31<02:55, 1.13s/it] 24%|██▍ | 48/199 [00:31<01:30, 1.66it/s] [2024-06-06 23:42:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (3584,), dtype: float16
24%|██▍ | 48/199 [00:31<01:30, 1.66it/s] [2024-06-06 23:42:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
24%|██▍ | 48/199 [00:32<01:30, 1.66it/s] [2024-06-06 23:42:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
24%|██▍ | 48/199 [00:32<01:30, 1.66it/s] 25%|██▌ | 50/199 [00:32<01:14, 2.00it/s] [2024-06-06 23:42:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
25%|██▌ | 50/199 [00:33<01:14, 2.00it/s] [2024-06-06 23:42:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
25%|██▌ | 50/199 [00:34<01:14, 2.00it/s] [2024-06-06 23:42:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (3584,), dtype: float16
25%|██▌ | 50/199 [00:34<01:14, 2.00it/s] 26%|██▌ | 52/199 [00:34<01:30, 1.62it/s] [2024-06-06 23:42:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.c_attn.bias", shape: (4608,), dtype: float16
26%|██▌ | 52/199 [00:34<01:30, 1.62it/s] [2024-06-06 23:42:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
26%|██▌ | 52/199 [00:34<01:30, 1.62it/s] [2024-06-06 23:42:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
26%|██▌ | 52/199 [00:34<01:30, 1.62it/s] [2024-06-06 23:42:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
26%|██▌ | 52/199 [00:34<01:30, 1.62it/s] [2024-06-06 23:42:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
26%|██▌ | 52/199 [00:34<01:30, 1.62it/s] 28%|██▊ | 55/199 [00:34<00:58, 2.44it/s] [2024-06-06 23:42:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (3584,), dtype: float16
28%|██▊ | 55/199 [00:34<00:58, 2.44it/s] [2024-06-06 23:42:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
28%|██▊ | 55/199 [00:34<00:58, 2.44it/s] [2024-06-06 23:42:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
28%|██▊ | 55/199 [00:34<00:58, 2.44it/s] 29%|██▊ | 57/199 [00:34<00:50, 2.80it/s] [2024-06-06 23:42:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
29%|██▊ | 57/199 [00:36<00:50, 2.80it/s] [2024-06-06 23:42:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
29%|██▊ | 57/199 [00:36<00:50, 2.80it/s] 29%|██▉ | 58/199 [00:36<01:22, 1.71it/s] [2024-06-06 23:42:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (3584,), dtype: float16
29%|██▉ | 58/199 [00:36<01:22, 1.71it/s] [2024-06-06 23:42:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.c_attn.bias", shape: (4608,), dtype: float16
29%|██▉ | 58/199 [00:36<01:22, 1.71it/s] [2024-06-06 23:42:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
29%|██▉ | 58/199 [00:36<01:22, 1.71it/s] [2024-06-06 23:42:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
29%|██▉ | 58/199 [00:36<01:22, 1.71it/s] [2024-06-06 23:42:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
29%|██▉ | 58/199 [00:36<01:22, 1.71it/s] [2024-06-06 23:42:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
29%|██▉ | 58/199 [00:36<01:22, 1.71it/s] 31%|███ | 62/199 [00:36<00:44, 3.08it/s] [2024-06-06 23:42:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (3584,), dtype: float16
31%|███ | 62/199 [00:36<00:44, 3.08it/s] [2024-06-06 23:42:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
31%|███ | 62/199 [00:36<00:44, 3.08it/s] [2024-06-06 23:42:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
31%|███ | 62/199 [00:36<00:44, 3.08it/s] 32%|███▏ | 64/199 [00:36<00:39, 3.42it/s] [2024-06-06 23:43:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
32%|███▏ | 64/199 [00:38<00:39, 3.42it/s] [2024-06-06 23:43:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
32%|███▏ | 64/199 [00:38<00:39, 3.42it/s] [2024-06-06 23:43:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (3584,), dtype: float16
32%|███▏ | 64/199 [00:38<00:39, 3.42it/s] 33%|███▎ | 66/199 [00:38<01:00, 2.18it/s] [2024-06-06 23:43:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.c_attn.bias", shape: (4608,), dtype: float16
33%|███▎ | 66/199 [00:38<01:00, 2.18it/s] [2024-06-06 23:43:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
33%|███▎ | 66/199 [00:38<01:00, 2.18it/s] [2024-06-06 23:43:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
33%|███▎ | 66/199 [00:38<01:00, 2.18it/s] [2024-06-06 23:43:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
33%|███▎ | 66/199 [00:38<01:00, 2.18it/s] [2024-06-06 23:43:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
33%|███▎ | 66/199 [00:38<01:00, 2.18it/s] 35%|███▍ | 69/199 [00:38<00:40, 3.25it/s] [2024-06-06 23:43:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (3584,), dtype: float16
35%|███▍ | 69/199 [00:38<00:40, 3.25it/s] [2024-06-06 23:43:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
35%|███▍ | 69/199 [00:39<00:40, 3.25it/s] [2024-06-06 23:43:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
35%|███▍ | 69/199 [00:39<00:40, 3.25it/s] 36%|███▌ | 71/199 [00:39<00:35, 3.58it/s] [2024-06-06 23:43:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
36%|███▌ | 71/199 [00:40<00:35, 3.58it/s] [2024-06-06 23:43:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
36%|███▌ | 71/199 [00:40<00:35, 3.58it/s] [2024-06-06 23:43:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (3584,), dtype: float16
36%|███▌ | 71/199 [00:40<00:35, 3.58it/s] 37%|███▋ | 73/199 [00:40<00:51, 2.43it/s] [2024-06-06 23:43:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.c_attn.bias", shape: (4608,), dtype: float16
37%|███▋ | 73/199 [00:40<00:51, 2.43it/s] [2024-06-06 23:43:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
37%|███▋ | 73/199 [00:40<00:51, 2.43it/s] [2024-06-06 23:43:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
37%|███▋ | 73/199 [00:40<00:51, 2.43it/s] [2024-06-06 23:43:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
37%|███▋ | 73/199 [00:41<00:51, 2.43it/s] [2024-06-06 23:43:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
37%|███▋ | 73/199 [00:41<00:51, 2.43it/s] 38%|███▊ | 76/199 [00:41<00:33, 3.62it/s] [2024-06-06 23:43:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (3584,), dtype: float16
38%|███▊ | 76/199 [00:41<00:33, 3.62it/s] [2024-06-06 23:43:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
38%|███▊ | 76/199 [00:41<00:33, 3.62it/s] [2024-06-06 23:43:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
38%|███▊ | 76/199 [00:41<00:33, 3.62it/s] 39%|███▉ | 78/199 [00:41<00:30, 4.00it/s] [2024-06-06 23:43:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
39%|███▉ | 78/199 [00:42<00:30, 4.00it/s] [2024-06-06 23:43:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
39%|███▉ | 78/199 [00:42<00:30, 4.00it/s] [2024-06-06 23:43:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (3584,), dtype: float16
39%|███▉ | 78/199 [00:43<00:30, 4.00it/s] 40%|████ | 80/199 [00:43<00:48, 2.47it/s] [2024-06-06 23:43:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.c_attn.bias", shape: (4608,), dtype: float16
40%|████ | 80/199 [00:43<00:48, 2.47it/s] [2024-06-06 23:43:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
40%|████ | 80/199 [00:43<00:48, 2.47it/s] [2024-06-06 23:43:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
40%|████ | 80/199 [00:43<00:48, 2.47it/s] [2024-06-06 23:43:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
40%|████ | 80/199 [00:43<00:48, 2.47it/s] [2024-06-06 23:43:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
40%|████ | 80/199 [00:43<00:48, 2.47it/s] 42%|████▏ | 83/199 [00:43<00:31, 3.67it/s] [2024-06-06 23:43:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.c_attn.bias", shape: (4608,), dtype: float16
42%|████▏ | 83/199 [00:43<00:31, 3.67it/s] [2024-06-06 23:43:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
42%|████▏ | 83/199 [00:43<00:31, 3.67it/s] [2024-06-06 23:43:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
42%|████▏ | 83/199 [00:43<00:31, 3.67it/s] 43%|████▎ | 85/199 [00:43<00:25, 4.51it/s] [2024-06-06 23:43:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
43%|████▎ | 85/199 [00:43<00:25, 4.51it/s] [2024-06-06 23:43:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
43%|████▎ | 85/199 [00:43<00:25, 4.51it/s] [2024-06-06 23:43:05] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Qwen2-7B-Instruct/model-00001-of-00004.safetensors
43%|████▎ | 85/199 [00:43<00:25, 4.51it/s] [2024-06-06 23:43:06] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Qwen2-7B-Instruct/model-00002-of-00004.safetensors
43%|████▎ | 85/199 [00:43<00:25, 4.51it/s] [2024-06-06 23:43:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (3584,), dtype: float16
43%|████▎ | 85/199 [00:48<00:25, 4.51it/s] 44%|████▎ | 87/199 [00:48<01:34, 1.19it/s] [2024-06-06 23:43:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
44%|████▎ | 87/199 [00:48<01:34, 1.19it/s] [2024-06-06 23:43:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
44%|████▎ | 87/199 [00:48<01:34, 1.19it/s] 44%|████▍ | 88/199 [00:48<01:24, 1.31it/s] [2024-06-06 23:43:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
44%|████▍ | 88/199 [00:49<01:24, 1.31it/s] [2024-06-06 23:43:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
44%|████▍ | 88/199 [00:50<01:24, 1.31it/s] 45%|████▍ | 89/199 [00:50<01:38, 1.11it/s] [2024-06-06 23:43:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (3584,), dtype: float16
45%|████▍ | 89/199 [00:50<01:38, 1.11it/s] [2024-06-06 23:43:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.c_attn.bias", shape: (4608,), dtype: float16
45%|████▍ | 89/199 [00:50<01:38, 1.11it/s] [2024-06-06 23:43:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
45%|████▍ | 89/199 [00:50<01:38, 1.11it/s] [2024-06-06 23:43:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
45%|████▍ | 89/199 [00:50<01:38, 1.11it/s] [2024-06-06 23:43:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
45%|████▍ | 89/199 [00:50<01:38, 1.11it/s] [2024-06-06 23:43:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
45%|████▍ | 89/199 [00:50<01:38, 1.11it/s] 47%|████▋ | 93/199 [00:50<00:48, 2.18it/s] [2024-06-06 23:43:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (3584,), dtype: float16
47%|████▋ | 93/199 [00:50<00:48, 2.18it/s] [2024-06-06 23:43:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
47%|████▋ | 93/199 [00:50<00:48, 2.18it/s] [2024-06-06 23:43:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
47%|████▋ | 93/199 [00:50<00:48, 2.18it/s] 48%|████▊ | 95/199 [00:50<00:39, 2.62it/s] [2024-06-06 23:43:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
48%|████▊ | 95/199 [00:51<00:39, 2.62it/s] [2024-06-06 23:43:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
48%|████▊ | 95/199 [00:51<00:39, 2.62it/s] 48%|████▊ | 96/199 [00:51<00:51, 1.99it/s] [2024-06-06 23:43:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (3584,), dtype: float16
48%|████▊ | 96/199 [00:51<00:51, 1.99it/s] [2024-06-06 23:43:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.c_attn.bias", shape: (4608,), dtype: float16
48%|████▊ | 96/199 [00:51<00:51, 1.99it/s] [2024-06-06 23:43:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
48%|████▊ | 96/199 [00:51<00:51, 1.99it/s] [2024-06-06 23:43:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
48%|████▊ | 96/199 [00:51<00:51, 1.99it/s] [2024-06-06 23:43:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
48%|████▊ | 96/199 [00:51<00:51, 1.99it/s] [2024-06-06 23:43:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
48%|████▊ | 96/199 [00:52<00:51, 1.99it/s] 50%|█████ | 100/199 [00:52<00:28, 3.50it/s] [2024-06-06 23:43:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (3584,), dtype: float16
50%|█████ | 100/199 [00:52<00:28, 3.50it/s] [2024-06-06 23:43:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
50%|█████ | 100/199 [00:52<00:28, 3.50it/s] [2024-06-06 23:43:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
50%|█████ | 100/199 [00:52<00:28, 3.50it/s] 51%|█████▏ | 102/199 [00:52<00:24, 3.89it/s] [2024-06-06 23:43:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
51%|█████▏ | 102/199 [00:53<00:24, 3.89it/s] [2024-06-06 23:43:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
51%|█████▏ | 102/199 [00:53<00:24, 3.89it/s] 52%|█████▏ | 103/199 [00:53<00:34, 2.79it/s] [2024-06-06 23:43:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (3584,), dtype: float16
52%|█████▏ | 103/199 [00:53<00:34, 2.79it/s] [2024-06-06 23:43:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.c_attn.bias", shape: (4608,), dtype: float16
52%|█████▏ | 103/199 [00:53<00:34, 2.79it/s] [2024-06-06 23:43:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
52%|█████▏ | 103/199 [00:53<00:34, 2.79it/s] [2024-06-06 23:43:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
52%|█████▏ | 103/199 [00:53<00:34, 2.79it/s] [2024-06-06 23:43:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
52%|█████▏ | 103/199 [00:53<00:34, 2.79it/s] [2024-06-06 23:43:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
52%|█████▏ | 103/199 [00:53<00:34, 2.79it/s] 54%|█████▍ | 107/199 [00:53<00:19, 4.71it/s] [2024-06-06 23:43:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (3584,), dtype: float16
54%|█████▍ | 107/199 [00:53<00:19, 4.71it/s] [2024-06-06 23:43:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
54%|█████▍ | 107/199 [00:53<00:19, 4.71it/s] [2024-06-06 23:43:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
54%|█████▍ | 107/199 [00:53<00:19, 4.71it/s] 55%|█████▍ | 109/199 [00:53<00:18, 4.94it/s] [2024-06-06 23:43:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
55%|█████▍ | 109/199 [00:54<00:18, 4.94it/s] [2024-06-06 23:43:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
55%|█████▍ | 109/199 [00:54<00:18, 4.94it/s] 55%|█████▌ | 110/199 [00:54<00:29, 3.00it/s] [2024-06-06 23:43:17] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (3584,), dtype: float16
55%|█████▌ | 110/199 [00:54<00:29, 3.00it/s] [2024-06-06 23:43:17] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.c_attn.bias", shape: (4608,), dtype: float16
55%|█████▌ | 110/199 [00:54<00:29, 3.00it/s] [2024-06-06 23:43:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
55%|█████▌ | 110/199 [00:54<00:29, 3.00it/s] [2024-06-06 23:43:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
55%|█████▌ | 110/199 [00:54<00:29, 3.00it/s] [2024-06-06 23:43:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
55%|█████▌ | 110/199 [00:55<00:29, 3.00it/s] [2024-06-06 23:43:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
55%|█████▌ | 110/199 [00:55<00:29, 3.00it/s] 57%|█████▋ | 114/199 [00:55<00:17, 4.96it/s] [2024-06-06 23:43:17] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Qwen2-7B-Instruct/model-00003-of-00004.safetensors
57%|█████▋ | 114/199 [00:55<00:17, 4.96it/s] [2024-06-06 23:43:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
57%|█████▋ | 114/199 [01:00<00:17, 4.96it/s] [2024-06-06 23:43:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
57%|█████▋ | 114/199 [01:00<00:17, 4.96it/s] [2024-06-06 23:43:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.c_attn.bias", shape: (4608,), dtype: float16
57%|█████▋ | 114/199 [01:00<00:17, 4.96it/s] 58%|█████▊ | 116/199 [01:00<01:09, 1.20it/s] [2024-06-06 23:43:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
58%|█████▊ | 116/199 [01:00<01:09, 1.20it/s] [2024-06-06 23:43:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
58%|█████▊ | 116/199 [01:00<01:09, 1.20it/s] [2024-06-06 23:43:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
58%|█████▊ | 116/199 [01:00<01:09, 1.20it/s] [2024-06-06 23:43:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
58%|█████▊ | 116/199 [01:00<01:09, 1.20it/s] 59%|█████▉ | 118/199 [01:00<00:51, 1.59it/s] [2024-06-06 23:43:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (3584,), dtype: float16
59%|█████▉ | 118/199 [01:00<00:51, 1.59it/s] [2024-06-06 23:43:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
59%|█████▉ | 118/199 [01:00<00:51, 1.59it/s] [2024-06-06 23:43:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
59%|█████▉ | 118/199 [01:01<00:51, 1.59it/s] 60%|██████ | 120/199 [01:01<00:40, 1.94it/s] [2024-06-06 23:43:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
60%|██████ | 120/199 [01:02<00:40, 1.94it/s] [2024-06-06 23:43:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
60%|██████ | 120/199 [01:02<00:40, 1.94it/s] 61%|██████ | 121/199 [01:02<00:53, 1.47it/s] [2024-06-06 23:43:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (3584,), dtype: float16
61%|██████ | 121/199 [01:02<00:53, 1.47it/s] [2024-06-06 23:43:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (3584,), dtype: float16
61%|██████ | 121/199 [01:02<00:53, 1.47it/s] [2024-06-06 23:43:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
61%|██████ | 121/199 [01:02<00:53, 1.47it/s] [2024-06-06 23:43:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
61%|██████ | 121/199 [01:02<00:53, 1.47it/s] 62%|██████▏ | 124/199 [01:02<00:33, 2.23it/s] [2024-06-06 23:43:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
62%|██████▏ | 124/199 [01:04<00:33, 2.23it/s] [2024-06-06 23:43:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
62%|██████▏ | 124/199 [01:04<00:33, 2.23it/s] 63%|██████▎ | 125/199 [01:04<00:43, 1.68it/s] [2024-06-06 23:43:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (3584,), dtype: float16
63%|██████▎ | 125/199 [01:04<00:43, 1.68it/s] [2024-06-06 23:43:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.c_attn.bias", shape: (4608,), dtype: float16
63%|██████▎ | 125/199 [01:04<00:43, 1.68it/s] [2024-06-06 23:43:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
63%|██████▎ | 125/199 [01:04<00:43, 1.68it/s] [2024-06-06 23:43:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
63%|██████▎ | 125/199 [01:04<00:43, 1.68it/s] 64%|██████▍ | 128/199 [01:04<00:26, 2.73it/s] [2024-06-06 23:43:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
64%|██████▍ | 128/199 [01:04<00:26, 2.73it/s] [2024-06-06 23:43:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
64%|██████▍ | 128/199 [01:04<00:26, 2.73it/s] [2024-06-06 23:43:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (3584,), dtype: float16
64%|██████▍ | 128/199 [01:04<00:26, 2.73it/s] [2024-06-06 23:43:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
64%|██████▍ | 128/199 [01:04<00:26, 2.73it/s] [2024-06-06 23:43:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
64%|██████▍ | 128/199 [01:04<00:26, 2.73it/s] 66%|██████▌ | 131/199 [01:04<00:19, 3.56it/s] [2024-06-06 23:43:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
66%|██████▌ | 131/199 [01:06<00:19, 3.56it/s] [2024-06-06 23:43:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
66%|██████▌ | 131/199 [01:06<00:19, 3.56it/s] 66%|██████▋ | 132/199 [01:06<00:30, 2.21it/s] [2024-06-06 23:43:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (3584,), dtype: float16
66%|██████▋ | 132/199 [01:06<00:30, 2.21it/s] [2024-06-06 23:43:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.c_attn.bias", shape: (4608,), dtype: float16
66%|██████▋ | 132/199 [01:06<00:30, 2.21it/s] [2024-06-06 23:43:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
66%|██████▋ | 132/199 [01:06<00:30, 2.21it/s] [2024-06-06 23:43:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
66%|██████▋ | 132/199 [01:06<00:30, 2.21it/s] 68%|██████▊ | 135/199 [01:06<00:18, 3.41it/s] [2024-06-06 23:43:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
68%|██████▊ | 135/199 [01:06<00:18, 3.41it/s] [2024-06-06 23:43:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
68%|██████▊ | 135/199 [01:06<00:18, 3.41it/s] [2024-06-06 23:43:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (3584,), dtype: float16
68%|██████▊ | 135/199 [01:06<00:18, 3.41it/s] [2024-06-06 23:43:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
68%|██████▊ | 135/199 [01:06<00:18, 3.41it/s] [2024-06-06 23:43:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
68%|██████▊ | 135/199 [01:06<00:18, 3.41it/s] 69%|██████▉ | 138/199 [01:06<00:14, 4.25it/s] [2024-06-06 23:43:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
69%|██████▉ | 138/199 [01:07<00:14, 4.25it/s] [2024-06-06 23:43:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
69%|██████▉ | 138/199 [01:07<00:14, 4.25it/s] [2024-06-06 23:43:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (3584,), dtype: float16
69%|██████▉ | 138/199 [01:07<00:14, 4.25it/s] 70%|███████ | 140/199 [01:07<00:19, 3.08it/s] [2024-06-06 23:43:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.c_attn.bias", shape: (4608,), dtype: float16
70%|███████ | 140/199 [01:07<00:19, 3.08it/s] [2024-06-06 23:43:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
70%|███████ | 140/199 [01:08<00:19, 3.08it/s] [2024-06-06 23:43:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
70%|███████ | 140/199 [01:08<00:19, 3.08it/s] 71%|███████▏ | 142/199 [01:08<00:14, 3.92it/s] [2024-06-06 23:43:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
71%|███████▏ | 142/199 [01:08<00:14, 3.92it/s] [2024-06-06 23:43:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
71%|███████▏ | 142/199 [01:08<00:14, 3.92it/s] [2024-06-06 23:43:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (3584,), dtype: float16
71%|███████▏ | 142/199 [01:08<00:14, 3.92it/s] [2024-06-06 23:43:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
71%|███████▏ | 142/199 [01:08<00:14, 3.92it/s] [2024-06-06 23:43:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
71%|███████▏ | 142/199 [01:08<00:14, 3.92it/s] 73%|███████▎ | 145/199 [01:08<00:11, 4.77it/s] [2024-06-06 23:43:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (3584,), dtype: float16
73%|███████▎ | 145/199 [01:08<00:11, 4.77it/s] [2024-06-06 23:43:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (3584,), dtype: float16
73%|███████▎ | 145/199 [01:08<00:11, 4.77it/s] [2024-06-06 23:43:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
73%|███████▎ | 145/199 [01:08<00:11, 4.77it/s] [2024-06-06 23:43:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
73%|███████▎ | 145/199 [01:08<00:11, 4.77it/s] 74%|███████▍ | 148/199 [01:08<00:08, 5.68it/s] [2024-06-06 23:43:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
74%|███████▍ | 148/199 [01:10<00:08, 5.68it/s] [2024-06-06 23:43:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
74%|███████▍ | 148/199 [01:10<00:08, 5.68it/s] 75%|███████▍ | 149/199 [01:10<00:17, 2.82it/s] [2024-06-06 23:43:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (3584,), dtype: float16
75%|███████▍ | 149/199 [01:10<00:17, 2.82it/s] [2024-06-06 23:43:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.c_attn.bias", shape: (4608,), dtype: float16
75%|███████▍ | 149/199 [01:10<00:17, 2.82it/s] [2024-06-06 23:43:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
75%|███████▍ | 149/199 [01:10<00:17, 2.82it/s] [2024-06-06 23:43:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
75%|███████▍ | 149/199 [01:10<00:17, 2.82it/s] 76%|███████▋ | 152/199 [01:10<00:11, 4.15it/s] [2024-06-06 23:43:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
76%|███████▋ | 152/199 [01:10<00:11, 4.15it/s] [2024-06-06 23:43:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
76%|███████▋ | 152/199 [01:10<00:11, 4.15it/s] [2024-06-06 23:43:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (3584,), dtype: float16
76%|███████▋ | 152/199 [01:10<00:11, 4.15it/s] [2024-06-06 23:43:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
76%|███████▋ | 152/199 [01:10<00:11, 4.15it/s] [2024-06-06 23:43:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
76%|███████▋ | 152/199 [01:10<00:11, 4.15it/s] 78%|███████▊ | 155/199 [01:10<00:09, 4.84it/s] [2024-06-06 23:43:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
78%|███████▊ | 155/199 [01:12<00:09, 4.84it/s] [2024-06-06 23:43:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
78%|███████▊ | 155/199 [01:12<00:09, 4.84it/s] 78%|███████▊ | 156/199 [01:12<00:17, 2.52it/s] [2024-06-06 23:43:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (3584,), dtype: float16
78%|███████▊ | 156/199 [01:12<00:17, 2.52it/s] [2024-06-06 23:43:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.c_attn.bias", shape: (4608,), dtype: float16
78%|███████▊ | 156/199 [01:12<00:17, 2.52it/s] [2024-06-06 23:43:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
78%|███████▊ | 156/199 [01:12<00:17, 2.52it/s] [2024-06-06 23:43:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
78%|███████▊ | 156/199 [01:12<00:17, 2.52it/s] 80%|███████▉ | 159/199 [01:12<00:10, 3.79it/s] [2024-06-06 23:43:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
80%|███████▉ | 159/199 [01:12<00:10, 3.79it/s] [2024-06-06 23:43:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
80%|███████▉ | 159/199 [01:12<00:10, 3.79it/s] [2024-06-06 23:43:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (3584,), dtype: float16
80%|███████▉ | 159/199 [01:12<00:10, 3.79it/s] [2024-06-06 23:43:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
80%|███████▉ | 159/199 [01:12<00:10, 3.79it/s] [2024-06-06 23:43:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
80%|███████▉ | 159/199 [01:12<00:10, 3.79it/s] 81%|████████▏ | 162/199 [01:12<00:08, 4.60it/s] [2024-06-06 23:43:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
81%|████████▏ | 162/199 [01:13<00:08, 4.60it/s] [2024-06-06 23:43:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
81%|████████▏ | 162/199 [01:14<00:08, 4.60it/s] [2024-06-06 23:43:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (3584,), dtype: float16
81%|████████▏ | 162/199 [01:14<00:08, 4.60it/s] 82%|████████▏ | 164/199 [01:14<00:11, 3.14it/s] [2024-06-06 23:43:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.c_attn.bias", shape: (4608,), dtype: float16
82%|████████▏ | 164/199 [01:14<00:11, 3.14it/s] [2024-06-06 23:43:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
82%|████████▏ | 164/199 [01:14<00:11, 3.14it/s] [2024-06-06 23:43:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
82%|████████▏ | 164/199 [01:14<00:11, 3.14it/s] 83%|████████▎ | 166/199 [01:14<00:08, 3.96it/s] [2024-06-06 23:43:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
83%|████████▎ | 166/199 [01:14<00:08, 3.96it/s] [2024-06-06 23:43:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
83%|████████▎ | 166/199 [01:14<00:08, 3.96it/s] [2024-06-06 23:43:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (3584,), dtype: float16
83%|████████▎ | 166/199 [01:14<00:08, 3.96it/s] [2024-06-06 23:43:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
83%|████████▎ | 166/199 [01:14<00:08, 3.96it/s] [2024-06-06 23:43:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
83%|████████▎ | 166/199 [01:14<00:08, 3.96it/s] 85%|████████▍ | 169/199 [01:14<00:06, 4.77it/s] [2024-06-06 23:43:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
85%|████████▍ | 169/199 [01:15<00:06, 4.77it/s] [2024-06-06 23:43:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
85%|████████▍ | 169/199 [01:15<00:06, 4.77it/s] 85%|████████▌ | 170/199 [01:15<00:10, 2.81it/s] [2024-06-06 23:43:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (3584,), dtype: float16
85%|████████▌ | 170/199 [01:15<00:10, 2.81it/s] [2024-06-06 23:43:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.c_attn.bias", shape: (4608,), dtype: float16
85%|████████▌ | 170/199 [01:15<00:10, 2.81it/s] [2024-06-06 23:43:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
85%|████████▌ | 170/199 [01:16<00:10, 2.81it/s] [2024-06-06 23:43:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
85%|████████▌ | 170/199 [01:16<00:10, 2.81it/s] 87%|████████▋ | 173/199 [01:16<00:06, 4.23it/s] [2024-06-06 23:43:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
87%|████████▋ | 173/199 [01:16<00:06, 4.23it/s] [2024-06-06 23:43:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
87%|████████▋ | 173/199 [01:16<00:06, 4.23it/s] [2024-06-06 23:43:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (3584,), dtype: float16
87%|████████▋ | 173/199 [01:16<00:06, 4.23it/s] [2024-06-06 23:43:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
87%|████████▋ | 173/199 [01:16<00:06, 4.23it/s] [2024-06-06 23:43:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
87%|████████▋ | 173/199 [01:16<00:06, 4.23it/s] 88%|████████▊ | 176/199 [01:16<00:04, 4.89it/s] [2024-06-06 23:43:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
88%|████████▊ | 176/199 [01:17<00:04, 4.89it/s] [2024-06-06 23:43:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
88%|████████▊ | 176/199 [01:17<00:04, 4.89it/s] 89%|████████▉ | 177/199 [01:17<00:07, 2.85it/s] [2024-06-06 23:43:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (3584,), dtype: float16
89%|████████▉ | 177/199 [01:17<00:07, 2.85it/s] [2024-06-06 23:43:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.c_attn.bias", shape: (4608,), dtype: float16
89%|████████▉ | 177/199 [01:17<00:07, 2.85it/s] [2024-06-06 23:43:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
89%|████████▉ | 177/199 [01:17<00:07, 2.85it/s] [2024-06-06 23:43:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
89%|████████▉ | 177/199 [01:17<00:07, 2.85it/s] 90%|█████████ | 180/199 [01:17<00:04, 4.27it/s] [2024-06-06 23:43:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
90%|█████████ | 180/199 [01:17<00:04, 4.27it/s] [2024-06-06 23:43:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
90%|█████████ | 180/199 [01:17<00:04, 4.27it/s] [2024-06-06 23:43:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (3584,), dtype: float16
90%|█████████ | 180/199 [01:17<00:04, 4.27it/s] [2024-06-06 23:43:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
90%|█████████ | 180/199 [01:18<00:04, 4.27it/s] [2024-06-06 23:43:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
90%|█████████ | 180/199 [01:18<00:04, 4.27it/s] 92%|█████████▏| 183/199 [01:18<00:03, 5.05it/s] [2024-06-06 23:43:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
92%|█████████▏| 183/199 [01:19<00:03, 5.05it/s] [2024-06-06 23:43:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
92%|█████████▏| 183/199 [01:19<00:03, 5.05it/s] [2024-06-06 23:43:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (3584,), dtype: float16
92%|█████████▏| 183/199 [01:19<00:03, 5.05it/s] 93%|█████████▎| 185/199 [01:19<00:03, 3.56it/s] [2024-06-06 23:43:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.c_attn.bias", shape: (4608,), dtype: float16
93%|█████████▎| 185/199 [01:19<00:03, 3.56it/s] [2024-06-06 23:43:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
93%|█████████▎| 185/199 [01:19<00:03, 3.56it/s] [2024-06-06 23:43:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
93%|█████████▎| 185/199 [01:19<00:03, 3.56it/s] 94%|█████████▍| 187/199 [01:19<00:02, 4.45it/s] [2024-06-06 23:43:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
94%|█████████▍| 187/199 [01:19<00:02, 4.45it/s] [2024-06-06 23:43:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
94%|█████████▍| 187/199 [01:19<00:02, 4.45it/s] [2024-06-06 23:43:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (3584,), dtype: float16
94%|█████████▍| 187/199 [01:19<00:02, 4.45it/s] [2024-06-06 23:43:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (3584, 2368), dtype: uint32
94%|█████████▍| 187/199 [01:19<00:02, 4.45it/s] [2024-06-06 23:43:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (3584, 592), dtype: float16
94%|█████████▍| 187/199 [01:19<00:02, 4.45it/s] 95%|█████████▌| 190/199 [01:19<00:01, 5.24it/s] [2024-06-06 23:43:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
95%|█████████▌| 190/199 [01:20<00:01, 5.24it/s] [2024-06-06 23:43:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
95%|█████████▌| 190/199 [01:20<00:01, 5.24it/s] 96%|█████████▌| 191/199 [01:20<00:02, 3.01it/s] [2024-06-06 23:43:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (3584,), dtype: float16
96%|█████████▌| 191/199 [01:20<00:02, 3.01it/s] [2024-06-06 23:43:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.c_attn.bias", shape: (4608,), dtype: float16
96%|█████████▌| 191/199 [01:20<00:02, 3.01it/s] [2024-06-06 23:43:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
96%|█████████▌| 191/199 [01:21<00:02, 3.01it/s] [2024-06-06 23:43:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
96%|█████████▌| 191/199 [01:21<00:02, 3.01it/s] 97%|█████████▋| 194/199 [01:21<00:01, 4.51it/s] [2024-06-06 23:43:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
97%|█████████▋| 194/199 [01:21<00:01, 4.51it/s] [2024-06-06 23:43:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
97%|█████████▋| 194/199 [01:21<00:01, 4.51it/s] [2024-06-06 23:43:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (37888, 448), dtype: uint32
97%|█████████▋| 194/199 [01:22<00:01, 4.51it/s] [2024-06-06 23:43:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (37888, 112), dtype: float16
97%|█████████▋| 194/199 [01:22<00:01, 4.51it/s] 98%|█████████▊| 196/199 [01:22<00:01, 2.95it/s] [2024-06-06 23:43:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.c_attn.bias", shape: (4608,), dtype: float16
98%|█████████▊| 196/199 [01:22<00:01, 2.95it/s] [2024-06-06 23:43:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.c_attn.q_weight", shape: (4608, 448), dtype: uint32
98%|█████████▊| 196/199 [01:22<00:01, 2.95it/s] [2024-06-06 23:43:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.c_attn.q_scale", shape: (4608, 112), dtype: float16
98%|█████████▊| 196/199 [01:22<00:01, 2.95it/s] 99%|█████████▉| 198/199 [01:22<00:00, 3.78it/s] [2024-06-06 23:43:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (3584, 448), dtype: uint32
99%|█████████▉| 198/199 [01:22<00:00, 3.78it/s] [2024-06-06 23:43:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (3584, 112), dtype: float16
99%|█████████▉| 198/199 [01:22<00:00, 3.78it/s] 100%|██████████| 199/199 [01:22<00:00, 2.41it/s]
[2024-06-06 23:43:44] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Qwen2-7B-Instruct/model-00002-of-00004.safetensors
[2024-06-06 23:43:45] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Qwen2-7B-Instruct/model-00003-of-00004.safetensors
[2024-06-06 23:43:45] INFO stats.py:77: Time usage: HF loading: 17.289 sec; Pre-quantization mapping: 48.744 sec; Quantization: 3.234 sec
[2024-06-06 23:43:45] INFO stats.py:91: RAM usage: Peak RAM: 14.397 GB. Total bytes loaded from disk: 28.370 GB
[2024-06-06 23:43:45] INFO convert_weight.py:155: Parameter size after quantization: 3.990 GB
[2024-06-06 23:43:45] INFO convert_weight.py:160: Total parameters: 7,615,616,512
[2024-06-06 23:43:45] INFO convert_weight.py:161: Bits per parameter: 4.501
[2024-06-06 23:43:45] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Qwen2-7B-Instruct-q4f16_1-MLC
All finished, 88 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Qwen2-7B-Instruct-q4f16_1-MLC/ndarray-cache.json