Hugging Face's logo

mlc-ai
/
Llama-3-8B-Instruct-q4f32_1-MLC

mlc-llm
web-llm
Model card Files Community
Llama-3-8B-Instruct-q4f32_1-MLC / logs.txt
riczhou's picture
riczhou
Initial commit
edbaaed verified
raw
history blame contribute delete
No virus
105 kB
/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Meta-Llama-3-8B-Instruct --quantization q4f32_1 --conv-template llama-3 --output /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC
[2024-06-04 03:10:23] INFO auto_config.py:116: Found model configuration: /models/Meta-Llama-3-8B-Instruct/config.json
[2024-06-04 03:10:23] INFO auto_config.py:154: Found model type: llama. Use `--model-type` to override.
[2024-06-04 03:10:23] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (8192)
[2024-06-04 03:10:23] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
[2024-06-04 03:10:23] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-04 03:10:23] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 128000
[2024-06-04 03:10:23] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [128001, 128009]
[2024-06-04 03:10:23] INFO gen_config.py:143: [generation_config.json] Setting temperature: 0.6
[2024-06-04 03:10:23] INFO gen_config.py:143: [generation_config.json] Setting top_p: 0.9
[2024-06-04 03:10:23] INFO gen_config.py:157: Not found tokenizer config: /models/Meta-Llama-3-8B-Instruct/tokenizer.model
[2024-06-04 03:10:23] 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-q4f32_1-MLC/tokenizer.json
[2024-06-04 03:10:23] INFO gen_config.py:157: Not found tokenizer config: /models/Meta-Llama-3-8B-Instruct/vocab.json
[2024-06-04 03:10:23] INFO gen_config.py:157: Not found tokenizer config: /models/Meta-Llama-3-8B-Instruct/merges.txt
[2024-06-04 03:10:23] INFO gen_config.py:157: Not found tokenizer config: /models/Meta-Llama-3-8B-Instruct/added_tokens.json
[2024-06-04 03:10:23] 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-q4f32_1-MLC/tokenizer_config.json
[2024-06-04 03:10:23] 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 03:10:23] INFO gen_config.py:32: [System default] Setting pad_token_id: 0
[2024-06-04 03:10:23] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-04 03:10:23] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-04 03:10:23] INFO gen_config.py:32: [System default] Setting repetition_penalty: 1.0
[2024-06-04 03:10:23] INFO gen_config.py:32: [System default] Setting mean_gen_len: 128
[2024-06-04 03:10:23] INFO gen_config.py:32: [System default] Setting max_gen_len: 512
[2024-06-04 03:10:23] INFO gen_config.py:32: [System default] Setting shift_fill_factor: 0.3
[2024-06-04 03:10:23] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC/mlc-chat-config.json
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Meta-Llama-3-8B-Instruct --quantization q4f32_1 --output /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC
[2024-06-04 03:10:24] INFO auto_config.py:116: Found model configuration: /models/Meta-Llama-3-8B-Instruct/config.json
[2024-06-04 03:10:26] INFO auto_device.py:79: Found device: cuda:0
[2024-06-04 03:10:27] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-04 03:10:29] INFO auto_device.py:88: Not found device: metal:0
[2024-06-04 03:10:30] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-04 03:10:30] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-04 03:10:30] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-04 03:10:30] INFO auto_device.py:79: Found device: vulkan:3
[2024-06-04 03:10:32] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-04 03:10:32] INFO auto_device.py:35: Using device: cuda:0
[2024-06-04 03:10:32] INFO auto_weight.py:71: Finding weights in: /models/Meta-Llama-3-8B-Instruct
[2024-06-04 03:10:32] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-04 03:10:32] 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 03:10:32] 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 03:10:32] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-04 03:10:32] INFO auto_config.py:154: Found model type: llama. Use `--model-type` to override.
[2024-06-04 03:10:32] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (8192)
[2024-06-04 03:10:32] 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='q4f32_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float32', 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 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-q4f32_1-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC
0%| | 0/195 [00:00<?, ?it/s] [2024-06-04 03:10:36] 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 03:10:39] INFO group_quantization.py:217: Compiling quantize function for key: ((128256, 4096), float32, cuda, axis=1, output_transpose=False)
0%| | 0/195 [00:02<?, ?it/s] [2024-06-04 03:10:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_weight", shape: (128256, 512), dtype: uint32
0%| | 0/195 [00:03<?, ?it/s] [2024-06-04 03:10:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_scale", shape: (128256, 128), dtype: float32
0%| | 0/195 [00:04<?, ?it/s] 1%| | 1/195 [00:04<15:45, 4.87s/it] [2024-06-04 03:10:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.input_layernorm.weight", shape: (4096,), dtype: float32
1%| | 1/195 [00:04<15:45, 4.87s/it] [2024-06-04 03:10:41] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 14336), float32, cuda, axis=1, output_transpose=False)
1%| | 1/195 [00:04<15:45, 4.87s/it] [2024-06-04 03:10:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
1%| | 1/195 [00:05<15:45, 4.87s/it] [2024-06-04 03:10:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
1%| | 1/195 [00:05<15:45, 4.87s/it] 2%|▏ | 3/195 [00:05<04:49, 1.51s/it] [2024-06-04 03:10:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.post_attention_layernorm.weight", shape: (4096,), dtype: float32
2%|▏ | 3/195 [00:05<04:49, 1.51s/it] [2024-06-04 03:10:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (4096,), dtype: float32
2%|▏ | 3/195 [00:05<04:49, 1.51s/it] [2024-06-04 03:10:41] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Meta-Llama-3-8B-Instruct/model-00004-of-00004.safetensors
2%|▏ | 3/195 [00:05<04:49, 1.51s/it] [2024-06-04 03:10:41] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Meta-Llama-3-8B-Instruct/model-00001-of-00004.safetensors
2%|▏ | 3/195 [00:05<04:49, 1.51s/it] [2024-06-04 03:10:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (128256, 512), dtype: uint32
2%|▏ | 3/195 [00:10<04:49, 1.51s/it] [2024-06-04 03:10:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (128256, 128), dtype: float32
2%|▏ | 3/195 [00:11<04:49, 1.51s/it] 3%|▎ | 6/195 [00:11<05:41, 1.81s/it] [2024-06-04 03:10:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (4096,), dtype: float32
3%|▎ | 6/195 [00:11<05:41, 1.81s/it] [2024-06-04 03:10:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
3%|▎ | 6/195 [00:11<05:41, 1.81s/it] [2024-06-04 03:10:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
3%|▎ | 6/195 [00:11<05:41, 1.81s/it] 4%|▍ | 8/195 [00:11<03:38, 1.17s/it] [2024-06-04 03:10:48] INFO group_quantization.py:217: Compiling quantize function for key: ((28672, 4096), float32, cuda, axis=1, output_transpose=False)
4%|▍ | 8/195 [00:11<03:38, 1.17s/it] [2024-06-04 03:10:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
4%|▍ | 8/195 [00:12<03:38, 1.17s/it] [2024-06-04 03:10:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
4%|▍ | 8/195 [00:12<03:38, 1.17s/it] 5%|▍ | 9/195 [00:12<03:21, 1.08s/it] [2024-06-04 03:10:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (4096,), dtype: float32
5%|▍ | 9/195 [00:12<03:21, 1.08s/it] [2024-06-04 03:10:48] INFO group_quantization.py:217: Compiling quantize function for key: ((6144, 4096), float32, cuda, axis=1, output_transpose=False)
5%|▍ | 9/195 [00:12<03:21, 1.08s/it] [2024-06-04 03:10:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
5%|▍ | 9/195 [00:12<03:21, 1.08s/it] [2024-06-04 03:10:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
5%|▍ | 9/195 [00:12<03:21, 1.08s/it] 6%|▌ | 11/195 [00:12<02:20, 1.31it/s] [2024-06-04 03:10:49] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 4096), float32, cuda, axis=1, output_transpose=False)
6%|▌ | 11/195 [00:12<02:20, 1.31it/s] [2024-06-04 03:10:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
6%|▌ | 11/195 [00:13<02:20, 1.31it/s] [2024-06-04 03:10:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
6%|▌ | 11/195 [00:13<02:20, 1.31it/s] 6%|▌ | 12/195 [00:13<02:08, 1.43it/s] [2024-06-04 03:10:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (4096,), dtype: float32
6%|▌ | 12/195 [00:13<02:08, 1.43it/s] [2024-06-04 03:10:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
6%|▌ | 12/195 [00:13<02:08, 1.43it/s] [2024-06-04 03:10:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
6%|▌ | 12/195 [00:13<02:08, 1.43it/s] 7%|▋ | 14/195 [00:13<01:23, 2.16it/s] [2024-06-04 03:10:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
7%|▋ | 14/195 [00:13<01:23, 2.16it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
7%|▋ | 14/195 [00:13<01:23, 2.16it/s] 8%|▊ | 15/195 [00:13<01:17, 2.31it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (4096,), dtype: float32
8%|▊ | 15/195 [00:13<01:17, 2.31it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
8%|▊ | 15/195 [00:13<01:17, 2.31it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
8%|▊ | 15/195 [00:13<01:17, 2.31it/s] 9%|▊ | 17/195 [00:13<00:51, 3.45it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
9%|▊ | 17/195 [00:13<00:51, 3.45it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
9%|▊ | 17/195 [00:13<00:51, 3.45it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (4096,), dtype: float32
9%|▊ | 17/195 [00:13<00:51, 3.45it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
9%|▊ | 17/195 [00:13<00:51, 3.45it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
9%|▊ | 17/195 [00:14<00:51, 3.45it/s] 10%|█ | 20/195 [00:14<00:31, 5.49it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
10%|█ | 20/195 [00:14<00:31, 5.49it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
10%|█ | 20/195 [00:14<00:31, 5.49it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (4096,), dtype: float32
10%|█ | 20/195 [00:14<00:31, 5.49it/s] 11%|█▏ | 22/195 [00:14<00:30, 5.75it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
11%|█▏ | 22/195 [00:14<00:30, 5.75it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
11%|█▏ | 22/195 [00:14<00:30, 5.75it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
11%|█▏ | 22/195 [00:14<00:30, 5.75it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
11%|█▏ | 22/195 [00:14<00:30, 5.75it/s] 12%|█▏ | 24/195 [00:14<00:23, 7.26it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (4096,), dtype: float32
12%|█▏ | 24/195 [00:14<00:23, 7.26it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
12%|█▏ | 24/195 [00:14<00:23, 7.26it/s] [2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
12%|█▏ | 24/195 [00:14<00:23, 7.26it/s] 13%|█▎ | 26/195 [00:14<00:19, 8.66it/s] [2024-06-04 03:10:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
13%|█▎ | 26/195 [00:15<00:19, 8.66it/s] [2024-06-04 03:10:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
13%|█▎ | 26/195 [00:15<00:19, 8.66it/s] [2024-06-04 03:10:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (4096,), dtype: float32
13%|█▎ | 26/195 [00:15<00:19, 8.66it/s] 14%|█▍ | 28/195 [00:15<00:30, 5.49it/s] [2024-06-04 03:10:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
14%|█▍ | 28/195 [00:15<00:30, 5.49it/s] [2024-06-04 03:10:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
14%|█▍ | 28/195 [00:15<00:30, 5.49it/s] [2024-06-04 03:10:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
14%|█▍ | 28/195 [00:15<00:30, 5.49it/s] [2024-06-04 03:10:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
14%|█▍ | 28/195 [00:15<00:30, 5.49it/s] [2024-06-04 03:10:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (4096,), dtype: float32
14%|█▍ | 28/195 [00:15<00:30, 5.49it/s] [2024-06-04 03:10:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
14%|█▍ | 28/195 [00:15<00:30, 5.49it/s] [2024-06-04 03:10:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
14%|█▍ | 28/195 [00:15<00:30, 5.49it/s] 16%|█▋ | 32/195 [00:15<00:20, 7.88it/s] [2024-06-04 03:10:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
16%|█▋ | 32/195 [00:15<00:20, 7.88it/s] [2024-06-04 03:10:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
16%|█▋ | 32/195 [00:16<00:20, 7.88it/s] [2024-06-04 03:10:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (4096,), dtype: float32
16%|█▋ | 32/195 [00:16<00:20, 7.88it/s] 17%|█▋ | 34/195 [00:16<00:27, 5.81it/s] [2024-06-04 03:10:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
17%|█▋ | 34/195 [00:16<00:27, 5.81it/s] [2024-06-04 03:10:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
17%|█▋ | 34/195 [00:16<00:27, 5.81it/s] [2024-06-04 03:10:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
17%|█▋ | 34/195 [00:16<00:27, 5.81it/s] [2024-06-04 03:10:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
17%|█▋ | 34/195 [00:16<00:27, 5.81it/s] 18%|█▊ | 36/195 [00:16<00:22, 7.04it/s] [2024-06-04 03:10:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (4096,), dtype: float32
18%|█▊ | 36/195 [00:16<00:22, 7.04it/s] [2024-06-04 03:10:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
18%|█▊ | 36/195 [00:16<00:22, 7.04it/s] [2024-06-04 03:10:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
18%|█▊ | 36/195 [00:16<00:22, 7.04it/s] 19%|█▉ | 38/195 [00:16<00:18, 8.32it/s] [2024-06-04 03:10:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
19%|█▉ | 38/195 [00:17<00:18, 8.32it/s] [2024-06-04 03:10:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
19%|█▉ | 38/195 [00:17<00:18, 8.32it/s] [2024-06-04 03:10:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (4096,), dtype: float32
19%|█▉ | 38/195 [00:17<00:18, 8.32it/s] 21%|██ | 40/195 [00:17<00:30, 5.07it/s] [2024-06-04 03:10:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
21%|██ | 40/195 [00:17<00:30, 5.07it/s] [2024-06-04 03:10:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
21%|██ | 40/195 [00:17<00:30, 5.07it/s] [2024-06-04 03:10:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
21%|██ | 40/195 [00:17<00:30, 5.07it/s] [2024-06-04 03:10:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
21%|██ | 40/195 [00:17<00:30, 5.07it/s] 22%|██▏ | 42/195 [00:17<00:24, 6.28it/s] [2024-06-04 03:10:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (4096,), dtype: float32
22%|██▏ | 42/195 [00:17<00:24, 6.28it/s] [2024-06-04 03:10:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
22%|██▏ | 42/195 [00:17<00:24, 6.28it/s] [2024-06-04 03:10:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
22%|██▏ | 42/195 [00:17<00:24, 6.28it/s] 23%|██▎ | 44/195 [00:17<00:19, 7.66it/s] [2024-06-04 03:10:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
23%|██▎ | 44/195 [00:17<00:19, 7.66it/s] [2024-06-04 03:10:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
23%|██▎ | 44/195 [00:18<00:19, 7.66it/s] [2024-06-04 03:10:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (4096,), dtype: float32
23%|██▎ | 44/195 [00:18<00:19, 7.66it/s] 24%|██▎ | 46/195 [00:18<00:28, 5.14it/s] [2024-06-04 03:10:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
24%|██▎ | 46/195 [00:18<00:28, 5.14it/s] [2024-06-04 03:10:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
24%|██▎ | 46/195 [00:18<00:28, 5.14it/s] [2024-06-04 03:10:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
24%|██▎ | 46/195 [00:18<00:28, 5.14it/s] [2024-06-04 03:10:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
24%|██▎ | 46/195 [00:18<00:28, 5.14it/s] 25%|██▍ | 48/195 [00:18<00:22, 6.54it/s] [2024-06-04 03:10:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (4096,), dtype: float32
25%|██▍ | 48/195 [00:18<00:22, 6.54it/s] [2024-06-04 03:10:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
25%|██▍ | 48/195 [00:18<00:22, 6.54it/s] [2024-06-04 03:10:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
25%|██▍ | 48/195 [00:18<00:22, 6.54it/s] 26%|██▌ | 50/195 [00:18<00:18, 7.86it/s] [2024-06-04 03:10:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
26%|██▌ | 50/195 [00:19<00:18, 7.86it/s] [2024-06-04 03:10:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
26%|██▌ | 50/195 [00:19<00:18, 7.86it/s] [2024-06-04 03:10:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (4096,), dtype: float32
26%|██▌ | 50/195 [00:19<00:18, 7.86it/s] 27%|██▋ | 52/195 [00:19<00:32, 4.40it/s] [2024-06-04 03:10:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
27%|██▋ | 52/195 [00:19<00:32, 4.40it/s] [2024-06-04 03:10:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
27%|██▋ | 52/195 [00:19<00:32, 4.40it/s] [2024-06-04 03:10:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
27%|██▋ | 52/195 [00:19<00:32, 4.40it/s] [2024-06-04 03:10:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
27%|██▋ | 52/195 [00:19<00:32, 4.40it/s] [2024-06-04 03:10:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (4096,), dtype: float32
27%|██▋ | 52/195 [00:19<00:32, 4.40it/s] [2024-06-04 03:10:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
27%|██▋ | 52/195 [00:19<00:32, 4.40it/s] [2024-06-04 03:10:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
27%|██▋ | 52/195 [00:19<00:32, 4.40it/s] 29%|██▊ | 56/195 [00:19<00:21, 6.57it/s] [2024-06-04 03:10:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
29%|██▊ | 56/195 [00:20<00:21, 6.57it/s] [2024-06-04 03:10:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
29%|██▊ | 56/195 [00:20<00:21, 6.57it/s] [2024-06-04 03:10:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (4096,), dtype: float32
29%|██▊ | 56/195 [00:20<00:21, 6.57it/s] 30%|██▉ | 58/195 [00:20<00:30, 4.43it/s] [2024-06-04 03:10:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
30%|██▉ | 58/195 [00:20<00:30, 4.43it/s] [2024-06-04 03:10:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
30%|██▉ | 58/195 [00:20<00:30, 4.43it/s] [2024-06-04 03:10:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
30%|██▉ | 58/195 [00:20<00:30, 4.43it/s] [2024-06-04 03:10:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
30%|██▉ | 58/195 [00:20<00:30, 4.43it/s] 31%|███ | 60/195 [00:20<00:24, 5.47it/s] [2024-06-04 03:10:56] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Meta-Llama-3-8B-Instruct/model-00001-of-00004.safetensors
31%|███ | 60/195 [00:20<00:24, 5.47it/s] [2024-06-04 03:10:57] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Meta-Llama-3-8B-Instruct/model-00002-of-00004.safetensors
31%|███ | 60/195 [00:21<00:24, 5.47it/s] [2024-06-04 03:11:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (4096,), dtype: float32
31%|███ | 60/195 [00:25<00:24, 5.47it/s] [2024-06-04 03:11:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
31%|███ | 60/195 [00:25<00:24, 5.47it/s] [2024-06-04 03:11:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
31%|███ | 60/195 [00:25<00:24, 5.47it/s] 32%|███▏ | 62/195 [00:25<01:40, 1.32it/s] [2024-06-04 03:11:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
32%|███▏ | 62/195 [00:26<01:40, 1.32it/s] [2024-06-04 03:11:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
32%|███▏ | 62/195 [00:26<01:40, 1.32it/s] 32%|███▏ | 63/195 [00:26<01:54, 1.15it/s] [2024-06-04 03:11:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (4096,), dtype: float32
32%|███▏ | 63/195 [00:26<01:54, 1.15it/s] [2024-06-04 03:11:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
32%|███▏ | 63/195 [00:26<01:54, 1.15it/s] [2024-06-04 03:11:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
32%|███▏ | 63/195 [00:26<01:54, 1.15it/s] 33%|███▎ | 65/195 [00:26<01:19, 1.63it/s] [2024-06-04 03:11:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
33%|███▎ | 65/195 [00:26<01:19, 1.63it/s] [2024-06-04 03:11:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
33%|███▎ | 65/195 [00:26<01:19, 1.63it/s] [2024-06-04 03:11:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (4096,), dtype: float32
33%|███▎ | 65/195 [00:26<01:19, 1.63it/s] [2024-06-04 03:11:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
33%|███▎ | 65/195 [00:26<01:19, 1.63it/s] [2024-06-04 03:11:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
33%|███▎ | 65/195 [00:26<01:19, 1.63it/s] 35%|███▍ | 68/195 [00:26<00:50, 2.50it/s] [2024-06-04 03:11:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
35%|███▍ | 68/195 [00:28<00:50, 2.50it/s] [2024-06-04 03:11:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
35%|███▍ | 68/195 [00:28<00:50, 2.50it/s] [2024-06-04 03:11:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (4096,), dtype: float32
35%|███▍ | 68/195 [00:28<00:50, 2.50it/s] 36%|███▌ | 70/195 [00:28<00:58, 2.14it/s] [2024-06-04 03:11:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
36%|███▌ | 70/195 [00:28<00:58, 2.14it/s] [2024-06-04 03:11:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
36%|███▌ | 70/195 [00:28<00:58, 2.14it/s] [2024-06-04 03:11:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
36%|███▌ | 70/195 [00:28<00:58, 2.14it/s] [2024-06-04 03:11:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
36%|███▌ | 70/195 [00:28<00:58, 2.14it/s] 37%|███▋ | 72/195 [00:28<00:43, 2.85it/s] [2024-06-04 03:11:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (4096,), dtype: float32
37%|███▋ | 72/195 [00:28<00:43, 2.85it/s] [2024-06-04 03:11:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
37%|███▋ | 72/195 [00:28<00:43, 2.85it/s] [2024-06-04 03:11:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
37%|███▋ | 72/195 [00:28<00:43, 2.85it/s] 38%|███▊ | 74/195 [00:28<00:32, 3.69it/s] [2024-06-04 03:11:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
38%|███▊ | 74/195 [00:29<00:32, 3.69it/s] [2024-06-04 03:11:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
38%|███▊ | 74/195 [00:29<00:32, 3.69it/s] [2024-06-04 03:11:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (4096,), dtype: float32
38%|███▊ | 74/195 [00:29<00:32, 3.69it/s] 39%|███▉ | 76/195 [00:29<00:41, 2.89it/s] [2024-06-04 03:11:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
39%|███▉ | 76/195 [00:29<00:41, 2.89it/s] [2024-06-04 03:11:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
39%|███▉ | 76/195 [00:29<00:41, 2.89it/s] [2024-06-04 03:11:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
39%|███▉ | 76/195 [00:29<00:41, 2.89it/s] [2024-06-04 03:11:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
39%|███▉ | 76/195 [00:29<00:41, 2.89it/s] [2024-06-04 03:11:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (4096,), dtype: float32
39%|███▉ | 76/195 [00:29<00:41, 2.89it/s] [2024-06-04 03:11:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
39%|███▉ | 76/195 [00:29<00:41, 2.89it/s] [2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
39%|███▉ | 76/195 [00:29<00:41, 2.89it/s] 41%|████ | 80/195 [00:29<00:25, 4.54it/s] [2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
41%|████ | 80/195 [00:30<00:25, 4.54it/s] [2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
41%|████ | 80/195 [00:30<00:25, 4.54it/s] [2024-06-04 03:11:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (4096,), dtype: float32
41%|████ | 80/195 [00:30<00:25, 4.54it/s] 42%|████▏ | 82/195 [00:30<00:23, 4.72it/s] [2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
42%|████▏ | 82/195 [00:30<00:23, 4.72it/s] [2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
42%|████▏ | 82/195 [00:30<00:23, 4.72it/s] [2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
42%|████▏ | 82/195 [00:30<00:23, 4.72it/s] [2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
42%|████▏ | 82/195 [00:30<00:23, 4.72it/s] 43%|████▎ | 84/195 [00:30<00:19, 5.79it/s] [2024-06-04 03:11:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (4096,), dtype: float32
43%|████▎ | 84/195 [00:30<00:19, 5.79it/s] [2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
43%|████▎ | 84/195 [00:30<00:19, 5.79it/s] [2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
43%|████▎ | 84/195 [00:30<00:19, 5.79it/s] 44%|████▍ | 86/195 [00:30<00:15, 6.91it/s] [2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
44%|████▍ | 86/195 [00:30<00:15, 6.91it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
44%|████▍ | 86/195 [00:30<00:15, 6.91it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (4096,), dtype: float32
44%|████▍ | 86/195 [00:30<00:15, 6.91it/s] 45%|████▌ | 88/195 [00:30<00:16, 6.49it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
45%|████▌ | 88/195 [00:30<00:16, 6.49it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
45%|████▌ | 88/195 [00:30<00:16, 6.49it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
45%|████▌ | 88/195 [00:30<00:16, 6.49it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
45%|████▌ | 88/195 [00:30<00:16, 6.49it/s] 46%|████▌ | 90/195 [00:30<00:13, 7.68it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (4096,), dtype: float32
46%|████▌ | 90/195 [00:30<00:13, 7.68it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
46%|████▌ | 90/195 [00:31<00:13, 7.68it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
46%|████▌ | 90/195 [00:31<00:13, 7.68it/s] 47%|████▋ | 92/195 [00:31<00:11, 8.93it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
47%|████▋ | 92/195 [00:31<00:11, 8.93it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
47%|████▋ | 92/195 [00:31<00:11, 8.93it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (4096,), dtype: float32
47%|████▋ | 92/195 [00:31<00:11, 8.93it/s] 48%|████▊ | 94/195 [00:31<00:13, 7.71it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
48%|████▊ | 94/195 [00:31<00:13, 7.71it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
48%|████▊ | 94/195 [00:31<00:13, 7.71it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
48%|████▊ | 94/195 [00:31<00:13, 7.71it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
48%|████▊ | 94/195 [00:31<00:13, 7.71it/s] 49%|████▉ | 96/195 [00:31<00:10, 9.25it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (4096,), dtype: float32
49%|████▉ | 96/195 [00:31<00:10, 9.25it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
49%|████▉ | 96/195 [00:31<00:10, 9.25it/s] [2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
49%|████▉ | 96/195 [00:31<00:10, 9.25it/s] 50%|█████ | 98/195 [00:31<00:09, 10.19it/s] [2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
50%|█████ | 98/195 [00:31<00:09, 10.19it/s] [2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
50%|█████ | 98/195 [00:32<00:09, 10.19it/s] [2024-06-04 03:11:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (4096,), dtype: float32
50%|█████ | 98/195 [00:32<00:09, 10.19it/s] 51%|█████▏ | 100/195 [00:32<00:12, 7.84it/s] [2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
51%|█████▏ | 100/195 [00:32<00:12, 7.84it/s] [2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
51%|█████▏ | 100/195 [00:32<00:12, 7.84it/s] [2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
51%|█████▏ | 100/195 [00:32<00:12, 7.84it/s] [2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
51%|█████▏ | 100/195 [00:32<00:12, 7.84it/s] [2024-06-04 03:11:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (4096,), dtype: float32
51%|█████▏ | 100/195 [00:32<00:12, 7.84it/s] [2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
51%|█████▏ | 100/195 [00:32<00:12, 7.84it/s] [2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
51%|█████▏ | 100/195 [00:32<00:12, 7.84it/s] 53%|█████▎ | 104/195 [00:32<00:09, 9.93it/s] [2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
53%|█████▎ | 104/195 [00:32<00:09, 9.93it/s] [2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
53%|█████▎ | 104/195 [00:32<00:09, 9.93it/s] [2024-06-04 03:11:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (4096,), dtype: float32
53%|█████▎ | 104/195 [00:32<00:09, 9.93it/s] 54%|█████▍ | 106/195 [00:32<00:10, 8.43it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
54%|█████▍ | 106/195 [00:32<00:10, 8.43it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
54%|█████▍ | 106/195 [00:32<00:10, 8.43it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
54%|█████▍ | 106/195 [00:32<00:10, 8.43it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
54%|█████▍ | 106/195 [00:32<00:10, 8.43it/s] 55%|█████▌ | 108/195 [00:32<00:09, 9.65it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (4096,), dtype: float32
55%|█████▌ | 108/195 [00:32<00:09, 9.65it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
55%|█████▌ | 108/195 [00:32<00:09, 9.65it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
55%|█████▌ | 108/195 [00:32<00:09, 9.65it/s] 56%|█████▋ | 110/195 [00:33<00:07, 10.66it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
56%|█████▋ | 110/195 [00:33<00:07, 10.66it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
56%|█████▋ | 110/195 [00:33<00:07, 10.66it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (4096,), dtype: float32
56%|█████▋ | 110/195 [00:33<00:07, 10.66it/s] 57%|█████▋ | 112/195 [00:33<00:09, 8.60it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
57%|█████▋ | 112/195 [00:33<00:09, 8.60it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
57%|█████▋ | 112/195 [00:33<00:09, 8.60it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
57%|█████▋ | 112/195 [00:33<00:09, 8.60it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
57%|█████▋ | 112/195 [00:33<00:09, 8.60it/s] 58%|█████▊ | 114/195 [00:33<00:08, 9.72it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (4096,), dtype: float32
58%|█████▊ | 114/195 [00:33<00:08, 9.72it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
58%|█████▊ | 114/195 [00:33<00:08, 9.72it/s] [2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
58%|█████▊ | 114/195 [00:33<00:08, 9.72it/s] 59%|█████▉ | 116/195 [00:33<00:07, 10.80it/s] [2024-06-04 03:11:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
59%|█████▉ | 116/195 [00:33<00:07, 10.80it/s] [2024-06-04 03:11:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
59%|█████▉ | 116/195 [00:33<00:07, 10.80it/s] [2024-06-04 03:11:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (4096,), dtype: float32
59%|█████▉ | 116/195 [00:33<00:07, 10.80it/s] 61%|██████ | 118/195 [00:33<00:08, 8.64it/s] [2024-06-04 03:11:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
61%|██████ | 118/195 [00:34<00:08, 8.64it/s] [2024-06-04 03:11:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
61%|██████ | 118/195 [00:34<00:08, 8.64it/s] [2024-06-04 03:11:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
61%|██████ | 118/195 [00:34<00:08, 8.64it/s] [2024-06-04 03:11:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
61%|██████ | 118/195 [00:34<00:08, 8.64it/s] 62%|██████▏ | 120/195 [00:34<00:07, 10.18it/s] [2024-06-04 03:11:10] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Meta-Llama-3-8B-Instruct/model-00003-of-00004.safetensors
62%|██████▏ | 120/195 [00:34<00:07, 10.18it/s] [2024-06-04 03:11:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
62%|██████▏ | 120/195 [00:39<00:07, 10.18it/s] [2024-06-04 03:11:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
62%|██████▏ | 120/195 [00:39<00:07, 10.18it/s] [2024-06-04 03:11:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
62%|██████▏ | 120/195 [00:40<00:07, 10.18it/s] [2024-06-04 03:11:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
62%|██████▏ | 120/195 [00:40<00:07, 10.18it/s] 63%|██████▎ | 122/195 [00:40<01:10, 1.04it/s] [2024-06-04 03:11:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
63%|██████▎ | 122/195 [00:40<01:10, 1.04it/s] [2024-06-04 03:11:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
63%|██████▎ | 122/195 [00:40<01:10, 1.04it/s] [2024-06-04 03:11:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (4096,), dtype: float32
63%|██████▎ | 122/195 [00:40<01:10, 1.04it/s] [2024-06-04 03:11:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
63%|██████▎ | 122/195 [00:40<01:10, 1.04it/s] [2024-06-04 03:11:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
63%|██████▎ | 122/195 [00:40<01:10, 1.04it/s] 64%|██████▍ | 125/195 [00:40<00:44, 1.58it/s] [2024-06-04 03:11:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
64%|██████▍ | 125/195 [00:41<00:44, 1.58it/s] [2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
64%|██████▍ | 125/195 [00:41<00:44, 1.58it/s] 65%|██████▍ | 126/195 [00:41<00:52, 1.33it/s] [2024-06-04 03:11:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (4096,), dtype: float32
65%|██████▍ | 126/195 [00:41<00:52, 1.33it/s] [2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
65%|██████▍ | 126/195 [00:41<00:52, 1.33it/s] [2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
65%|██████▍ | 126/195 [00:41<00:52, 1.33it/s] [2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
65%|██████▍ | 126/195 [00:41<00:52, 1.33it/s] [2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
65%|██████▍ | 126/195 [00:41<00:52, 1.33it/s] [2024-06-04 03:11:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (4096,), dtype: float32
65%|██████▍ | 126/195 [00:41<00:52, 1.33it/s] [2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
65%|██████▍ | 126/195 [00:41<00:52, 1.33it/s] [2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
65%|██████▍ | 126/195 [00:42<00:52, 1.33it/s] 67%|██████▋ | 131/195 [00:42<00:24, 2.60it/s] [2024-06-04 03:11:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (4096,), dtype: float32
67%|██████▋ | 131/195 [00:42<00:24, 2.60it/s] [2024-06-04 03:11:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (4096,), dtype: float32
67%|██████▋ | 131/195 [00:42<00:24, 2.60it/s] [2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
67%|██████▋ | 131/195 [00:42<00:24, 2.60it/s] [2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
67%|██████▋ | 131/195 [00:42<00:24, 2.60it/s] 69%|██████▊ | 134/195 [00:42<00:17, 3.56it/s] [2024-06-04 03:11:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
69%|██████▊ | 134/195 [00:43<00:17, 3.56it/s] [2024-06-04 03:11:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
69%|██████▊ | 134/195 [00:43<00:17, 3.56it/s] [2024-06-04 03:11:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (4096,), dtype: float32
69%|██████▊ | 134/195 [00:43<00:17, 3.56it/s] 70%|██████▉ | 136/195 [00:43<00:19, 3.04it/s] [2024-06-04 03:11:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
70%|██████▉ | 136/195 [00:43<00:19, 3.04it/s] [2024-06-04 03:11:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
70%|██████▉ | 136/195 [00:43<00:19, 3.04it/s] [2024-06-04 03:11:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
70%|██████▉ | 136/195 [00:43<00:19, 3.04it/s] [2024-06-04 03:11:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
70%|██████▉ | 136/195 [00:43<00:19, 3.04it/s] 71%|███████ | 138/195 [00:43<00:14, 3.81it/s] [2024-06-04 03:11:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (4096,), dtype: float32
71%|███████ | 138/195 [00:43<00:14, 3.81it/s] [2024-06-04 03:11:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
71%|███████ | 138/195 [00:43<00:14, 3.81it/s] [2024-06-04 03:11:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
71%|███████ | 138/195 [00:43<00:14, 3.81it/s] 72%|███████▏ | 140/195 [00:43<00:11, 4.72it/s] [2024-06-04 03:11:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
72%|███████▏ | 140/195 [00:44<00:11, 4.72it/s] [2024-06-04 03:11:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
72%|███████▏ | 140/195 [00:44<00:11, 4.72it/s] [2024-06-04 03:11:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (4096,), dtype: float32
72%|███████▏ | 140/195 [00:44<00:11, 4.72it/s] 73%|███████▎ | 142/195 [00:44<00:15, 3.51it/s] [2024-06-04 03:11:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
73%|███████▎ | 142/195 [00:44<00:15, 3.51it/s] [2024-06-04 03:11:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
73%|███████▎ | 142/195 [00:44<00:15, 3.51it/s] 73%|███████▎ | 143/195 [00:44<00:13, 3.88it/s] [2024-06-04 03:11:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
73%|███████▎ | 143/195 [00:44<00:13, 3.88it/s] [2024-06-04 03:11:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
73%|███████▎ | 143/195 [00:44<00:13, 3.88it/s] [2024-06-04 03:11:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (4096,), dtype: float32
73%|███████▎ | 143/195 [00:44<00:13, 3.88it/s] [2024-06-04 03:11:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
73%|███████▎ | 143/195 [00:44<00:13, 3.88it/s] [2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
73%|███████▎ | 143/195 [00:44<00:13, 3.88it/s] 75%|███████▍ | 146/195 [00:44<00:08, 5.71it/s] [2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
75%|███████▍ | 146/195 [00:45<00:08, 5.71it/s] [2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
75%|███████▍ | 146/195 [00:45<00:08, 5.71it/s] [2024-06-04 03:11:21] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (4096,), dtype: float32
75%|███████▍ | 146/195 [00:45<00:08, 5.71it/s] 76%|███████▌ | 148/195 [00:45<00:09, 4.83it/s] [2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
76%|███████▌ | 148/195 [00:45<00:09, 4.83it/s] [2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
76%|███████▌ | 148/195 [00:45<00:09, 4.83it/s] [2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
76%|███████▌ | 148/195 [00:45<00:09, 4.83it/s] [2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
76%|███████▌ | 148/195 [00:45<00:09, 4.83it/s] 77%|███████▋ | 150/195 [00:45<00:07, 6.07it/s] [2024-06-04 03:11:21] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (4096,), dtype: float32
77%|███████▋ | 150/195 [00:45<00:07, 6.07it/s] [2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
77%|███████▋ | 150/195 [00:45<00:07, 6.07it/s] [2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
77%|███████▋ | 150/195 [00:45<00:07, 6.07it/s] 78%|███████▊ | 152/195 [00:45<00:05, 7.25it/s] [2024-06-04 03:11:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
78%|███████▊ | 152/195 [00:46<00:05, 7.25it/s] [2024-06-04 03:11:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
78%|███████▊ | 152/195 [00:46<00:05, 7.25it/s] [2024-06-04 03:11:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (4096,), dtype: float32
78%|███████▊ | 152/195 [00:46<00:05, 7.25it/s] 79%|███████▉ | 154/195 [00:46<00:07, 5.27it/s] [2024-06-04 03:11:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
79%|███████▉ | 154/195 [00:46<00:07, 5.27it/s] [2024-06-04 03:11:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
79%|███████▉ | 154/195 [00:46<00:07, 5.27it/s] [2024-06-04 03:11:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
79%|███████▉ | 154/195 [00:46<00:07, 5.27it/s] [2024-06-04 03:11:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
79%|███████▉ | 154/195 [00:46<00:07, 5.27it/s] [2024-06-04 03:11:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (4096,), dtype: float32
79%|███████▉ | 154/195 [00:46<00:07, 5.27it/s] [2024-06-04 03:11:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
79%|███████▉ | 154/195 [00:46<00:07, 5.27it/s] [2024-06-04 03:11:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
79%|███████▉ | 154/195 [00:46<00:07, 5.27it/s] 81%|████████ | 158/195 [00:46<00:05, 7.38it/s] [2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
81%|████████ | 158/195 [00:46<00:05, 7.38it/s] [2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
81%|████████ | 158/195 [00:47<00:05, 7.38it/s] [2024-06-04 03:11:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (4096,), dtype: float32
81%|████████ | 158/195 [00:47<00:05, 7.38it/s] 82%|████████▏ | 160/195 [00:47<00:06, 5.51it/s] [2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
82%|████████▏ | 160/195 [00:47<00:06, 5.51it/s] [2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
82%|████████▏ | 160/195 [00:47<00:06, 5.51it/s] [2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
82%|████████▏ | 160/195 [00:47<00:06, 5.51it/s] [2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
82%|████████▏ | 160/195 [00:47<00:06, 5.51it/s] 83%|████████▎ | 162/195 [00:47<00:04, 6.65it/s] [2024-06-04 03:11:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (4096,), dtype: float32
83%|████████▎ | 162/195 [00:47<00:04, 6.65it/s] [2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
83%|████████▎ | 162/195 [00:47<00:04, 6.65it/s] [2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
83%|████████▎ | 162/195 [00:47<00:04, 6.65it/s] 84%|████████▍ | 164/195 [00:47<00:03, 7.83it/s] [2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
84%|████████▍ | 164/195 [00:47<00:03, 7.83it/s] [2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
84%|████████▍ | 164/195 [00:47<00:03, 7.83it/s] [2024-06-04 03:11:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (4096,), dtype: float32
84%|████████▍ | 164/195 [00:47<00:03, 7.83it/s] 85%|████████▌ | 166/195 [00:47<00:04, 6.25it/s] [2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
85%|████████▌ | 166/195 [00:47<00:04, 6.25it/s] [2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
85%|████████▌ | 166/195 [00:47<00:04, 6.25it/s] 86%|████████▌ | 167/195 [00:48<00:04, 6.55it/s] [2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
86%|████████▌ | 167/195 [00:48<00:04, 6.55it/s] [2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
86%|████████▌ | 167/195 [00:48<00:04, 6.55it/s] [2024-06-04 03:11:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (4096,), dtype: float32
86%|████████▌ | 167/195 [00:48<00:04, 6.55it/s] [2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
86%|████████▌ | 167/195 [00:48<00:04, 6.55it/s] [2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
86%|████████▌ | 167/195 [00:48<00:04, 6.55it/s] 87%|████████▋ | 170/195 [00:48<00:02, 8.93it/s] [2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
87%|████████▋ | 170/195 [00:48<00:02, 8.93it/s] [2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
87%|████████▋ | 170/195 [00:48<00:02, 8.93it/s] [2024-06-04 03:11:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (4096,), dtype: float32
87%|████████▋ | 170/195 [00:48<00:02, 8.93it/s] 88%|████████▊ | 172/195 [00:48<00:03, 6.43it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
88%|████████▊ | 172/195 [00:48<00:03, 6.43it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
88%|████████▊ | 172/195 [00:48<00:03, 6.43it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
88%|████████▊ | 172/195 [00:48<00:03, 6.43it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
88%|████████▊ | 172/195 [00:48<00:03, 6.43it/s] 89%|████████▉ | 174/195 [00:48<00:02, 7.88it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.input_layernorm.weight", shape: (4096,), dtype: float32
89%|████████▉ | 174/195 [00:48<00:02, 7.88it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
89%|████████▉ | 174/195 [00:48<00:02, 7.88it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
89%|████████▉ | 174/195 [00:48<00:02, 7.88it/s] 90%|█████████ | 176/195 [00:48<00:02, 8.98it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
90%|█████████ | 176/195 [00:49<00:02, 8.98it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
90%|█████████ | 176/195 [00:49<00:02, 8.98it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.post_attention_layernorm.weight", shape: (4096,), dtype: float32
90%|█████████ | 176/195 [00:49<00:02, 8.98it/s] 91%|█████████▏| 178/195 [00:49<00:02, 6.64it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
91%|█████████▏| 178/195 [00:49<00:02, 6.64it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
91%|█████████▏| 178/195 [00:49<00:02, 6.64it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
91%|█████████▏| 178/195 [00:49<00:02, 6.64it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
91%|█████████▏| 178/195 [00:49<00:02, 6.64it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.input_layernorm.weight", shape: (4096,), dtype: float32
91%|█████████▏| 178/195 [00:49<00:02, 6.64it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
91%|█████████▏| 178/195 [00:49<00:02, 6.64it/s] [2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
91%|█████████▏| 178/195 [00:49<00:02, 6.64it/s] 93%|█████████▎| 182/195 [00:49<00:01, 8.75it/s] [2024-06-04 03:11:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
93%|█████████▎| 182/195 [00:50<00:01, 8.75it/s] [2024-06-04 03:11:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
93%|█████████▎| 182/195 [00:50<00:01, 8.75it/s] [2024-06-04 03:11:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.post_attention_layernorm.weight", shape: (4096,), dtype: float32
93%|█████████▎| 182/195 [00:50<00:01, 8.75it/s] 94%|█████████▍| 184/195 [00:50<00:01, 6.68it/s] [2024-06-04 03:11:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
94%|█████████▍| 184/195 [00:50<00:01, 6.68it/s] [2024-06-04 03:11:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
94%|█████████▍| 184/195 [00:50<00:01, 6.68it/s] [2024-06-04 03:11:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
94%|█████████▍| 184/195 [00:50<00:01, 6.68it/s] [2024-06-04 03:11:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
94%|█████████▍| 184/195 [00:50<00:01, 6.68it/s] 95%|█████████▌| 186/195 [00:50<00:01, 7.90it/s] [2024-06-04 03:11:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.input_layernorm.weight", shape: (4096,), dtype: float32
95%|█████████▌| 186/195 [00:50<00:01, 7.90it/s] [2024-06-04 03:11:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
95%|█████████▌| 186/195 [00:50<00:01, 7.90it/s] [2024-06-04 03:11:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
95%|█████████▌| 186/195 [00:50<00:01, 7.90it/s] 96%|█████████▋| 188/195 [00:50<00:00, 9.03it/s] [2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
96%|█████████▋| 188/195 [00:50<00:00, 9.03it/s] [2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
96%|█████████▋| 188/195 [00:50<00:00, 9.03it/s] [2024-06-04 03:11:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.post_attention_layernorm.weight", shape: (4096,), dtype: float32
96%|█████████▋| 188/195 [00:50<00:00, 9.03it/s] 97%|█████████▋| 190/195 [00:50<00:00, 7.15it/s] [2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
97%|█████████▋| 190/195 [00:51<00:00, 7.15it/s] [2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
97%|█████████▋| 190/195 [00:51<00:00, 7.15it/s] 98%|█████████▊| 191/195 [00:51<00:00, 7.35it/s] [2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
98%|█████████▊| 191/195 [00:51<00:00, 7.35it/s] [2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
98%|█████████▊| 191/195 [00:51<00:00, 7.35it/s] [2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
98%|█████████▊| 191/195 [00:51<00:00, 7.35it/s] [2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
98%|█████████▊| 191/195 [00:51<00:00, 7.35it/s] 99%|█████████▉| 193/195 [00:51<00:00, 6.55it/s] [2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
99%|█████████▉| 193/195 [00:51<00:00, 6.55it/s] [2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
99%|█████████▉| 193/195 [00:51<00:00, 6.55it/s] [2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
99%|█████████▉| 193/195 [00:51<00:00, 6.55it/s] [2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
99%|█████████▉| 193/195 [00:51<00:00, 6.55it/s] 100%|██████████| 195/195 [00:51<00:00, 7.88it/s] 100%|██████████| 195/195 [00:51<00:00, 3.78it/s]
[2024-06-04 03:11:27] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Meta-Llama-3-8B-Instruct/model-00002-of-00004.safetensors
[2024-06-04 03:11:28] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Meta-Llama-3-8B-Instruct/model-00003-of-00004.safetensors
[2024-06-04 03:11:28] INFO stats.py:77: Time usage: HF loading: 15.651 sec; Pre-quantization mapping: 17.726 sec; Quantization: 3.229 sec
[2024-06-04 03:11:28] INFO stats.py:91: RAM usage: Peak RAM: 18.469 GB. Total bytes loaded from disk: 29.915 GB
[2024-06-04 03:11:28] INFO convert_weight.py:155: Parameter size after quantization: 4.675 GB
[2024-06-04 03:11:28] INFO convert_weight.py:160: Total parameters: 8,030,261,248
[2024-06-04 03:11:28] INFO convert_weight.py:161: Bits per parameter: 5.001
[2024-06-04 03:11:28] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC
All finished, 108 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC/ndarray-cache.json
Also saved a bf16 record to /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC/ndarray-cache-b16.json