Hugging Face's logo

mlc-ai
/
Llama-3-8B-Instruct-q3f16_1-MLC

MLC-LLM
web-llm
Model card Files Community
Llama-3-8B-Instruct-q3f16_1-MLC / logs.txt
riczhou's picture
riczhou
Initial commit
349f119 verified
raw
history blame
No virus
105 kB
/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Meta-Llama-3-8B-Instruct --quantization q3f16_1 --conv-template llama-3 --output /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q3f16_1-MLC
[2024-06-04 03:19:09] INFO auto_config.py:116: Found model configuration: /models/Meta-Llama-3-8B-Instruct/config.json
[2024-06-04 03:19:09] INFO auto_config.py:154: Found model type: llama. Use `--model-type` to override.
[2024-06-04 03:19:09] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (8192)
[2024-06-04 03:19:09] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
[2024-06-04 03:19:09] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-04 03:19:09] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 128000
[2024-06-04 03:19:09] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [128001, 128009]
[2024-06-04 03:19:09] INFO gen_config.py:143: [generation_config.json] Setting temperature: 0.6
[2024-06-04 03:19:09] INFO gen_config.py:143: [generation_config.json] Setting top_p: 0.9
[2024-06-04 03:19:09] INFO gen_config.py:157: Not found tokenizer config: /models/Meta-Llama-3-8B-Instruct/tokenizer.model
[2024-06-04 03:19:09] INFO gen_config.py:155: Found tokenizer config: /models/Meta-Llama-3-8B-Instruct/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q3f16_1-MLC/tokenizer.json
[2024-06-04 03:19:09] INFO gen_config.py:157: Not found tokenizer config: /models/Meta-Llama-3-8B-Instruct/vocab.json
[2024-06-04 03:19:09] INFO gen_config.py:157: Not found tokenizer config: /models/Meta-Llama-3-8B-Instruct/merges.txt
[2024-06-04 03:19:09] INFO gen_config.py:157: Not found tokenizer config: /models/Meta-Llama-3-8B-Instruct/added_tokens.json
[2024-06-04 03:19:09] INFO gen_config.py:155: Found tokenizer config: /models/Meta-Llama-3-8B-Instruct/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q3f16_1-MLC/tokenizer_config.json
[2024-06-04 03:19:09] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_level', 'prepend_space_in_encode': False, 'strip_space_in_decode': False}
[2024-06-04 03:19:09] INFO gen_config.py:32: [System default] Setting pad_token_id: 0
[2024-06-04 03:19:09] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-04 03:19:09] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-04 03:19:09] INFO gen_config.py:32: [System default] Setting repetition_penalty: 1.0
[2024-06-04 03:19:09] INFO gen_config.py:32: [System default] Setting mean_gen_len: 128
[2024-06-04 03:19:09] INFO gen_config.py:32: [System default] Setting max_gen_len: 512
[2024-06-04 03:19:09] INFO gen_config.py:32: [System default] Setting shift_fill_factor: 0.3
[2024-06-04 03:19:09] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q3f16_1-MLC/mlc-chat-config.json
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Meta-Llama-3-8B-Instruct --quantization q3f16_1 --output /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q3f16_1-MLC
[2024-06-04 03:19:10] INFO auto_config.py:116: Found model configuration: /models/Meta-Llama-3-8B-Instruct/config.json
[2024-06-04 03:19:12] INFO auto_device.py:79: Found device: cuda:0
[2024-06-04 03:19:13] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-04 03:19:15] INFO auto_device.py:88: Not found device: metal:0
[2024-06-04 03:19:16] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-04 03:19:16] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-04 03:19:16] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-04 03:19:16] INFO auto_device.py:79: Found device: vulkan:3
[2024-06-04 03:19:18] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-04 03:19:18] INFO auto_device.py:35: Using device: cuda:0
[2024-06-04 03:19:18] INFO auto_weight.py:71: Finding weights in: /models/Meta-Llama-3-8B-Instruct
[2024-06-04 03:19:18] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-04 03:19:18] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /models/Meta-Llama-3-8B-Instruct/model.safetensors.index.json
[2024-06-04 03:19:18] INFO auto_weight.py:107: Using source weight configuration: /models/Meta-Llama-3-8B-Instruct/model.safetensors.index.json. Use `--source` to override.
[2024-06-04 03:19:18] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-04 03:19:18] INFO auto_config.py:154: Found model type: llama. Use `--model-type` to override.
[2024-06-04 03:19:18] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (8192)
[2024-06-04 03:19:18] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
Weight conversion with arguments:
--config /models/Meta-Llama-3-8B-Instruct/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 llama
--device cuda:0
--source /models/Meta-Llama-3-8B-Instruct/model.safetensors.index.json
--source-format huggingface-safetensor
--output /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q3f16_1-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q3f16_1-MLC
0%| | 0/195 [00:00<?, ?it/s] [2024-06-04 03:19:22] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Meta-Llama-3-8B-Instruct/model-00004-of-00004.safetensors
0%| | 0/195 [00:00<?, ?it/s] [2024-06-04 03:19:25] INFO group_quantization.py:217: Compiling quantize function for key: ((128256, 4096), float16, cuda, axis=1, output_transpose=False)
0%| | 0/195 [00:03<?, ?it/s] [2024-06-04 03:19:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_weight", shape: (128256, 412), dtype: uint32
0%| | 0/195 [00:04<?, ?it/s] [2024-06-04 03:19:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_scale", shape: (128256, 103), dtype: float16
0%| | 0/195 [00:05<?, ?it/s] 1%| | 1/195 [00:05<17:14, 5.33s/it] [2024-06-04 03:19:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.input_layernorm.weight", shape: (4096,), dtype: float16
1%| | 1/195 [00:05<17:14, 5.33s/it] [2024-06-04 03:19:27] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 14336), float16, cuda, axis=1, output_transpose=False)
1%| | 1/195 [00:05<17:14, 5.33s/it] [2024-06-04 03:19:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
1%| | 1/195 [00:06<17:14, 5.33s/it] [2024-06-04 03:19:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
1%| | 1/195 [00:06<17:14, 5.33s/it] 2%|▏ | 3/195 [00:06<05:20, 1.67s/it] [2024-06-04 03:19:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.post_attention_layernorm.weight", shape: (4096,), dtype: float16
2%|▏ | 3/195 [00:06<05:20, 1.67s/it] [2024-06-04 03:19:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (4096,), dtype: float16
2%|▏ | 3/195 [00:06<05:20, 1.67s/it] [2024-06-04 03:19:28] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Meta-Llama-3-8B-Instruct/model-00004-of-00004.safetensors
2%|▏ | 3/195 [00:06<05:20, 1.67s/it] [2024-06-04 03:19:28] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Meta-Llama-3-8B-Instruct/model-00001-of-00004.safetensors
2%|▏ | 3/195 [00:06<05:20, 1.67s/it] [2024-06-04 03:19:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (128256, 412), dtype: uint32
2%|▏ | 3/195 [00:12<05:20, 1.67s/it] [2024-06-04 03:19:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (128256, 103), dtype: float16
2%|▏ | 3/195 [00:12<05:20, 1.67s/it] 3%|▎ | 6/195 [00:12<06:23, 2.03s/it] [2024-06-04 03:19:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (4096,), dtype: float16
3%|▎ | 6/195 [00:12<06:23, 2.03s/it] [2024-06-04 03:19:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
3%|▎ | 6/195 [00:13<06:23, 2.03s/it] [2024-06-04 03:19:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
3%|▎ | 6/195 [00:13<06:23, 2.03s/it] 4%|▍ | 8/195 [00:13<04:08, 1.33s/it] [2024-06-04 03:19:35] INFO group_quantization.py:217: Compiling quantize function for key: ((28672, 4096), float16, cuda, axis=1, output_transpose=False)
4%|▍ | 8/195 [00:13<04:08, 1.33s/it] [2024-06-04 03:19:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
4%|▍ | 8/195 [00:14<04:08, 1.33s/it] [2024-06-04 03:19:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
4%|▍ | 8/195 [00:14<04:08, 1.33s/it] 5%|▍ | 9/195 [00:14<04:00, 1.29s/it] [2024-06-04 03:19:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (4096,), dtype: float16
5%|▍ | 9/195 [00:14<04:00, 1.29s/it] [2024-06-04 03:19:36] INFO group_quantization.py:217: Compiling quantize function for key: ((6144, 4096), float16, cuda, axis=1, output_transpose=False)
5%|▍ | 9/195 [00:14<04:00, 1.29s/it] [2024-06-04 03:19:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
5%|▍ | 9/195 [00:14<04:00, 1.29s/it] [2024-06-04 03:19:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
5%|▍ | 9/195 [00:14<04:00, 1.29s/it] 6%|▌ | 11/195 [00:14<02:50, 1.08it/s] [2024-06-04 03:19:37] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 4096), float16, cuda, axis=1, output_transpose=False)
6%|▌ | 11/195 [00:14<02:50, 1.08it/s] [2024-06-04 03:19:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
6%|▌ | 11/195 [00:15<02:50, 1.08it/s] [2024-06-04 03:19:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
6%|▌ | 11/195 [00:15<02:50, 1.08it/s] 6%|▌ | 12/195 [00:15<02:36, 1.17it/s] [2024-06-04 03:19:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (4096,), dtype: float16
6%|▌ | 12/195 [00:15<02:36, 1.17it/s] [2024-06-04 03:19:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
6%|▌ | 12/195 [00:15<02:36, 1.17it/s] [2024-06-04 03:19:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
6%|▌ | 12/195 [00:15<02:36, 1.17it/s] 7%|▋ | 14/195 [00:15<01:45, 1.71it/s] [2024-06-04 03:19:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
7%|▋ | 14/195 [00:16<01:45, 1.71it/s] [2024-06-04 03:19:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
7%|▋ | 14/195 [00:16<01:45, 1.71it/s] 8%|▊ | 15/195 [00:16<01:48, 1.65it/s] [2024-06-04 03:19:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (4096,), dtype: float16
8%|▊ | 15/195 [00:16<01:48, 1.65it/s] [2024-06-04 03:19:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
8%|▊ | 15/195 [00:16<01:48, 1.65it/s] [2024-06-04 03:19:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
8%|▊ | 15/195 [00:16<01:48, 1.65it/s] 9%|▊ | 17/195 [00:16<01:10, 2.51it/s] [2024-06-04 03:19:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
9%|▊ | 17/195 [00:16<01:10, 2.51it/s] [2024-06-04 03:19:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
9%|▊ | 17/195 [00:16<01:10, 2.51it/s] [2024-06-04 03:19:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (4096,), dtype: float16
9%|▊ | 17/195 [00:16<01:10, 2.51it/s] [2024-06-04 03:19:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
9%|▊ | 17/195 [00:16<01:10, 2.51it/s] [2024-06-04 03:19:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
9%|▊ | 17/195 [00:16<01:10, 2.51it/s] 10%|█ | 20/195 [00:16<00:47, 3.67it/s] [2024-06-04 03:19:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
10%|█ | 20/195 [00:17<00:47, 3.67it/s] [2024-06-04 03:19:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
10%|█ | 20/195 [00:17<00:47, 3.67it/s] 11%|█ | 21/195 [00:17<01:00, 2.90it/s] [2024-06-04 03:19:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (4096,), dtype: float16
11%|█ | 21/195 [00:17<01:00, 2.90it/s] [2024-06-04 03:19:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
11%|█ | 21/195 [00:17<01:00, 2.90it/s] [2024-06-04 03:19:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
11%|█ | 21/195 [00:17<01:00, 2.90it/s] 12%|█▏ | 23/195 [00:17<00:42, 4.03it/s] [2024-06-04 03:19:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
12%|█▏ | 23/195 [00:17<00:42, 4.03it/s] [2024-06-04 03:19:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
12%|█▏ | 23/195 [00:17<00:42, 4.03it/s] [2024-06-04 03:19:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (4096,), dtype: float16
12%|█▏ | 23/195 [00:17<00:42, 4.03it/s] [2024-06-04 03:19:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
12%|█▏ | 23/195 [00:18<00:42, 4.03it/s] [2024-06-04 03:19:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
12%|█▏ | 23/195 [00:18<00:42, 4.03it/s] 13%|█▎ | 26/195 [00:18<00:32, 5.19it/s] [2024-06-04 03:19:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
13%|█▎ | 26/195 [00:18<00:32, 5.19it/s] [2024-06-04 03:19:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
13%|█▎ | 26/195 [00:18<00:32, 5.19it/s] 14%|█▍ | 27/195 [00:18<00:45, 3.70it/s] [2024-06-04 03:19:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (4096,), dtype: float16
14%|█▍ | 27/195 [00:18<00:45, 3.70it/s] [2024-06-04 03:19:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
14%|█▍ | 27/195 [00:18<00:45, 3.70it/s] [2024-06-04 03:19:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
14%|█▍ | 27/195 [00:18<00:45, 3.70it/s] 15%|█▍ | 29/195 [00:18<00:33, 4.99it/s] [2024-06-04 03:19:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
15%|█▍ | 29/195 [00:18<00:33, 4.99it/s] [2024-06-04 03:19:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
15%|█▍ | 29/195 [00:18<00:33, 4.99it/s] [2024-06-04 03:19:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (4096,), dtype: float16
15%|█▍ | 29/195 [00:18<00:33, 4.99it/s] [2024-06-04 03:19:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
15%|█▍ | 29/195 [00:19<00:33, 4.99it/s] [2024-06-04 03:19:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
15%|█▍ | 29/195 [00:19<00:33, 4.99it/s] 16%|█▋ | 32/195 [00:19<00:26, 6.12it/s] [2024-06-04 03:19:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
16%|█▋ | 32/195 [00:19<00:26, 6.12it/s] [2024-06-04 03:19:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
16%|█▋ | 32/195 [00:19<00:26, 6.12it/s] [2024-06-04 03:19:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (4096,), dtype: float16
16%|█▋ | 32/195 [00:19<00:26, 6.12it/s] 17%|█▋ | 34/195 [00:19<00:34, 4.73it/s] [2024-06-04 03:19:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
17%|█▋ | 34/195 [00:19<00:34, 4.73it/s] [2024-06-04 03:19:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
17%|█▋ | 34/195 [00:19<00:34, 4.73it/s] 18%|█▊ | 35/195 [00:19<00:30, 5.16it/s] [2024-06-04 03:19:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
18%|█▊ | 35/195 [00:19<00:30, 5.16it/s] [2024-06-04 03:19:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
18%|█▊ | 35/195 [00:19<00:30, 5.16it/s] [2024-06-04 03:19:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (4096,), dtype: float16
18%|█▊ | 35/195 [00:19<00:30, 5.16it/s] [2024-06-04 03:19:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
18%|█▊ | 35/195 [00:20<00:30, 5.16it/s] [2024-06-04 03:19:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
18%|█▊ | 35/195 [00:20<00:30, 5.16it/s] 19%|█▉ | 38/195 [00:20<00:24, 6.28it/s] [2024-06-04 03:19:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
19%|█▉ | 38/195 [00:20<00:24, 6.28it/s] [2024-06-04 03:19:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
19%|█▉ | 38/195 [00:20<00:24, 6.28it/s] 20%|██ | 39/195 [00:20<00:37, 4.11it/s] [2024-06-04 03:19:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (4096,), dtype: float16
20%|██ | 39/195 [00:20<00:37, 4.11it/s] [2024-06-04 03:19:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
20%|██ | 39/195 [00:21<00:37, 4.11it/s] [2024-06-04 03:19:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
20%|██ | 39/195 [00:21<00:37, 4.11it/s] 21%|██ | 41/195 [00:21<00:28, 5.45it/s] [2024-06-04 03:19:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
21%|██ | 41/195 [00:21<00:28, 5.45it/s] [2024-06-04 03:19:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
21%|██ | 41/195 [00:21<00:28, 5.45it/s] [2024-06-04 03:19:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (4096,), dtype: float16
21%|██ | 41/195 [00:21<00:28, 5.45it/s] [2024-06-04 03:19:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
21%|██ | 41/195 [00:21<00:28, 5.45it/s] [2024-06-04 03:19:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
21%|██ | 41/195 [00:21<00:28, 5.45it/s] 23%|██▎ | 44/195 [00:21<00:23, 6.46it/s] [2024-06-04 03:19:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
23%|██▎ | 44/195 [00:21<00:23, 6.46it/s] [2024-06-04 03:19:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
23%|██▎ | 44/195 [00:21<00:23, 6.46it/s] 23%|██▎ | 45/195 [00:22<00:35, 4.23it/s] [2024-06-04 03:19:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (4096,), dtype: float16
23%|██▎ | 45/195 [00:22<00:35, 4.23it/s] [2024-06-04 03:19:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
23%|██▎ | 45/195 [00:22<00:35, 4.23it/s] [2024-06-04 03:19:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
23%|██▎ | 45/195 [00:22<00:35, 4.23it/s] 24%|██▍ | 47/195 [00:22<00:26, 5.59it/s] [2024-06-04 03:19:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
24%|██▍ | 47/195 [00:22<00:26, 5.59it/s] [2024-06-04 03:19:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
24%|██▍ | 47/195 [00:22<00:26, 5.59it/s] [2024-06-04 03:19:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (4096,), dtype: float16
24%|██▍ | 47/195 [00:22<00:26, 5.59it/s] [2024-06-04 03:19:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
24%|██▍ | 47/195 [00:22<00:26, 5.59it/s] [2024-06-04 03:19:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
24%|██▍ | 47/195 [00:22<00:26, 5.59it/s] 26%|██▌ | 50/195 [00:22<00:22, 6.57it/s] [2024-06-04 03:19:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
26%|██▌ | 50/195 [00:22<00:22, 6.57it/s] [2024-06-04 03:19:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
26%|██▌ | 50/195 [00:23<00:22, 6.57it/s] 26%|██▌ | 51/195 [00:23<00:33, 4.24it/s] [2024-06-04 03:19:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (4096,), dtype: float16
26%|██▌ | 51/195 [00:23<00:33, 4.24it/s] [2024-06-04 03:19:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
26%|██▌ | 51/195 [00:23<00:33, 4.24it/s] [2024-06-04 03:19:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
26%|██▌ | 51/195 [00:23<00:33, 4.24it/s] 27%|██▋ | 53/195 [00:23<00:25, 5.56it/s] [2024-06-04 03:19:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
27%|██▋ | 53/195 [00:23<00:25, 5.56it/s] [2024-06-04 03:19:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
27%|██▋ | 53/195 [00:23<00:25, 5.56it/s] [2024-06-04 03:19:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (4096,), dtype: float16
27%|██▋ | 53/195 [00:23<00:25, 5.56it/s] [2024-06-04 03:19:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
27%|██▋ | 53/195 [00:23<00:25, 5.56it/s] [2024-06-04 03:19:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
27%|██▋ | 53/195 [00:23<00:25, 5.56it/s] 29%|██▊ | 56/195 [00:23<00:21, 6.49it/s] [2024-06-04 03:19:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
29%|██▊ | 56/195 [00:24<00:21, 6.49it/s] [2024-06-04 03:19:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
29%|██▊ | 56/195 [00:24<00:21, 6.49it/s] 29%|██▉ | 57/195 [00:24<00:32, 4.23it/s] [2024-06-04 03:19:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (4096,), dtype: float16
29%|██▉ | 57/195 [00:24<00:32, 4.23it/s] [2024-06-04 03:19:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
29%|██▉ | 57/195 [00:24<00:32, 4.23it/s] [2024-06-04 03:19:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
29%|██▉ | 57/195 [00:24<00:32, 4.23it/s] 30%|███ | 59/195 [00:24<00:24, 5.56it/s] [2024-06-04 03:19:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
30%|███ | 59/195 [00:24<00:24, 5.56it/s] [2024-06-04 03:19:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
30%|███ | 59/195 [00:24<00:24, 5.56it/s] [2024-06-04 03:19:46] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Meta-Llama-3-8B-Instruct/model-00001-of-00004.safetensors
30%|███ | 59/195 [00:24<00:24, 5.56it/s] [2024-06-04 03:19:47] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Meta-Llama-3-8B-Instruct/model-00002-of-00004.safetensors
30%|███ | 59/195 [00:25<00:24, 5.56it/s] [2024-06-04 03:19:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (4096,), dtype: float16
30%|███ | 59/195 [00:29<00:24, 5.56it/s] 31%|███▏ | 61/195 [00:29<01:59, 1.12it/s] [2024-06-04 03:19:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
31%|███▏ | 61/195 [00:29<01:59, 1.12it/s] [2024-06-04 03:19:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
31%|███▏ | 61/195 [00:29<01:59, 1.12it/s] 32%|███▏ | 62/195 [00:29<01:43, 1.28it/s] [2024-06-04 03:19:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
32%|███▏ | 62/195 [00:30<01:43, 1.28it/s] [2024-06-04 03:19:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
32%|███▏ | 62/195 [00:30<01:43, 1.28it/s] 32%|███▏ | 63/195 [00:30<01:39, 1.33it/s] [2024-06-04 03:19:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (4096,), dtype: float16
32%|███▏ | 63/195 [00:30<01:39, 1.33it/s] [2024-06-04 03:19:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
32%|███▏ | 63/195 [00:30<01:39, 1.33it/s] [2024-06-04 03:19:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
32%|███▏ | 63/195 [00:30<01:39, 1.33it/s] 33%|███▎ | 65/195 [00:30<01:04, 2.02it/s] [2024-06-04 03:19:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
33%|███▎ | 65/195 [00:30<01:04, 2.02it/s] [2024-06-04 03:19:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
33%|███▎ | 65/195 [00:30<01:04, 2.02it/s] [2024-06-04 03:19:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (4096,), dtype: float16
33%|███▎ | 65/195 [00:30<01:04, 2.02it/s] [2024-06-04 03:19:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
33%|███▎ | 65/195 [00:30<01:04, 2.02it/s] [2024-06-04 03:19:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
33%|███▎ | 65/195 [00:30<01:04, 2.02it/s] 35%|███▍ | 68/195 [00:30<00:41, 3.08it/s] [2024-06-04 03:19:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
35%|███▍ | 68/195 [00:31<00:41, 3.08it/s] [2024-06-04 03:19:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
35%|███▍ | 68/195 [00:31<00:41, 3.08it/s] 35%|███▌ | 69/195 [00:31<00:48, 2.61it/s] [2024-06-04 03:19:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (4096,), dtype: float16
35%|███▌ | 69/195 [00:31<00:48, 2.61it/s] [2024-06-04 03:19:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
35%|███▌ | 69/195 [00:31<00:48, 2.61it/s] [2024-06-04 03:19:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
35%|███▌ | 69/195 [00:31<00:48, 2.61it/s] 36%|███▋ | 71/195 [00:31<00:34, 3.65it/s] [2024-06-04 03:19:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
36%|███▋ | 71/195 [00:31<00:34, 3.65it/s] [2024-06-04 03:19:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
36%|███▋ | 71/195 [00:31<00:34, 3.65it/s] [2024-06-04 03:19:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (4096,), dtype: float16
36%|███▋ | 71/195 [00:31<00:34, 3.65it/s] [2024-06-04 03:19:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
36%|███▋ | 71/195 [00:31<00:34, 3.65it/s] [2024-06-04 03:19:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
36%|███▋ | 71/195 [00:31<00:34, 3.65it/s] 38%|███▊ | 74/195 [00:31<00:24, 4.86it/s] [2024-06-04 03:19:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
38%|███▊ | 74/195 [00:32<00:24, 4.86it/s] [2024-06-04 03:19:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
38%|███▊ | 74/195 [00:32<00:24, 4.86it/s] 38%|███▊ | 75/195 [00:32<00:33, 3.56it/s] [2024-06-04 03:19:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (4096,), dtype: float16
38%|███▊ | 75/195 [00:32<00:33, 3.56it/s] [2024-06-04 03:19:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
38%|███▊ | 75/195 [00:32<00:33, 3.56it/s] [2024-06-04 03:19:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
38%|███▊ | 75/195 [00:32<00:33, 3.56it/s] 39%|███▉ | 77/195 [00:32<00:24, 4.79it/s] [2024-06-04 03:19:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
39%|███▉ | 77/195 [00:32<00:24, 4.79it/s] [2024-06-04 03:19:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
39%|███▉ | 77/195 [00:32<00:24, 4.79it/s] [2024-06-04 03:19:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (4096,), dtype: float16
39%|███▉ | 77/195 [00:32<00:24, 4.79it/s] [2024-06-04 03:19:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
39%|███▉ | 77/195 [00:32<00:24, 4.79it/s] [2024-06-04 03:19:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
39%|███▉ | 77/195 [00:32<00:24, 4.79it/s] 41%|████ | 80/195 [00:32<00:19, 5.95it/s] [2024-06-04 03:19:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
41%|████ | 80/195 [00:33<00:19, 5.95it/s] [2024-06-04 03:19:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
41%|████ | 80/195 [00:33<00:19, 5.95it/s] [2024-06-04 03:19:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (4096,), dtype: float16
41%|████ | 80/195 [00:33<00:19, 5.95it/s] 42%|████▏ | 82/195 [00:33<00:24, 4.69it/s] [2024-06-04 03:19:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
42%|████▏ | 82/195 [00:33<00:24, 4.69it/s] [2024-06-04 03:19:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
42%|████▏ | 82/195 [00:33<00:24, 4.69it/s] 43%|████▎ | 83/195 [00:33<00:21, 5.10it/s] [2024-06-04 03:19:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
43%|████▎ | 83/195 [00:33<00:21, 5.10it/s] [2024-06-04 03:19:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
43%|████▎ | 83/195 [00:33<00:21, 5.10it/s] [2024-06-04 03:19:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (4096,), dtype: float16
43%|████▎ | 83/195 [00:33<00:21, 5.10it/s] [2024-06-04 03:19:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
43%|████▎ | 83/195 [00:33<00:21, 5.10it/s] [2024-06-04 03:19:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
43%|████▎ | 83/195 [00:34<00:21, 5.10it/s] 44%|████▍ | 86/195 [00:34<00:17, 6.24it/s] [2024-06-04 03:19:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
44%|████▍ | 86/195 [00:34<00:17, 6.24it/s] [2024-06-04 03:19:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
44%|████▍ | 86/195 [00:34<00:17, 6.24it/s] 45%|████▍ | 87/195 [00:34<00:26, 4.12it/s] [2024-06-04 03:19:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (4096,), dtype: float16
45%|████▍ | 87/195 [00:34<00:26, 4.12it/s] [2024-06-04 03:19:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
45%|████▍ | 87/195 [00:34<00:26, 4.12it/s] [2024-06-04 03:19:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
45%|████▍ | 87/195 [00:34<00:26, 4.12it/s] 46%|████▌ | 89/195 [00:34<00:19, 5.48it/s] [2024-06-04 03:19:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
46%|████▌ | 89/195 [00:34<00:19, 5.48it/s] [2024-06-04 03:19:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
46%|████▌ | 89/195 [00:34<00:19, 5.48it/s] [2024-06-04 03:19:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (4096,), dtype: float16
46%|████▌ | 89/195 [00:34<00:19, 5.48it/s] [2024-06-04 03:19:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
46%|████▌ | 89/195 [00:35<00:19, 5.48it/s] [2024-06-04 03:19:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
46%|████▌ | 89/195 [00:35<00:19, 5.48it/s] 47%|████▋ | 92/195 [00:35<00:15, 6.52it/s] [2024-06-04 03:19:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
47%|████▋ | 92/195 [00:35<00:15, 6.52it/s] [2024-06-04 03:19:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
47%|████▋ | 92/195 [00:35<00:15, 6.52it/s] 48%|████▊ | 93/195 [00:35<00:24, 4.23it/s] [2024-06-04 03:19:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (4096,), dtype: float16
48%|████▊ | 93/195 [00:35<00:24, 4.23it/s] [2024-06-04 03:19:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
48%|████▊ | 93/195 [00:35<00:24, 4.23it/s] [2024-06-04 03:19:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
48%|████▊ | 93/195 [00:35<00:24, 4.23it/s] 49%|████▊ | 95/195 [00:35<00:17, 5.58it/s] [2024-06-04 03:19:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
49%|████▊ | 95/195 [00:35<00:17, 5.58it/s] [2024-06-04 03:19:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
49%|████▊ | 95/195 [00:35<00:17, 5.58it/s] [2024-06-04 03:19:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (4096,), dtype: float16
49%|████▊ | 95/195 [00:35<00:17, 5.58it/s] [2024-06-04 03:19:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
49%|████▊ | 95/195 [00:36<00:17, 5.58it/s] [2024-06-04 03:19:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
49%|████▊ | 95/195 [00:36<00:17, 5.58it/s] 50%|█████ | 98/195 [00:36<00:14, 6.62it/s] [2024-06-04 03:19:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
50%|█████ | 98/195 [00:36<00:14, 6.62it/s] [2024-06-04 03:19:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
50%|█████ | 98/195 [00:36<00:14, 6.62it/s] [2024-06-04 03:19:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (4096,), dtype: float16
50%|█████ | 98/195 [00:36<00:14, 6.62it/s] 51%|█████▏ | 100/195 [00:36<00:19, 4.98it/s] [2024-06-04 03:19:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
51%|█████▏ | 100/195 [00:36<00:19, 4.98it/s] [2024-06-04 03:19:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
51%|█████▏ | 100/195 [00:36<00:19, 4.98it/s] 52%|█████▏ | 101/195 [00:36<00:17, 5.38it/s] [2024-06-04 03:19:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
52%|█████▏ | 101/195 [00:37<00:17, 5.38it/s] [2024-06-04 03:19:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
52%|█████▏ | 101/195 [00:37<00:17, 5.38it/s] [2024-06-04 03:19:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (4096,), dtype: float16
52%|█████▏ | 101/195 [00:37<00:17, 5.38it/s] [2024-06-04 03:19:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
52%|█████▏ | 101/195 [00:37<00:17, 5.38it/s] [2024-06-04 03:19:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
52%|█████▏ | 101/195 [00:37<00:17, 5.38it/s] 53%|█████▎ | 104/195 [00:37<00:14, 6.49it/s] [2024-06-04 03:19:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
53%|█████▎ | 104/195 [00:37<00:14, 6.49it/s] [2024-06-04 03:20:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
53%|█████▎ | 104/195 [00:37<00:14, 6.49it/s] 54%|█████▍ | 105/195 [00:37<00:21, 4.21it/s] [2024-06-04 03:20:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (4096,), dtype: float16
54%|█████▍ | 105/195 [00:37<00:21, 4.21it/s] [2024-06-04 03:20:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
54%|█████▍ | 105/195 [00:38<00:21, 4.21it/s] [2024-06-04 03:20:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
54%|█████▍ | 105/195 [00:38<00:21, 4.21it/s] 55%|█████▍ | 107/195 [00:38<00:15, 5.58it/s] [2024-06-04 03:20:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
55%|█████▍ | 107/195 [00:38<00:15, 5.58it/s] [2024-06-04 03:20:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
55%|█████▍ | 107/195 [00:38<00:15, 5.58it/s] [2024-06-04 03:20:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (4096,), dtype: float16
55%|█████▍ | 107/195 [00:38<00:15, 5.58it/s] [2024-06-04 03:20:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
55%|█████▍ | 107/195 [00:38<00:15, 5.58it/s] [2024-06-04 03:20:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
55%|█████▍ | 107/195 [00:38<00:15, 5.58it/s] 56%|█████▋ | 110/195 [00:38<00:12, 6.63it/s] [2024-06-04 03:20:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
56%|█████▋ | 110/195 [00:38<00:12, 6.63it/s] [2024-06-04 03:20:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
56%|█████▋ | 110/195 [00:39<00:12, 6.63it/s] 57%|█████▋ | 111/195 [00:39<00:19, 4.28it/s] [2024-06-04 03:20:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (4096,), dtype: float16
57%|█████▋ | 111/195 [00:39<00:19, 4.28it/s] [2024-06-04 03:20:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
57%|█████▋ | 111/195 [00:39<00:19, 4.28it/s] [2024-06-04 03:20:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
57%|█████▋ | 111/195 [00:39<00:19, 4.28it/s] 58%|█████▊ | 113/195 [00:39<00:14, 5.64it/s] [2024-06-04 03:20:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
58%|█████▊ | 113/195 [00:39<00:14, 5.64it/s] [2024-06-04 03:20:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
58%|█████▊ | 113/195 [00:39<00:14, 5.64it/s] [2024-06-04 03:20:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (4096,), dtype: float16
58%|█████▊ | 113/195 [00:39<00:14, 5.64it/s] [2024-06-04 03:20:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
58%|█████▊ | 113/195 [00:39<00:14, 5.64it/s] [2024-06-04 03:20:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
58%|█████▊ | 113/195 [00:39<00:14, 5.64it/s] 59%|█████▉ | 116/195 [00:39<00:11, 6.63it/s] [2024-06-04 03:20:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
59%|█████▉ | 116/195 [00:40<00:11, 6.63it/s] [2024-06-04 03:20:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
59%|█████▉ | 116/195 [00:40<00:11, 6.63it/s] 60%|██████ | 117/195 [00:40<00:18, 4.26it/s] [2024-06-04 03:20:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (4096,), dtype: float16
60%|██████ | 117/195 [00:40<00:18, 4.26it/s] [2024-06-04 03:20:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
60%|██████ | 117/195 [00:40<00:18, 4.26it/s] [2024-06-04 03:20:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
60%|██████ | 117/195 [00:40<00:18, 4.26it/s] 61%|██████ | 119/195 [00:40<00:13, 5.62it/s] [2024-06-04 03:20:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
61%|██████ | 119/195 [00:40<00:13, 5.62it/s] [2024-06-04 03:20:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
61%|██████ | 119/195 [00:40<00:13, 5.62it/s] [2024-06-04 03:20:02] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Meta-Llama-3-8B-Instruct/model-00003-of-00004.safetensors
61%|██████ | 119/195 [00:40<00:13, 5.62it/s] [2024-06-04 03:20:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
61%|██████ | 119/195 [00:45<00:13, 5.62it/s] [2024-06-04 03:20:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
61%|██████ | 119/195 [00:46<00:13, 5.62it/s] 62%|██████▏ | 121/195 [00:46<01:15, 1.01s/it] [2024-06-04 03:20:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
62%|██████▏ | 121/195 [00:46<01:15, 1.01s/it] [2024-06-04 03:20:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
62%|██████▏ | 121/195 [00:46<01:15, 1.01s/it] 63%|██████▎ | 122/195 [00:46<01:04, 1.14it/s] [2024-06-04 03:20:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
63%|██████▎ | 122/195 [00:46<01:04, 1.14it/s] [2024-06-04 03:20:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
63%|██████▎ | 122/195 [00:46<01:04, 1.14it/s] [2024-06-04 03:20:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (4096,), dtype: float16
63%|██████▎ | 122/195 [00:46<01:04, 1.14it/s] [2024-06-04 03:20:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
63%|██████▎ | 122/195 [00:46<01:04, 1.14it/s] [2024-06-04 03:20:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
63%|██████▎ | 122/195 [00:46<01:04, 1.14it/s] 64%|██████▍ | 125/195 [00:46<00:40, 1.74it/s] [2024-06-04 03:20:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
64%|██████▍ | 125/195 [00:48<00:40, 1.74it/s] [2024-06-04 03:20:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
64%|██████▍ | 125/195 [00:48<00:40, 1.74it/s] 65%|██████▍ | 126/195 [00:48<00:50, 1.36it/s] [2024-06-04 03:20:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (4096,), dtype: float16
65%|██████▍ | 126/195 [00:48<00:50, 1.36it/s] [2024-06-04 03:20:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
65%|██████▍ | 126/195 [00:48<00:50, 1.36it/s] [2024-06-04 03:20:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
65%|██████▍ | 126/195 [00:48<00:50, 1.36it/s] 66%|██████▌ | 128/195 [00:48<00:35, 1.91it/s] [2024-06-04 03:20:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
66%|██████▌ | 128/195 [00:48<00:35, 1.91it/s] [2024-06-04 03:20:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
66%|██████▌ | 128/195 [00:48<00:35, 1.91it/s] [2024-06-04 03:20:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (4096,), dtype: float16
66%|██████▌ | 128/195 [00:48<00:35, 1.91it/s] [2024-06-04 03:20:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
66%|██████▌ | 128/195 [00:48<00:35, 1.91it/s] [2024-06-04 03:20:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
66%|██████▌ | 128/195 [00:48<00:35, 1.91it/s] 67%|██████▋ | 131/195 [00:48<00:22, 2.82it/s] [2024-06-04 03:20:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (4096,), dtype: float16
67%|██████▋ | 131/195 [00:48<00:22, 2.82it/s] [2024-06-04 03:20:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (4096,), dtype: float16
67%|██████▋ | 131/195 [00:48<00:22, 2.82it/s] [2024-06-04 03:20:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
67%|██████▋ | 131/195 [00:49<00:22, 2.82it/s] [2024-06-04 03:20:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
67%|██████▋ | 131/195 [00:49<00:22, 2.82it/s] 69%|██████▊ | 134/195 [00:49<00:15, 3.90it/s] [2024-06-04 03:20:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
69%|██████▊ | 134/195 [00:50<00:15, 3.90it/s] [2024-06-04 03:20:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
69%|██████▊ | 134/195 [00:50<00:15, 3.90it/s] 69%|██████▉ | 135/195 [00:50<00:25, 2.33it/s] [2024-06-04 03:20:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (4096,), dtype: float16
69%|██████▉ | 135/195 [00:50<00:25, 2.33it/s] [2024-06-04 03:20:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
69%|██████▉ | 135/195 [00:50<00:25, 2.33it/s] [2024-06-04 03:20:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
69%|██████▉ | 135/195 [00:50<00:25, 2.33it/s] 70%|███████ | 137/195 [00:50<00:18, 3.06it/s] [2024-06-04 03:20:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
70%|███████ | 137/195 [00:50<00:18, 3.06it/s] [2024-06-04 03:20:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
70%|███████ | 137/195 [00:50<00:18, 3.06it/s] [2024-06-04 03:20:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (4096,), dtype: float16
70%|███████ | 137/195 [00:50<00:18, 3.06it/s] [2024-06-04 03:20:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
70%|███████ | 137/195 [00:51<00:18, 3.06it/s] [2024-06-04 03:20:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
70%|███████ | 137/195 [00:51<00:18, 3.06it/s] 72%|███████▏ | 140/195 [00:51<00:13, 4.09it/s] [2024-06-04 03:20:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
72%|███████▏ | 140/195 [00:52<00:13, 4.09it/s] [2024-06-04 03:20:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
72%|███████▏ | 140/195 [00:52<00:13, 4.09it/s] 72%|███████▏ | 141/195 [00:52<00:20, 2.60it/s] [2024-06-04 03:20:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (4096,), dtype: float16
72%|███████▏ | 141/195 [00:52<00:20, 2.60it/s] [2024-06-04 03:20:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
72%|███████▏ | 141/195 [00:52<00:20, 2.60it/s] [2024-06-04 03:20:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
72%|███████▏ | 141/195 [00:52<00:20, 2.60it/s] 73%|███████▎ | 143/195 [00:52<00:15, 3.43it/s] [2024-06-04 03:20:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
73%|███████▎ | 143/195 [00:52<00:15, 3.43it/s] [2024-06-04 03:20:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
73%|███████▎ | 143/195 [00:52<00:15, 3.43it/s] [2024-06-04 03:20:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (4096,), dtype: float16
73%|███████▎ | 143/195 [00:52<00:15, 3.43it/s] [2024-06-04 03:20:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
73%|███████▎ | 143/195 [00:52<00:15, 3.43it/s] [2024-06-04 03:20:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
73%|███████▎ | 143/195 [00:52<00:15, 3.43it/s] 75%|███████▍ | 146/195 [00:52<00:10, 4.52it/s] [2024-06-04 03:20:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
75%|███████▍ | 146/195 [00:53<00:10, 4.52it/s] [2024-06-04 03:20:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
75%|███████▍ | 146/195 [00:53<00:10, 4.52it/s] 75%|███████▌ | 147/195 [00:53<00:15, 3.07it/s] [2024-06-04 03:20:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (4096,), dtype: float16
75%|███████▌ | 147/195 [00:53<00:15, 3.07it/s] [2024-06-04 03:20:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
75%|███████▌ | 147/195 [00:53<00:15, 3.07it/s] [2024-06-04 03:20:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
75%|███████▌ | 147/195 [00:53<00:15, 3.07it/s] 76%|███████▋ | 149/195 [00:53<00:11, 4.00it/s] [2024-06-04 03:20:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
76%|███████▋ | 149/195 [00:53<00:11, 4.00it/s] [2024-06-04 03:20:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
76%|███████▋ | 149/195 [00:53<00:11, 4.00it/s] [2024-06-04 03:20:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (4096,), dtype: float16
76%|███████▋ | 149/195 [00:53<00:11, 4.00it/s] [2024-06-04 03:20:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
76%|███████▋ | 149/195 [00:54<00:11, 4.00it/s] [2024-06-04 03:20:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
76%|███████▋ | 149/195 [00:54<00:11, 4.00it/s] 78%|███████▊ | 152/195 [00:54<00:08, 5.10it/s] [2024-06-04 03:20:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
78%|███████▊ | 152/195 [00:54<00:08, 5.10it/s] [2024-06-04 03:20:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
78%|███████▊ | 152/195 [00:55<00:08, 5.10it/s] 78%|███████▊ | 153/195 [00:55<00:12, 3.24it/s] [2024-06-04 03:20:17] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (4096,), dtype: float16
78%|███████▊ | 153/195 [00:55<00:12, 3.24it/s] [2024-06-04 03:20:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
78%|███████▊ | 153/195 [00:55<00:12, 3.24it/s] [2024-06-04 03:20:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
78%|███████▊ | 153/195 [00:55<00:12, 3.24it/s] 79%|███████▉ | 155/195 [00:55<00:09, 4.20it/s] [2024-06-04 03:20:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
79%|███████▉ | 155/195 [00:55<00:09, 4.20it/s] [2024-06-04 03:20:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
79%|███████▉ | 155/195 [00:55<00:09, 4.20it/s] [2024-06-04 03:20:17] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (4096,), dtype: float16
79%|███████▉ | 155/195 [00:55<00:09, 4.20it/s] [2024-06-04 03:20:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
79%|███████▉ | 155/195 [00:55<00:09, 4.20it/s] [2024-06-04 03:20:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
79%|███████▉ | 155/195 [00:55<00:09, 4.20it/s] 81%|████████ | 158/195 [00:55<00:06, 5.30it/s] [2024-06-04 03:20:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
81%|████████ | 158/195 [00:56<00:06, 5.30it/s] [2024-06-04 03:20:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
81%|████████ | 158/195 [00:56<00:06, 5.30it/s] 82%|████████▏ | 159/195 [00:56<00:10, 3.31it/s] [2024-06-04 03:20:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (4096,), dtype: float16
82%|████████▏ | 159/195 [00:56<00:10, 3.31it/s] [2024-06-04 03:20:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
82%|████████▏ | 159/195 [00:56<00:10, 3.31it/s] [2024-06-04 03:20:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
82%|████████▏ | 159/195 [00:56<00:10, 3.31it/s] 83%|████████▎ | 161/195 [00:56<00:07, 4.29it/s] [2024-06-04 03:20:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
83%|████████▎ | 161/195 [00:56<00:07, 4.29it/s] [2024-06-04 03:20:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
83%|████████▎ | 161/195 [00:56<00:07, 4.29it/s] [2024-06-04 03:20:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (4096,), dtype: float16
83%|████████▎ | 161/195 [00:56<00:07, 4.29it/s] [2024-06-04 03:20:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
83%|████████▎ | 161/195 [00:56<00:07, 4.29it/s] [2024-06-04 03:20:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
83%|████████▎ | 161/195 [00:56<00:07, 4.29it/s] 84%|████████▍ | 164/195 [00:56<00:05, 5.37it/s] [2024-06-04 03:20:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
84%|████████▍ | 164/195 [00:57<00:05, 5.37it/s] [2024-06-04 03:20:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
84%|████████▍ | 164/195 [00:57<00:05, 5.37it/s] 85%|████████▍ | 165/195 [00:57<00:08, 3.45it/s] [2024-06-04 03:20:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (4096,), dtype: float16
85%|████████▍ | 165/195 [00:57<00:08, 3.45it/s] [2024-06-04 03:20:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
85%|████████▍ | 165/195 [00:57<00:08, 3.45it/s] [2024-06-04 03:20:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
85%|████████▍ | 165/195 [00:57<00:08, 3.45it/s] 86%|████████▌ | 167/195 [00:57<00:06, 4.44it/s] [2024-06-04 03:20:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
86%|████████▌ | 167/195 [00:58<00:06, 4.44it/s] [2024-06-04 03:20:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
86%|████████▌ | 167/195 [00:58<00:06, 4.44it/s] [2024-06-04 03:20:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (4096,), dtype: float16
86%|████████▌ | 167/195 [00:58<00:06, 4.44it/s] [2024-06-04 03:20:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
86%|████████▌ | 167/195 [00:58<00:06, 4.44it/s] [2024-06-04 03:20:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
86%|████████▌ | 167/195 [00:58<00:06, 4.44it/s] 87%|████████▋ | 170/195 [00:58<00:04, 5.50it/s] [2024-06-04 03:20:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
87%|████████▋ | 170/195 [00:59<00:04, 5.50it/s] [2024-06-04 03:20:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
87%|████████▋ | 170/195 [00:59<00:04, 5.50it/s] 88%|████████▊ | 171/195 [00:59<00:06, 3.46it/s] [2024-06-04 03:20:21] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (4096,), dtype: float16
88%|████████▊ | 171/195 [00:59<00:06, 3.46it/s] [2024-06-04 03:20:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
88%|████████▊ | 171/195 [00:59<00:06, 3.46it/s] [2024-06-04 03:20:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
88%|████████▊ | 171/195 [00:59<00:06, 3.46it/s] 89%|████████▊ | 173/195 [00:59<00:04, 4.45it/s] [2024-06-04 03:20:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
89%|████████▊ | 173/195 [00:59<00:04, 4.45it/s] [2024-06-04 03:20:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
89%|████████▊ | 173/195 [00:59<00:04, 4.45it/s] [2024-06-04 03:20:21] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.input_layernorm.weight", shape: (4096,), dtype: float16
89%|████████▊ | 173/195 [00:59<00:04, 4.45it/s] [2024-06-04 03:20:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
89%|████████▊ | 173/195 [00:59<00:04, 4.45it/s] [2024-06-04 03:20:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
89%|████████▊ | 173/195 [00:59<00:04, 4.45it/s] 90%|█████████ | 176/195 [00:59<00:03, 5.51it/s] [2024-06-04 03:20:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
90%|█████████ | 176/195 [01:00<00:03, 5.51it/s] [2024-06-04 03:20:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
90%|█████████ | 176/195 [01:00<00:03, 5.51it/s] 91%|█████████ | 177/195 [01:00<00:04, 3.85it/s] [2024-06-04 03:20:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.post_attention_layernorm.weight", shape: (4096,), dtype: float16
91%|█████████ | 177/195 [01:00<00:04, 3.85it/s] [2024-06-04 03:20:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
91%|█████████ | 177/195 [01:00<00:04, 3.85it/s] [2024-06-04 03:20:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
91%|█████████ | 177/195 [01:00<00:04, 3.85it/s] 92%|█████████▏| 179/195 [01:00<00:03, 4.89it/s] [2024-06-04 03:20:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
92%|█████████▏| 179/195 [01:00<00:03, 4.89it/s] [2024-06-04 03:20:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
92%|█████████▏| 179/195 [01:00<00:03, 4.89it/s] [2024-06-04 03:20:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.input_layernorm.weight", shape: (4096,), dtype: float16
92%|█████████▏| 179/195 [01:00<00:03, 4.89it/s] [2024-06-04 03:20:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
92%|█████████▏| 179/195 [01:00<00:03, 4.89it/s] [2024-06-04 03:20:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
92%|█████████▏| 179/195 [01:00<00:03, 4.89it/s] 93%|█████████▎| 182/195 [01:00<00:02, 5.91it/s] [2024-06-04 03:20:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
93%|█████████▎| 182/195 [01:01<00:02, 5.91it/s] [2024-06-04 03:20:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
93%|█████████▎| 182/195 [01:01<00:02, 5.91it/s] 94%|█████████▍| 183/195 [01:01<00:03, 3.76it/s] [2024-06-04 03:20:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.post_attention_layernorm.weight", shape: (4096,), dtype: float16
94%|█████████▍| 183/195 [01:01<00:03, 3.76it/s] [2024-06-04 03:20:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
94%|█████████▍| 183/195 [01:01<00:03, 3.76it/s] [2024-06-04 03:20:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
94%|█████████▍| 183/195 [01:01<00:03, 3.76it/s] 95%|█████████▍| 185/195 [01:01<00:02, 4.80it/s] [2024-06-04 03:20:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
95%|█████████▍| 185/195 [01:01<00:02, 4.80it/s] [2024-06-04 03:20:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
95%|█████████▍| 185/195 [01:01<00:02, 4.80it/s] [2024-06-04 03:20:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.input_layernorm.weight", shape: (4096,), dtype: float16
95%|█████████▍| 185/195 [01:01<00:02, 4.80it/s] [2024-06-04 03:20:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
95%|█████████▍| 185/195 [01:02<00:02, 4.80it/s] [2024-06-04 03:20:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
95%|█████████▍| 185/195 [01:02<00:02, 4.80it/s] 96%|█████████▋| 188/195 [01:02<00:01, 5.84it/s] [2024-06-04 03:20:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
96%|█████████▋| 188/195 [01:02<00:01, 5.84it/s] [2024-06-04 03:20:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
96%|█████████▋| 188/195 [01:02<00:01, 5.84it/s] 97%|█████████▋| 189/195 [01:02<00:01, 4.04it/s] [2024-06-04 03:20:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.post_attention_layernorm.weight", shape: (4096,), dtype: float16
97%|█████████▋| 189/195 [01:02<00:01, 4.04it/s] [2024-06-04 03:20:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
97%|█████████▋| 189/195 [01:02<00:01, 4.04it/s] [2024-06-04 03:20:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
97%|█████████▋| 189/195 [01:02<00:01, 4.04it/s] 98%|█████████▊| 191/195 [01:02<00:00, 5.08it/s] [2024-06-04 03:20:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
98%|█████████▊| 191/195 [01:03<00:00, 5.08it/s] [2024-06-04 03:20:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
98%|█████████▊| 191/195 [01:03<00:00, 5.08it/s] [2024-06-04 03:20:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
98%|█████████▊| 191/195 [01:03<00:00, 5.08it/s] [2024-06-04 03:20:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
98%|█████████▊| 191/195 [01:03<00:00, 5.08it/s] 99%|█████████▉| 193/195 [01:03<00:00, 3.95it/s] [2024-06-04 03:20:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
99%|█████████▉| 193/195 [01:03<00:00, 3.95it/s] [2024-06-04 03:20:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
99%|█████████▉| 193/195 [01:03<00:00, 3.95it/s] 99%|█████████▉| 194/195 [01:03<00:00, 4.25it/s] [2024-06-04 03:20:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
99%|█████████▉| 194/195 [01:03<00:00, 4.25it/s] [2024-06-04 03:20:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
99%|█████████▉| 194/195 [01:03<00:00, 4.25it/s] 100%|██████████| 195/195 [01:03<00:00, 3.05it/s]
[2024-06-04 03:20:26] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Meta-Llama-3-8B-Instruct/model-00002-of-00004.safetensors
[2024-06-04 03:20:26] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Meta-Llama-3-8B-Instruct/model-00003-of-00004.safetensors
[2024-06-04 03:20:27] INFO stats.py:77: Time usage: HF loading: 15.891 sec; Pre-quantization mapping: 34.829 sec; Quantization: 3.112 sec
[2024-06-04 03:20:27] INFO stats.py:91: RAM usage: Peak RAM: 18.469 GB. Total bytes loaded from disk: 29.915 GB
[2024-06-04 03:20:27] INFO convert_weight.py:155: Parameter size after quantization: 3.382 GB
[2024-06-04 03:20:27] INFO convert_weight.py:160: Total parameters: 8,030,261,248
[2024-06-04 03:20:27] INFO convert_weight.py:161: Bits per parameter: 3.618
[2024-06-04 03:20:27] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q3f16_1-MLC
All finished, 100 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q3f16_1-MLC/ndarray-cache.json