Hugging Face's logo

mlc-ai
/
Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC

MLC-LLM
web-llm
Model card Files Community
Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC / logs.txt
riczhou's picture
riczhou
Initial commit
c501289 verified
raw
history blame contribute delete
207 kB
/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Hermes-2-Pro-Llama-3-8B --quantization q3f16_1 --conv-template llama-3 --output /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC
[2024-06-04 03:29:25] INFO auto_config.py:116: Found model configuration: /models/Hermes-2-Pro-Llama-3-8B/config.json
[2024-06-04 03:29:25] INFO auto_config.py:154: Found model type: llama. Use `--model-type` to override.
[2024-06-04 03:29:25] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (8192)
[2024-06-04 03:29:25] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
[2024-06-04 03:29:25] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-04 03:29:25] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 128000
[2024-06-04 03:29:25] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: 128003
[2024-06-04 03:29:25] INFO gen_config.py:157: Not found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer.model
[2024-06-04 03:29:25] INFO gen_config.py:155: Found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC/tokenizer.json
[2024-06-04 03:29:25] INFO gen_config.py:157: Not found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/vocab.json
[2024-06-04 03:29:25] INFO gen_config.py:157: Not found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/merges.txt
[2024-06-04 03:29:25] INFO gen_config.py:157: Not found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/added_tokens.json
[2024-06-04 03:29:25] INFO gen_config.py:155: Found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC/tokenizer_config.json
[2024-06-04 03:29:25] 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 03:29:25] INFO gen_config.py:32: [System default] Setting pad_token_id: 0
[2024-06-04 03:29:25] INFO gen_config.py:32: [System default] Setting temperature: 1.0
[2024-06-04 03:29:25] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-04 03:29:25] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-04 03:29:25] INFO gen_config.py:32: [System default] Setting repetition_penalty: 1.0
[2024-06-04 03:29:25] INFO gen_config.py:32: [System default] Setting top_p: 1.0
[2024-06-04 03:29:25] INFO gen_config.py:32: [System default] Setting mean_gen_len: 128
[2024-06-04 03:29:25] INFO gen_config.py:32: [System default] Setting max_gen_len: 512
[2024-06-04 03:29:25] INFO gen_config.py:32: [System default] Setting shift_fill_factor: 0.3
[2024-06-04 03:29:25] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC/mlc-chat-config.json
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Hermes-2-Pro-Llama-3-8B --quantization q3f16_1 --output /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC
[2024-06-04 03:29:26] INFO auto_config.py:116: Found model configuration: /models/Hermes-2-Pro-Llama-3-8B/config.json
[2024-06-04 03:29:28] INFO auto_device.py:79: Found device: cuda:0
[2024-06-04 03:29:29] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-04 03:29:31] INFO auto_device.py:88: Not found device: metal:0
[2024-06-04 03:29:32] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-04 03:29:32] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-04 03:29:32] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-04 03:29:32] INFO auto_device.py:79: Found device: vulkan:3
[2024-06-04 03:29:34] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-04 03:29:34] INFO auto_device.py:35: Using device: cuda:0
[2024-06-04 03:29:34] INFO auto_weight.py:71: Finding weights in: /models/Hermes-2-Pro-Llama-3-8B
[2024-06-04 03:29:34] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-04 03:29:34] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /models/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json
[2024-06-04 03:29:34] INFO auto_weight.py:107: Using source weight configuration: /models/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json. Use `--source` to override.
[2024-06-04 03:29:34] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-04 03:29:34] INFO auto_config.py:154: Found model type: llama. Use `--model-type` to override.
[2024-06-04 03:29:34] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (8192)
[2024-06-04 03:29:34] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
Weight conversion with arguments:
--config /models/Hermes-2-Pro-Llama-3-8B/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/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json
--source-format huggingface-safetensor
--output /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC
0%| | 0/195 [00:00<?, ?it/s] [2024-06-04 03:29:38] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00004-of-00004.safetensors
0%| | 0/195 [00:00<?, ?it/s] [2024-06-04 03:29:41] INFO group_quantization.py:217: Compiling quantize function for key: ((128288, 4096), float16, cuda, axis=1, output_transpose=False)
0%| | 0/195 [00:02<?, ?it/s] [2024-06-04 03:29:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_weight", shape: (128288, 412), dtype: uint32
0%| | 0/195 [00:03<?, ?it/s] [2024-06-04 03:29:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_scale", shape: (128288, 103), dtype: float16
0%| | 0/195 [00:04<?, ?it/s] 1%| | 1/195 [00:04<14:20, 4.44s/it] [2024-06-04 03:29:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.input_layernorm.weight", shape: (4096,), dtype: float16
1%| | 1/195 [00:04<14:20, 4.44s/it] [2024-06-04 03:29:42] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 14336), float16, cuda, axis=1, output_transpose=False)
1%| | 1/195 [00:04<14:20, 4.44s/it] [2024-06-04 03:29:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
1%| | 1/195 [00:04<14:20, 4.44s/it] [2024-06-04 03:29:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
1%| | 1/195 [00:05<14:20, 4.44s/it] 2%|▏ | 3/195 [00:05<04:22, 1.37s/it] [2024-06-04 03:29:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.post_attention_layernorm.weight", shape: (4096,), dtype: float16
2%|▏ | 3/195 [00:05<04:22, 1.37s/it] [2024-06-04 03:29:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (4096,), dtype: float16
2%|▏ | 3/195 [00:05<04:22, 1.37s/it] [2024-06-04 03:29:43] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00004-of-00004.safetensors
2%|▏ | 3/195 [00:05<04:22, 1.37s/it] [2024-06-04 03:29:43] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00001-of-00004.safetensors
2%|▏ | 3/195 [00:05<04:22, 1.37s/it] [2024-06-04 03:29:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (128288, 412), dtype: uint32
2%|▏ | 3/195 [00:05<04:22, 1.37s/it] [2024-06-04 03:29:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (128288, 103), dtype: float16
2%|▏ | 3/195 [00:06<04:22, 1.37s/it] 3%|▎ | 6/195 [00:06<02:28, 1.28it/s] [2024-06-04 03:29:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (4096,), dtype: float16
3%|▎ | 6/195 [00:06<02:28, 1.28it/s] [2024-06-04 03:29:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
3%|▎ | 6/195 [00:06<02:28, 1.28it/s] [2024-06-04 03:29:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
3%|▎ | 6/195 [00:06<02:28, 1.28it/s] [2024-06-04 03:29:44] INFO group_quantization.py:217: Compiling quantize function for key: ((28672, 4096), float16, cuda, axis=1, output_transpose=False)
3%|▎ | 6/195 [00:06<02:28, 1.28it/s] [2024-06-04 03:29:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
3%|▎ | 6/195 [00:06<02:28, 1.28it/s] [2024-06-04 03:29:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
3%|▎ | 6/195 [00:07<02:28, 1.28it/s] 5%|▍ | 9/195 [00:07<01:42, 1.82it/s] [2024-06-04 03:29:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (4096,), dtype: float16
5%|▍ | 9/195 [00:07<01:42, 1.82it/s] [2024-06-04 03:29:45] INFO group_quantization.py:217: Compiling quantize function for key: ((6144, 4096), float16, cuda, axis=1, output_transpose=False)
5%|▍ | 9/195 [00:07<01:42, 1.82it/s] [2024-06-04 03:29:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
5%|▍ | 9/195 [00:07<01:42, 1.82it/s] [2024-06-04 03:29:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
5%|▍ | 9/195 [00:07<01:42, 1.82it/s] 6%|▌ | 11/195 [00:07<01:24, 2.19it/s] [2024-06-04 03:29:45] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 4096), float16, cuda, axis=1, output_transpose=False)
6%|▌ | 11/195 [00:07<01:24, 2.19it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
6%|▌ | 11/195 [00:08<01:24, 2.19it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
6%|▌ | 11/195 [00:08<01:24, 2.19it/s] 6%|▌ | 12/195 [00:08<01:24, 2.16it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (4096,), dtype: float16
6%|▌ | 12/195 [00:08<01:24, 2.16it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
6%|▌ | 12/195 [00:08<01:24, 2.16it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
6%|▌ | 12/195 [00:08<01:24, 2.16it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
6%|▌ | 12/195 [00:08<01:24, 2.16it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
6%|▌ | 12/195 [00:08<01:24, 2.16it/s] 8%|▊ | 15/195 [00:08<00:56, 3.21it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (4096,), dtype: float16
8%|▊ | 15/195 [00:08<00:56, 3.21it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
8%|▊ | 15/195 [00:08<00:56, 3.21it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
8%|▊ | 15/195 [00:08<00:56, 3.21it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
8%|▊ | 15/195 [00:08<00:56, 3.21it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
8%|▊ | 15/195 [00:08<00:56, 3.21it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (4096,), dtype: float16
8%|▊ | 15/195 [00:08<00:56, 3.21it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
8%|▊ | 15/195 [00:08<00:56, 3.21it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
8%|▊ | 15/195 [00:08<00:56, 3.21it/s] 10%|█ | 20/195 [00:08<00:29, 5.98it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
10%|█ | 20/195 [00:08<00:29, 5.98it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
10%|█ | 20/195 [00:08<00:29, 5.98it/s] [2024-06-04 03:29:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (4096,), dtype: float16
10%|█ | 20/195 [00:08<00:29, 5.98it/s] 11%|█▏ | 22/195 [00:08<00:27, 6.29it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
11%|█▏ | 22/195 [00:08<00:27, 6.29it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
11%|█▏ | 22/195 [00:08<00:27, 6.29it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
11%|█▏ | 22/195 [00:08<00:27, 6.29it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
11%|█▏ | 22/195 [00:08<00:27, 6.29it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (4096,), dtype: float16
11%|█▏ | 22/195 [00:08<00:27, 6.29it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
11%|█▏ | 22/195 [00:08<00:27, 6.29it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
11%|█▏ | 22/195 [00:08<00:27, 6.29it/s] 13%|█▎ | 26/195 [00:08<00:18, 9.10it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
13%|█▎ | 26/195 [00:09<00:18, 9.10it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
13%|█▎ | 26/195 [00:09<00:18, 9.10it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (4096,), dtype: float16
13%|█▎ | 26/195 [00:09<00:18, 9.10it/s] 14%|█▍ | 28/195 [00:09<00:19, 8.76it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
14%|█▍ | 28/195 [00:09<00:19, 8.76it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
14%|█▍ | 28/195 [00:09<00:19, 8.76it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
14%|█▍ | 28/195 [00:09<00:19, 8.76it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
14%|█▍ | 28/195 [00:09<00:19, 8.76it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (4096,), dtype: float16
14%|█▍ | 28/195 [00:09<00:19, 8.76it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
14%|█▍ | 28/195 [00:09<00:19, 8.76it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
14%|█▍ | 28/195 [00:09<00:19, 8.76it/s] 16%|█▋ | 32/195 [00:09<00:13, 12.18it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
16%|█▋ | 32/195 [00:09<00:13, 12.18it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
16%|█▋ | 32/195 [00:09<00:13, 12.18it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (4096,), dtype: float16
16%|█▋ | 32/195 [00:09<00:13, 12.18it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
16%|█▋ | 32/195 [00:09<00:13, 12.18it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
16%|█▋ | 32/195 [00:09<00:13, 12.18it/s] 18%|█▊ | 35/195 [00:09<00:13, 11.53it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
18%|█▊ | 35/195 [00:09<00:13, 11.53it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
18%|█▊ | 35/195 [00:09<00:13, 11.53it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (4096,), dtype: float16
18%|█▊ | 35/195 [00:09<00:13, 11.53it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
18%|█▊ | 35/195 [00:09<00:13, 11.53it/s] [2024-06-04 03:29:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
18%|█▊ | 35/195 [00:09<00:13, 11.53it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
18%|█▊ | 35/195 [00:09<00:13, 11.53it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
18%|█▊ | 35/195 [00:10<00:13, 11.53it/s] 20%|██ | 39/195 [00:10<00:14, 10.49it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (4096,), dtype: float16
20%|██ | 39/195 [00:10<00:14, 10.49it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
20%|██ | 39/195 [00:10<00:14, 10.49it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
20%|██ | 39/195 [00:10<00:14, 10.49it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
20%|██ | 39/195 [00:10<00:14, 10.49it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
20%|██ | 39/195 [00:10<00:14, 10.49it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (4096,), dtype: float16
20%|██ | 39/195 [00:10<00:14, 10.49it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
20%|██ | 39/195 [00:10<00:14, 10.49it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
20%|██ | 39/195 [00:10<00:14, 10.49it/s] 23%|██▎ | 44/195 [00:10<00:10, 14.62it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
23%|██▎ | 44/195 [00:10<00:10, 14.62it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
23%|██▎ | 44/195 [00:10<00:10, 14.62it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (4096,), dtype: float16
23%|██▎ | 44/195 [00:10<00:10, 14.62it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
23%|██▎ | 44/195 [00:10<00:10, 14.62it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
23%|██▎ | 44/195 [00:10<00:10, 14.62it/s] 24%|██▍ | 47/195 [00:10<00:13, 11.00it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
24%|██▍ | 47/195 [00:10<00:13, 11.00it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
24%|██▍ | 47/195 [00:10<00:13, 11.00it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (4096,), dtype: float16
24%|██▍ | 47/195 [00:10<00:13, 11.00it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
24%|██▍ | 47/195 [00:10<00:13, 11.00it/s] [2024-06-04 03:29:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
24%|██▍ | 47/195 [00:10<00:13, 11.00it/s] [2024-06-04 03:29:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
24%|██▍ | 47/195 [00:11<00:13, 11.00it/s] [2024-06-04 03:29:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
24%|██▍ | 47/195 [00:11<00:13, 11.00it/s] 26%|██▌ | 51/195 [00:11<00:16, 8.93it/s] [2024-06-04 03:29:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (4096,), dtype: float16
26%|██▌ | 51/195 [00:11<00:16, 8.93it/s] [2024-06-04 03:29:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
26%|██▌ | 51/195 [00:11<00:16, 8.93it/s] [2024-06-04 03:29:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
26%|██▌ | 51/195 [00:11<00:16, 8.93it/s] [2024-06-04 03:29:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
26%|██▌ | 51/195 [00:11<00:16, 8.93it/s] [2024-06-04 03:29:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
26%|██▌ | 51/195 [00:11<00:16, 8.93it/s] [2024-06-04 03:29:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (4096,), dtype: float16
26%|██▌ | 51/195 [00:11<00:16, 8.93it/s] [2024-06-04 03:29:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
26%|██▌ | 51/195 [00:11<00:16, 8.93it/s] [2024-06-04 03:29:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
26%|██▌ | 51/195 [00:11<00:16, 8.93it/s] 29%|██▊ | 56/195 [00:11<00:12, 11.12it/s] [2024-06-04 03:29:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
29%|██▊ | 56/195 [00:12<00:12, 11.12it/s] [2024-06-04 03:29:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
29%|██▊ | 56/195 [00:12<00:12, 11.12it/s] [2024-06-04 03:29:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (4096,), dtype: float16
29%|██▊ | 56/195 [00:12<00:12, 11.12it/s] 30%|██▉ | 58/195 [00:12<00:20, 6.82it/s] [2024-06-04 03:29:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
30%|██▉ | 58/195 [00:12<00:20, 6.82it/s] [2024-06-04 03:29:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
30%|██▉ | 58/195 [00:12<00:20, 6.82it/s] [2024-06-04 03:29:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
30%|██▉ | 58/195 [00:12<00:20, 6.82it/s] [2024-06-04 03:29:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
30%|██▉ | 58/195 [00:12<00:20, 6.82it/s] [2024-06-04 03:29:50] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00001-of-00004.safetensors
30%|██▉ | 58/195 [00:12<00:20, 6.82it/s] [2024-06-04 03:29:50] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00002-of-00004.safetensors
30%|██▉ | 58/195 [00:12<00:20, 6.82it/s] [2024-06-04 03:29:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (4096,), dtype: float16
30%|██▉ | 58/195 [00:12<00:20, 6.82it/s] 31%|███▏ | 61/195 [00:12<00:17, 7.65it/s] [2024-06-04 03:29:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
31%|███▏ | 61/195 [00:12<00:17, 7.65it/s] [2024-06-04 03:29:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
31%|███▏ | 61/195 [00:12<00:17, 7.65it/s] [2024-06-04 03:29:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
31%|███▏ | 61/195 [00:13<00:17, 7.65it/s] [2024-06-04 03:29:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
31%|███▏ | 61/195 [00:13<00:17, 7.65it/s] 32%|███▏ | 63/195 [00:13<00:27, 4.86it/s] [2024-06-04 03:29:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (4096,), dtype: float16
32%|███▏ | 63/195 [00:13<00:27, 4.86it/s] [2024-06-04 03:29:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
32%|███▏ | 63/195 [00:13<00:27, 4.86it/s] [2024-06-04 03:29:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
32%|███▏ | 63/195 [00:13<00:27, 4.86it/s] [2024-06-04 03:29:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
32%|███▏ | 63/195 [00:13<00:27, 4.86it/s] [2024-06-04 03:29:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
32%|███▏ | 63/195 [00:13<00:27, 4.86it/s] [2024-06-04 03:29:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (4096,), dtype: float16
32%|███▏ | 63/195 [00:13<00:27, 4.86it/s] [2024-06-04 03:29:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
32%|███▏ | 63/195 [00:13<00:27, 4.86it/s] [2024-06-04 03:29:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
32%|███▏ | 63/195 [00:13<00:27, 4.86it/s] 35%|███▍ | 68/195 [00:13<00:18, 7.03it/s] [2024-06-04 03:29:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
35%|███▍ | 68/195 [00:14<00:18, 7.03it/s] [2024-06-04 03:29:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
35%|███▍ | 68/195 [00:14<00:18, 7.03it/s] [2024-06-04 03:29:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (4096,), dtype: float16
35%|███▍ | 68/195 [00:14<00:18, 7.03it/s] 36%|███▌ | 70/195 [00:14<00:23, 5.24it/s] [2024-06-04 03:29:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
36%|███▌ | 70/195 [00:14<00:23, 5.24it/s] [2024-06-04 03:29:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
36%|███▌ | 70/195 [00:14<00:23, 5.24it/s] [2024-06-04 03:29:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
36%|███▌ | 70/195 [00:14<00:23, 5.24it/s] [2024-06-04 03:29:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
36%|███▌ | 70/195 [00:14<00:23, 5.24it/s] [2024-06-04 03:29:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (4096,), dtype: float16
36%|███▌ | 70/195 [00:14<00:23, 5.24it/s] [2024-06-04 03:29:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
36%|███▌ | 70/195 [00:14<00:23, 5.24it/s] [2024-06-04 03:29:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
36%|███▌ | 70/195 [00:14<00:23, 5.24it/s] 38%|███▊ | 74/195 [00:14<00:17, 7.03it/s] [2024-06-04 03:29:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
38%|███▊ | 74/195 [00:15<00:17, 7.03it/s] [2024-06-04 03:29:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
38%|███▊ | 74/195 [00:15<00:17, 7.03it/s] [2024-06-04 03:29:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (4096,), dtype: float16
38%|███▊ | 74/195 [00:15<00:17, 7.03it/s] 39%|███▉ | 76/195 [00:15<00:23, 5.10it/s] [2024-06-04 03:29:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
39%|███▉ | 76/195 [00:15<00:23, 5.10it/s] [2024-06-04 03:29:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
39%|███▉ | 76/195 [00:15<00:23, 5.10it/s] [2024-06-04 03:29:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
39%|███▉ | 76/195 [00:15<00:23, 5.10it/s] [2024-06-04 03:29:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
39%|███▉ | 76/195 [00:15<00:23, 5.10it/s] [2024-06-04 03:29:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (4096,), dtype: float16
39%|███▉ | 76/195 [00:15<00:23, 5.10it/s] [2024-06-04 03:29:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
39%|███▉ | 76/195 [00:15<00:23, 5.10it/s] [2024-06-04 03:29:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
39%|███▉ | 76/195 [00:15<00:23, 5.10it/s] 41%|████ | 80/195 [00:15<00:15, 7.34it/s] [2024-06-04 03:29:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
41%|████ | 80/195 [00:16<00:15, 7.34it/s] [2024-06-04 03:29:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
41%|████ | 80/195 [00:16<00:15, 7.34it/s] [2024-06-04 03:29:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (4096,), dtype: float16
41%|████ | 80/195 [00:16<00:15, 7.34it/s] 42%|████▏ | 82/195 [00:16<00:22, 5.02it/s] [2024-06-04 03:29:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
42%|████▏ | 82/195 [00:16<00:22, 5.02it/s] [2024-06-04 03:29:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
42%|████▏ | 82/195 [00:16<00:22, 5.02it/s] [2024-06-04 03:29:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
42%|████▏ | 82/195 [00:16<00:22, 5.02it/s] [2024-06-04 03:29:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
42%|████▏ | 82/195 [00:16<00:22, 5.02it/s] [2024-06-04 03:29:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (4096,), dtype: float16
42%|████▏ | 82/195 [00:16<00:22, 5.02it/s] [2024-06-04 03:29:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
42%|████▏ | 82/195 [00:16<00:22, 5.02it/s] [2024-06-04 03:29:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
42%|████▏ | 82/195 [00:16<00:22, 5.02it/s] 44%|████▍ | 86/195 [00:16<00:14, 7.31it/s] [2024-06-04 03:29:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
44%|████▍ | 86/195 [00:17<00:14, 7.31it/s] [2024-06-04 03:29:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
44%|████▍ | 86/195 [00:17<00:14, 7.31it/s] [2024-06-04 03:29:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (4096,), dtype: float16
44%|████▍ | 86/195 [00:17<00:14, 7.31it/s] 45%|████▌ | 88/195 [00:17<00:20, 5.29it/s] [2024-06-04 03:29:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
45%|████▌ | 88/195 [00:17<00:20, 5.29it/s] [2024-06-04 03:29:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
45%|████▌ | 88/195 [00:17<00:20, 5.29it/s] [2024-06-04 03:29:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
45%|████▌ | 88/195 [00:17<00:20, 5.29it/s] [2024-06-04 03:29:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
45%|████▌ | 88/195 [00:17<00:20, 5.29it/s] [2024-06-04 03:29:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (4096,), dtype: float16
45%|████▌ | 88/195 [00:17<00:20, 5.29it/s] [2024-06-04 03:29:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
45%|████▌ | 88/195 [00:17<00:20, 5.29it/s] [2024-06-04 03:29:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
45%|████▌ | 88/195 [00:17<00:20, 5.29it/s] 47%|████▋ | 92/195 [00:17<00:13, 7.71it/s] [2024-06-04 03:29:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
47%|████▋ | 92/195 [00:18<00:13, 7.71it/s] [2024-06-04 03:29:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
47%|████▋ | 92/195 [00:18<00:13, 7.71it/s] [2024-06-04 03:29:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (4096,), dtype: float16
47%|████▋ | 92/195 [00:18<00:13, 7.71it/s] 48%|████▊ | 94/195 [00:18<00:17, 5.70it/s] [2024-06-04 03:29:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
48%|████▊ | 94/195 [00:18<00:17, 5.70it/s] [2024-06-04 03:29:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
48%|████▊ | 94/195 [00:18<00:17, 5.70it/s] [2024-06-04 03:29:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
48%|████▊ | 94/195 [00:18<00:17, 5.70it/s] [2024-06-04 03:29:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
48%|████▊ | 94/195 [00:18<00:17, 5.70it/s] [2024-06-04 03:29:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (4096,), dtype: float16
48%|████▊ | 94/195 [00:18<00:17, 5.70it/s] [2024-06-04 03:29:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
48%|████▊ | 94/195 [00:18<00:17, 5.70it/s] [2024-06-04 03:29:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
48%|████▊ | 94/195 [00:18<00:17, 5.70it/s] 50%|█████ | 98/195 [00:18<00:11, 8.26it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
50%|█████ | 98/195 [00:18<00:11, 8.26it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
50%|█████ | 98/195 [00:19<00:11, 8.26it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (4096,), dtype: float16
50%|█████ | 98/195 [00:19<00:11, 8.26it/s] 51%|█████▏ | 100/195 [00:19<00:14, 6.65it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
51%|█████▏ | 100/195 [00:19<00:14, 6.65it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
51%|█████▏ | 100/195 [00:19<00:14, 6.65it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
51%|█████▏ | 100/195 [00:19<00:14, 6.65it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
51%|█████▏ | 100/195 [00:19<00:14, 6.65it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (4096,), dtype: float16
51%|█████▏ | 100/195 [00:19<00:14, 6.65it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
51%|█████▏ | 100/195 [00:19<00:14, 6.65it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
51%|█████▏ | 100/195 [00:19<00:14, 6.65it/s] 53%|█████▎ | 104/195 [00:19<00:09, 9.51it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
53%|█████▎ | 104/195 [00:19<00:09, 9.51it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
53%|█████▎ | 104/195 [00:19<00:09, 9.51it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (4096,), dtype: float16
53%|█████▎ | 104/195 [00:19<00:09, 9.51it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
53%|█████▎ | 104/195 [00:19<00:09, 9.51it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
53%|█████▎ | 104/195 [00:19<00:09, 9.51it/s] 55%|█████▍ | 107/195 [00:19<00:09, 9.77it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
55%|█████▍ | 107/195 [00:19<00:09, 9.77it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
55%|█████▍ | 107/195 [00:19<00:09, 9.77it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (4096,), dtype: float16
55%|█████▍ | 107/195 [00:19<00:09, 9.77it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
55%|█████▍ | 107/195 [00:19<00:09, 9.77it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
55%|█████▍ | 107/195 [00:19<00:09, 9.77it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
55%|█████▍ | 107/195 [00:19<00:09, 9.77it/s] [2024-06-04 03:29:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
55%|█████▍ | 107/195 [00:19<00:09, 9.77it/s] 57%|█████▋ | 111/195 [00:19<00:08, 10.24it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (4096,), dtype: float16
57%|█████▋ | 111/195 [00:19<00:08, 10.24it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
57%|█████▋ | 111/195 [00:19<00:08, 10.24it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
57%|█████▋ | 111/195 [00:19<00:08, 10.24it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
57%|█████▋ | 111/195 [00:19<00:08, 10.24it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
57%|█████▋ | 111/195 [00:19<00:08, 10.24it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (4096,), dtype: float16
57%|█████▋ | 111/195 [00:19<00:08, 10.24it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
57%|█████▋ | 111/195 [00:19<00:08, 10.24it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
57%|█████▋ | 111/195 [00:20<00:08, 10.24it/s] 59%|█████▉ | 116/195 [00:20<00:05, 14.43it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
59%|█████▉ | 116/195 [00:20<00:05, 14.43it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
59%|█████▉ | 116/195 [00:20<00:05, 14.43it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (4096,), dtype: float16
59%|█████▉ | 116/195 [00:20<00:05, 14.43it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
59%|█████▉ | 116/195 [00:20<00:05, 14.43it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
59%|█████▉ | 116/195 [00:20<00:05, 14.43it/s] 61%|██████ | 119/195 [00:20<00:05, 13.16it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
61%|██████ | 119/195 [00:20<00:05, 13.16it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
61%|██████ | 119/195 [00:20<00:05, 13.16it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00003-of-00004.safetensors
61%|██████ | 119/195 [00:20<00:05, 13.16it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
61%|██████ | 119/195 [00:20<00:05, 13.16it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
61%|██████ | 119/195 [00:20<00:05, 13.16it/s] 62%|██████▏ | 121/195 [00:20<00:06, 11.97it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
62%|██████▏ | 121/195 [00:20<00:06, 11.97it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
62%|██████▏ | 121/195 [00:20<00:06, 11.97it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
62%|██████▏ | 121/195 [00:20<00:06, 11.97it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
62%|██████▏ | 121/195 [00:20<00:06, 11.97it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (4096,), dtype: float16
62%|██████▏ | 121/195 [00:20<00:06, 11.97it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
62%|██████▏ | 121/195 [00:20<00:06, 11.97it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
62%|██████▏ | 121/195 [00:20<00:06, 11.97it/s] 64%|██████▍ | 125/195 [00:20<00:04, 14.22it/s] [2024-06-04 03:29:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
64%|██████▍ | 125/195 [00:20<00:04, 14.22it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
64%|██████▍ | 125/195 [00:20<00:04, 14.22it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (4096,), dtype: float16
64%|██████▍ | 125/195 [00:20<00:04, 14.22it/s] 65%|██████▌ | 127/195 [00:20<00:05, 12.80it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
65%|██████▌ | 127/195 [00:20<00:05, 12.80it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
65%|██████▌ | 127/195 [00:21<00:05, 12.80it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
65%|██████▌ | 127/195 [00:21<00:05, 12.80it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
65%|██████▌ | 127/195 [00:21<00:05, 12.80it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (4096,), dtype: float16
65%|██████▌ | 127/195 [00:21<00:05, 12.80it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
65%|██████▌ | 127/195 [00:21<00:05, 12.80it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
65%|██████▌ | 127/195 [00:21<00:05, 12.80it/s] 67%|██████▋ | 131/195 [00:21<00:04, 15.26it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (4096,), dtype: float16
67%|██████▋ | 131/195 [00:21<00:04, 15.26it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (4096,), dtype: float16
67%|██████▋ | 131/195 [00:21<00:04, 15.26it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
67%|██████▋ | 131/195 [00:21<00:04, 15.26it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
67%|██████▋ | 131/195 [00:21<00:04, 15.26it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
67%|██████▋ | 131/195 [00:21<00:04, 15.26it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
67%|██████▋ | 131/195 [00:21<00:04, 15.26it/s] 69%|██████▉ | 135/195 [00:21<00:04, 14.57it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (4096,), dtype: float16
69%|██████▉ | 135/195 [00:21<00:04, 14.57it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
69%|██████▉ | 135/195 [00:21<00:04, 14.57it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
69%|██████▉ | 135/195 [00:21<00:04, 14.57it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
69%|██████▉ | 135/195 [00:21<00:04, 14.57it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
69%|██████▉ | 135/195 [00:21<00:04, 14.57it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (4096,), dtype: float16
69%|██████▉ | 135/195 [00:21<00:04, 14.57it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
69%|██████▉ | 135/195 [00:21<00:04, 14.57it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
69%|██████▉ | 135/195 [00:21<00:04, 14.57it/s] 72%|███████▏ | 140/195 [00:21<00:03, 17.74it/s] [2024-06-04 03:29:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
72%|███████▏ | 140/195 [00:21<00:03, 17.74it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
72%|███████▏ | 140/195 [00:21<00:03, 17.74it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (4096,), dtype: float16
72%|███████▏ | 140/195 [00:21<00:03, 17.74it/s] 73%|███████▎ | 142/195 [00:21<00:03, 13.30it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
73%|███████▎ | 142/195 [00:21<00:03, 13.30it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
73%|███████▎ | 142/195 [00:22<00:03, 13.30it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
73%|███████▎ | 142/195 [00:22<00:03, 13.30it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
73%|███████▎ | 142/195 [00:22<00:03, 13.30it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (4096,), dtype: float16
73%|███████▎ | 142/195 [00:22<00:03, 13.30it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
73%|███████▎ | 142/195 [00:22<00:03, 13.30it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
73%|███████▎ | 142/195 [00:22<00:03, 13.30it/s] 75%|███████▍ | 146/195 [00:22<00:03, 15.40it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
75%|███████▍ | 146/195 [00:22<00:03, 15.40it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
75%|███████▍ | 146/195 [00:22<00:03, 15.40it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (4096,), dtype: float16
75%|███████▍ | 146/195 [00:22<00:03, 15.40it/s] 76%|███████▌ | 148/195 [00:22<00:03, 13.28it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
76%|███████▌ | 148/195 [00:22<00:03, 13.28it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
76%|███████▌ | 148/195 [00:22<00:03, 13.28it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
76%|███████▌ | 148/195 [00:22<00:03, 13.28it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
76%|███████▌ | 148/195 [00:22<00:03, 13.28it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (4096,), dtype: float16
76%|███████▌ | 148/195 [00:22<00:03, 13.28it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
76%|███████▌ | 148/195 [00:22<00:03, 13.28it/s] [2024-06-04 03:30:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
76%|███████▌ | 148/195 [00:22<00:03, 13.28it/s] 78%|███████▊ | 152/195 [00:22<00:02, 15.56it/s] [2024-06-04 03:30:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
78%|███████▊ | 152/195 [00:22<00:02, 15.56it/s] [2024-06-04 03:30:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
78%|███████▊ | 152/195 [00:23<00:02, 15.56it/s] [2024-06-04 03:30:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (4096,), dtype: float16
78%|███████▊ | 152/195 [00:23<00:02, 15.56it/s] 79%|███████▉ | 154/195 [00:23<00:04, 9.58it/s] [2024-06-04 03:30:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
79%|███████▉ | 154/195 [00:23<00:04, 9.58it/s] [2024-06-04 03:30:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
79%|███████▉ | 154/195 [00:23<00:04, 9.58it/s] [2024-06-04 03:30:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
79%|███████▉ | 154/195 [00:23<00:04, 9.58it/s] [2024-06-04 03:30:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
79%|███████▉ | 154/195 [00:23<00:04, 9.58it/s] [2024-06-04 03:30:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (4096,), dtype: float16
79%|███████▉ | 154/195 [00:23<00:04, 9.58it/s] [2024-06-04 03:30:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
79%|███████▉ | 154/195 [00:23<00:04, 9.58it/s] [2024-06-04 03:30:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
79%|███████▉ | 154/195 [00:23<00:04, 9.58it/s] 81%|████████ | 158/195 [00:23<00:03, 12.11it/s] [2024-06-04 03:30:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
81%|████████ | 158/195 [00:23<00:03, 12.11it/s] [2024-06-04 03:30:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
81%|████████ | 158/195 [00:23<00:03, 12.11it/s] [2024-06-04 03:30:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (4096,), dtype: float16
81%|████████ | 158/195 [00:23<00:03, 12.11it/s] 82%|████████▏ | 160/195 [00:23<00:04, 8.05it/s] [2024-06-04 03:30:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
82%|████████▏ | 160/195 [00:23<00:04, 8.05it/s] [2024-06-04 03:30:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
82%|████████▏ | 160/195 [00:23<00:04, 8.05it/s] [2024-06-04 03:30:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
82%|████████▏ | 160/195 [00:23<00:04, 8.05it/s] [2024-06-04 03:30:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
82%|████████▏ | 160/195 [00:23<00:04, 8.05it/s] [2024-06-04 03:30:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (4096,), dtype: float16
82%|████████▏ | 160/195 [00:23<00:04, 8.05it/s] [2024-06-04 03:30:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
82%|████████▏ | 160/195 [00:23<00:04, 8.05it/s] [2024-06-04 03:30:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
82%|████████▏ | 160/195 [00:23<00:04, 8.05it/s] 84%|████████▍ | 164/195 [00:23<00:02, 10.55it/s] [2024-06-04 03:30:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
84%|████████▍ | 164/195 [00:24<00:02, 10.55it/s] [2024-06-04 03:30:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
84%|████████▍ | 164/195 [00:24<00:02, 10.55it/s] [2024-06-04 03:30:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (4096,), dtype: float16
84%|████████▍ | 164/195 [00:24<00:02, 10.55it/s] 85%|████████▌ | 166/195 [00:24<00:03, 7.52it/s] [2024-06-04 03:30:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
85%|████████▌ | 166/195 [00:24<00:03, 7.52it/s] [2024-06-04 03:30:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
85%|████████▌ | 166/195 [00:24<00:03, 7.52it/s] [2024-06-04 03:30:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
85%|████████▌ | 166/195 [00:24<00:03, 7.52it/s] [2024-06-04 03:30:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
85%|████████▌ | 166/195 [00:24<00:03, 7.52it/s] [2024-06-04 03:30:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (4096,), dtype: float16
85%|████████▌ | 166/195 [00:24<00:03, 7.52it/s] [2024-06-04 03:30:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
85%|████████▌ | 166/195 [00:24<00:03, 7.52it/s] [2024-06-04 03:30:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
85%|████████▌ | 166/195 [00:24<00:03, 7.52it/s] 87%|████████▋ | 170/195 [00:24<00:02, 10.01it/s] [2024-06-04 03:30:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
87%|████████▋ | 170/195 [00:25<00:02, 10.01it/s] [2024-06-04 03:30:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
87%|████████▋ | 170/195 [00:25<00:02, 10.01it/s] [2024-06-04 03:30:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (4096,), dtype: float16
87%|████████▋ | 170/195 [00:25<00:02, 10.01it/s] 88%|████████▊ | 172/195 [00:25<00:03, 7.59it/s] [2024-06-04 03:30:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
88%|████████▊ | 172/195 [00:25<00:03, 7.59it/s] [2024-06-04 03:30:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
88%|████████▊ | 172/195 [00:25<00:03, 7.59it/s] [2024-06-04 03:30:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
88%|████████▊ | 172/195 [00:25<00:03, 7.59it/s] [2024-06-04 03:30:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
88%|████████▊ | 172/195 [00:25<00:03, 7.59it/s] [2024-06-04 03:30:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.input_layernorm.weight", shape: (4096,), dtype: float16
88%|████████▊ | 172/195 [00:25<00:03, 7.59it/s] [2024-06-04 03:30:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
88%|████████▊ | 172/195 [00:25<00:03, 7.59it/s] [2024-06-04 03:30:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
88%|████████▊ | 172/195 [00:25<00:03, 7.59it/s] 90%|█████████ | 176/195 [00:25<00:01, 10.11it/s] [2024-06-04 03:30:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
90%|█████████ | 176/195 [00:25<00:01, 10.11it/s] [2024-06-04 03:30:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
90%|█████████ | 176/195 [00:25<00:01, 10.11it/s] [2024-06-04 03:30:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.post_attention_layernorm.weight", shape: (4096,), dtype: float16
90%|█████████ | 176/195 [00:25<00:01, 10.11it/s] 91%|█████████▏| 178/195 [00:25<00:02, 8.27it/s] [2024-06-04 03:30:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
91%|█████████▏| 178/195 [00:25<00:02, 8.27it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
91%|█████████▏| 178/195 [00:25<00:02, 8.27it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
91%|█████████▏| 178/195 [00:25<00:02, 8.27it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
91%|█████████▏| 178/195 [00:25<00:02, 8.27it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.input_layernorm.weight", shape: (4096,), dtype: float16
91%|█████████▏| 178/195 [00:25<00:02, 8.27it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
91%|█████████▏| 178/195 [00:25<00:02, 8.27it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
91%|█████████▏| 178/195 [00:25<00:02, 8.27it/s] 93%|█████████▎| 182/195 [00:25<00:01, 10.86it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
93%|█████████▎| 182/195 [00:26<00:01, 10.86it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
93%|█████████▎| 182/195 [00:26<00:01, 10.86it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.post_attention_layernorm.weight", shape: (4096,), dtype: float16
93%|█████████▎| 182/195 [00:26<00:01, 10.86it/s] 94%|█████████▍| 184/195 [00:26<00:01, 10.31it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
94%|█████████▍| 184/195 [00:26<00:01, 10.31it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
94%|█████████▍| 184/195 [00:26<00:01, 10.31it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
94%|█████████▍| 184/195 [00:26<00:01, 10.31it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
94%|█████████▍| 184/195 [00:26<00:01, 10.31it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.input_layernorm.weight", shape: (4096,), dtype: float16
94%|█████████▍| 184/195 [00:26<00:01, 10.31it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
94%|█████████▍| 184/195 [00:26<00:01, 10.31it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
94%|█████████▍| 184/195 [00:26<00:01, 10.31it/s] 96%|█████████▋| 188/195 [00:26<00:00, 12.95it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
96%|█████████▋| 188/195 [00:26<00:00, 12.95it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
96%|█████████▋| 188/195 [00:26<00:00, 12.95it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.post_attention_layernorm.weight", shape: (4096,), dtype: float16
96%|█████████▋| 188/195 [00:26<00:00, 12.95it/s] 97%|█████████▋| 190/195 [00:26<00:00, 11.82it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
97%|█████████▋| 190/195 [00:26<00:00, 11.82it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
97%|█████████▋| 190/195 [00:26<00:00, 11.82it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
97%|█████████▋| 190/195 [00:26<00:00, 11.82it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
97%|█████████▋| 190/195 [00:26<00:00, 11.82it/s] [2024-06-04 03:30:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
97%|█████████▋| 190/195 [00:26<00:00, 11.82it/s] [2024-06-04 03:30:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
97%|█████████▋| 190/195 [00:26<00:00, 11.82it/s] 99%|█████████▉| 193/195 [00:26<00:00, 11.03it/s] [2024-06-04 03:30:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
99%|█████████▉| 193/195 [00:26<00:00, 11.03it/s] [2024-06-04 03:30:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
99%|█████████▉| 193/195 [00:26<00:00, 11.03it/s] [2024-06-04 03:30:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
99%|█████████▉| 193/195 [00:27<00:00, 11.03it/s] [2024-06-04 03:30:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
99%|█████████▉| 193/195 [00:27<00:00, 11.03it/s] 100%|██████████| 195/195 [00:27<00:00, 7.22it/s]
[2024-06-04 03:30:05] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00002-of-00004.safetensors
[2024-06-04 03:30:05] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00003-of-00004.safetensors
[2024-06-04 03:30:05] INFO stats.py:77: Time usage: HF loading: 1.294 sec; Pre-quantization mapping: 11.751 sec; Quantization: 3.056 sec
[2024-06-04 03:30:05] INFO stats.py:91: RAM usage: Peak RAM: 9.235 GB. Total bytes loaded from disk: 14.958 GB
[2024-06-04 03:30:05] INFO convert_weight.py:155: Parameter size after quantization: 3.382 GB
[2024-06-04 03:30:05] INFO convert_weight.py:160: Total parameters: 8,030,523,392
[2024-06-04 03:30:05] INFO convert_weight.py:161: Bits per parameter: 3.618
[2024-06-04 03:30:05] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC
All finished, 100 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC/ndarray-cache.json
/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Hermes-2-Pro-Llama-3-8B --quantization q3f16_1 --conv-template hermes2_pro_llama3 --output /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC
[2024-06-06 23:23:54] INFO auto_config.py:116: Found model configuration: /models/Hermes-2-Pro-Llama-3-8B/config.json
[2024-06-06 23:23:54] INFO auto_config.py:154: Found model type: llama. Use `--model-type` to override.
[2024-06-06 23:23:54] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (8192)
[2024-06-06 23:23:54] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
[2024-06-06 23:23:54] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-06 23:23:54] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 128000
[2024-06-06 23:23:54] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: 128003
[2024-06-06 23:23:54] INFO gen_config.py:157: Not found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer.model
[2024-06-06 23:23:54] INFO gen_config.py:155: Found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC/tokenizer.json
[2024-06-06 23:23:54] INFO gen_config.py:157: Not found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/vocab.json
[2024-06-06 23:23:54] INFO gen_config.py:157: Not found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/merges.txt
[2024-06-06 23:23:54] INFO gen_config.py:157: Not found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/added_tokens.json
[2024-06-06 23:23:54] INFO gen_config.py:155: Found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC/tokenizer_config.json
[2024-06-06 23:23:54] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_level', 'prepend_space_in_encode': False, 'strip_space_in_decode': False}
[2024-06-06 23:23:54] INFO gen_config.py:32: [System default] Setting pad_token_id: 0
[2024-06-06 23:23:54] INFO gen_config.py:32: [System default] Setting temperature: 1.0
[2024-06-06 23:23:54] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-06 23:23:54] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-06 23:23:54] INFO gen_config.py:32: [System default] Setting repetition_penalty: 1.0
[2024-06-06 23:23:54] INFO gen_config.py:32: [System default] Setting top_p: 1.0
[2024-06-06 23:23:54] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC/mlc-chat-config.json
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Hermes-2-Pro-Llama-3-8B --quantization q3f16_1 --output /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC
[2024-06-06 23:23:56] INFO auto_config.py:116: Found model configuration: /models/Hermes-2-Pro-Llama-3-8B/config.json
[2024-06-06 23:23:58] INFO auto_device.py:79: Found device: cuda:0
[2024-06-06 23:23:59] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-06 23:24:00] INFO auto_device.py:88: Not found device: metal:0
[2024-06-06 23:24:02] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-06 23:24:02] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-06 23:24:02] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-06 23:24:02] INFO auto_device.py:79: Found device: vulkan:3
[2024-06-06 23:24:04] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-06 23:24:04] INFO auto_device.py:35: Using device: cuda:0
[2024-06-06 23:24:04] INFO auto_weight.py:71: Finding weights in: /models/Hermes-2-Pro-Llama-3-8B
[2024-06-06 23:24:04] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-06 23:24:04] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /models/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json
[2024-06-06 23:24:04] INFO auto_weight.py:107: Using source weight configuration: /models/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json. Use `--source` to override.
[2024-06-06 23:24:04] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-06 23:24:04] INFO auto_config.py:154: Found model type: llama. Use `--model-type` to override.
[2024-06-06 23:24:04] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (8192)
[2024-06-06 23:24:04] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
Weight conversion with arguments:
--config /models/Hermes-2-Pro-Llama-3-8B/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/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json
--source-format huggingface-safetensor
--output /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC
0%| | 0/195 [00:00<?, ?it/s] [2024-06-06 23:24:08] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00004-of-00004.safetensors
0%| | 0/195 [00:00<?, ?it/s] [2024-06-06 23:24:09] INFO group_quantization.py:217: Compiling quantize function for key: ((128288, 4096), float16, cuda, axis=1, output_transpose=False)
0%| | 0/195 [00:01<?, ?it/s] [2024-06-06 23:24:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_weight", shape: (128288, 412), dtype: uint32
0%| | 0/195 [00:02<?, ?it/s] [2024-06-06 23:24:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_scale", shape: (128288, 103), dtype: float16
0%| | 0/195 [00:03<?, ?it/s] 1%| | 1/195 [00:03<12:30, 3.87s/it] [2024-06-06 23:24:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.input_layernorm.weight", shape: (4096,), dtype: float16
1%| | 1/195 [00:03<12:30, 3.87s/it] [2024-06-06 23:24:11] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 14336), float16, cuda, axis=1, output_transpose=False)
1%| | 1/195 [00:03<12:30, 3.87s/it] [2024-06-06 23:24:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
1%| | 1/195 [00:04<12:30, 3.87s/it] [2024-06-06 23:24:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
1%| | 1/195 [00:04<12:30, 3.87s/it] 2%|▏ | 3/195 [00:04<03:59, 1.25s/it] [2024-06-06 23:24:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.post_attention_layernorm.weight", shape: (4096,), dtype: float16
2%|▏ | 3/195 [00:04<03:59, 1.25s/it] [2024-06-06 23:24:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (4096,), dtype: float16
2%|▏ | 3/195 [00:04<03:59, 1.25s/it] [2024-06-06 23:24:12] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00004-of-00004.safetensors
2%|▏ | 3/195 [00:04<03:59, 1.25s/it] [2024-06-06 23:24:12] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00001-of-00004.safetensors
2%|▏ | 3/195 [00:04<03:59, 1.25s/it] [2024-06-06 23:24:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (128288, 412), dtype: uint32
2%|▏ | 3/195 [00:04<03:59, 1.25s/it] [2024-06-06 23:24:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (128288, 103), dtype: float16
2%|▏ | 3/195 [00:05<03:59, 1.25s/it] 3%|▎ | 6/195 [00:06<02:30, 1.26it/s] [2024-06-06 23:24:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (4096,), dtype: float16
3%|▎ | 6/195 [00:06<02:30, 1.26it/s] [2024-06-06 23:24:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
3%|▎ | 6/195 [00:06<02:30, 1.26it/s] [2024-06-06 23:24:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
3%|▎ | 6/195 [00:06<02:30, 1.26it/s] 4%|▍ | 8/195 [00:06<01:38, 1.89it/s] [2024-06-06 23:24:14] INFO group_quantization.py:217: Compiling quantize function for key: ((28672, 4096), float16, cuda, axis=1, output_transpose=False)
4%|▍ | 8/195 [00:06<01:38, 1.89it/s] [2024-06-06 23:24:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
4%|▍ | 8/195 [00:06<01:38, 1.89it/s] [2024-06-06 23:24:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
4%|▍ | 8/195 [00:07<01:38, 1.89it/s] 5%|▍ | 9/195 [00:07<01:56, 1.60it/s] [2024-06-06 23:24:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (4096,), dtype: float16
5%|▍ | 9/195 [00:07<01:56, 1.60it/s] [2024-06-06 23:24:15] INFO group_quantization.py:217: Compiling quantize function for key: ((6144, 4096), float16, cuda, axis=1, output_transpose=False)
5%|▍ | 9/195 [00:07<01:56, 1.60it/s] [2024-06-06 23:24:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
5%|▍ | 9/195 [00:07<01:56, 1.60it/s] [2024-06-06 23:24:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
5%|▍ | 9/195 [00:07<01:56, 1.60it/s] 6%|▌ | 11/195 [00:07<01:29, 2.05it/s] [2024-06-06 23:24:15] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 4096), float16, cuda, axis=1, output_transpose=False)
6%|▌ | 11/195 [00:07<01:29, 2.05it/s] [2024-06-06 23:24:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
6%|▌ | 11/195 [00:08<01:29, 2.05it/s] [2024-06-06 23:24:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
6%|▌ | 11/195 [00:08<01:29, 2.05it/s] 6%|▌ | 12/195 [00:08<01:29, 2.04it/s] [2024-06-06 23:24:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (4096,), dtype: float16
6%|▌ | 12/195 [00:08<01:29, 2.04it/s] [2024-06-06 23:24:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
6%|▌ | 12/195 [00:08<01:29, 2.04it/s] [2024-06-06 23:24:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
6%|▌ | 12/195 [00:08<01:29, 2.04it/s] 7%|▋ | 14/195 [00:08<01:00, 3.00it/s] [2024-06-06 23:24:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
7%|▋ | 14/195 [00:08<01:00, 3.00it/s] [2024-06-06 23:24:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
7%|▋ | 14/195 [00:08<01:00, 3.00it/s] 8%|▊ | 15/195 [00:08<01:04, 2.81it/s] [2024-06-06 23:24:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (4096,), dtype: float16
8%|▊ | 15/195 [00:08<01:04, 2.81it/s] [2024-06-06 23:24:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
8%|▊ | 15/195 [00:08<01:04, 2.81it/s] [2024-06-06 23:24:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
8%|▊ | 15/195 [00:08<01:04, 2.81it/s] [2024-06-06 23:24:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
8%|▊ | 15/195 [00:08<01:04, 2.81it/s] [2024-06-06 23:24:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
8%|▊ | 15/195 [00:08<01:04, 2.81it/s] [2024-06-06 23:24:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (4096,), dtype: float16
8%|▊ | 15/195 [00:08<01:04, 2.81it/s] [2024-06-06 23:24:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
8%|▊ | 15/195 [00:08<01:04, 2.81it/s] [2024-06-06 23:24:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
8%|▊ | 15/195 [00:08<01:04, 2.81it/s] 10%|█ | 20/195 [00:08<00:28, 6.16it/s] [2024-06-06 23:24:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
10%|█ | 20/195 [00:09<00:28, 6.16it/s] [2024-06-06 23:24:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
10%|█ | 20/195 [00:09<00:28, 6.16it/s] [2024-06-06 23:24:17] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (4096,), dtype: float16
10%|█ | 20/195 [00:09<00:28, 6.16it/s] 11%|█▏ | 22/195 [00:09<00:30, 5.68it/s] [2024-06-06 23:24:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
11%|█▏ | 22/195 [00:09<00:30, 5.68it/s] [2024-06-06 23:24:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
11%|█▏ | 22/195 [00:09<00:30, 5.68it/s] [2024-06-06 23:24:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
11%|█▏ | 22/195 [00:09<00:30, 5.68it/s] [2024-06-06 23:24:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
11%|█▏ | 22/195 [00:09<00:30, 5.68it/s] [2024-06-06 23:24:17] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (4096,), dtype: float16
11%|█▏ | 22/195 [00:09<00:30, 5.68it/s] [2024-06-06 23:24:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
11%|█▏ | 22/195 [00:09<00:30, 5.68it/s] [2024-06-06 23:24:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
11%|█▏ | 22/195 [00:09<00:30, 5.68it/s] 13%|█▎ | 26/195 [00:09<00:20, 8.24it/s] [2024-06-06 23:24:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
13%|█▎ | 26/195 [00:09<00:20, 8.24it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
13%|█▎ | 26/195 [00:09<00:20, 8.24it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (4096,), dtype: float16
13%|█▎ | 26/195 [00:10<00:20, 8.24it/s] 14%|█▍ | 28/195 [00:10<00:24, 6.93it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
14%|█▍ | 28/195 [00:10<00:24, 6.93it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
14%|█▍ | 28/195 [00:10<00:24, 6.93it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
14%|█▍ | 28/195 [00:10<00:24, 6.93it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
14%|█▍ | 28/195 [00:10<00:24, 6.93it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (4096,), dtype: float16
14%|█▍ | 28/195 [00:10<00:24, 6.93it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
14%|█▍ | 28/195 [00:10<00:24, 6.93it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
14%|█▍ | 28/195 [00:10<00:24, 6.93it/s] 16%|█▋ | 32/195 [00:10<00:16, 9.60it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
16%|█▋ | 32/195 [00:10<00:16, 9.60it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
16%|█▋ | 32/195 [00:10<00:16, 9.60it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (4096,), dtype: float16
16%|█▋ | 32/195 [00:10<00:16, 9.60it/s] 17%|█▋ | 34/195 [00:10<00:20, 7.68it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
17%|█▋ | 34/195 [00:10<00:20, 7.68it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
17%|█▋ | 34/195 [00:10<00:20, 7.68it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
17%|█▋ | 34/195 [00:10<00:20, 7.68it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
17%|█▋ | 34/195 [00:10<00:20, 7.68it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (4096,), dtype: float16
17%|█▋ | 34/195 [00:10<00:20, 7.68it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
17%|█▋ | 34/195 [00:10<00:20, 7.68it/s] [2024-06-06 23:24:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
17%|█▋ | 34/195 [00:10<00:20, 7.68it/s] 19%|█▉ | 38/195 [00:10<00:15, 10.36it/s] [2024-06-06 23:24:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
19%|█▉ | 38/195 [00:10<00:15, 10.36it/s] [2024-06-06 23:24:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
19%|█▉ | 38/195 [00:11<00:15, 10.36it/s] [2024-06-06 23:24:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (4096,), dtype: float16
19%|█▉ | 38/195 [00:11<00:15, 10.36it/s] 21%|██ | 40/195 [00:11<00:19, 8.02it/s] [2024-06-06 23:24:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
21%|██ | 40/195 [00:11<00:19, 8.02it/s] [2024-06-06 23:24:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
21%|██ | 40/195 [00:11<00:19, 8.02it/s] [2024-06-06 23:24:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
21%|██ | 40/195 [00:11<00:19, 8.02it/s] [2024-06-06 23:24:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
21%|██ | 40/195 [00:11<00:19, 8.02it/s] [2024-06-06 23:24:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (4096,), dtype: float16
21%|██ | 40/195 [00:11<00:19, 8.02it/s] [2024-06-06 23:24:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
21%|██ | 40/195 [00:11<00:19, 8.02it/s] [2024-06-06 23:24:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
21%|██ | 40/195 [00:11<00:19, 8.02it/s] 23%|██▎ | 44/195 [00:11<00:14, 10.73it/s] [2024-06-06 23:24:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
23%|██▎ | 44/195 [00:11<00:14, 10.73it/s] [2024-06-06 23:24:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
23%|██▎ | 44/195 [00:11<00:14, 10.73it/s] [2024-06-06 23:24:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (4096,), dtype: float16
23%|██▎ | 44/195 [00:11<00:14, 10.73it/s] 24%|██▎ | 46/195 [00:11<00:17, 8.41it/s] [2024-06-06 23:24:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
24%|██▎ | 46/195 [00:11<00:17, 8.41it/s] [2024-06-06 23:24:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
24%|██▎ | 46/195 [00:11<00:17, 8.41it/s] [2024-06-06 23:24:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
24%|██▎ | 46/195 [00:11<00:17, 8.41it/s] [2024-06-06 23:24:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
24%|██▎ | 46/195 [00:11<00:17, 8.41it/s] [2024-06-06 23:24:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (4096,), dtype: float16
24%|██▎ | 46/195 [00:11<00:17, 8.41it/s] [2024-06-06 23:24:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
24%|██▎ | 46/195 [00:11<00:17, 8.41it/s] [2024-06-06 23:24:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
24%|██▎ | 46/195 [00:12<00:17, 8.41it/s] 26%|██▌ | 50/195 [00:12<00:13, 11.04it/s] [2024-06-06 23:24:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
26%|██▌ | 50/195 [00:12<00:13, 11.04it/s] [2024-06-06 23:24:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
26%|██▌ | 50/195 [00:12<00:13, 11.04it/s] [2024-06-06 23:24:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (4096,), dtype: float16
26%|██▌ | 50/195 [00:12<00:13, 11.04it/s] 27%|██▋ | 52/195 [00:12<00:17, 8.40it/s] [2024-06-06 23:24:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
27%|██▋ | 52/195 [00:12<00:17, 8.40it/s] [2024-06-06 23:24:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
27%|██▋ | 52/195 [00:12<00:17, 8.40it/s] [2024-06-06 23:24:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
27%|██▋ | 52/195 [00:12<00:17, 8.40it/s] [2024-06-06 23:24:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
27%|██▋ | 52/195 [00:12<00:17, 8.40it/s] [2024-06-06 23:24:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (4096,), dtype: float16
27%|██▋ | 52/195 [00:12<00:17, 8.40it/s] [2024-06-06 23:24:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
27%|██▋ | 52/195 [00:12<00:17, 8.40it/s] [2024-06-06 23:24:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
27%|██▋ | 52/195 [00:12<00:17, 8.40it/s] 29%|██▊ | 56/195 [00:12<00:12, 11.03it/s] [2024-06-06 23:24:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
29%|██▊ | 56/195 [00:12<00:12, 11.03it/s] [2024-06-06 23:24:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
29%|██▊ | 56/195 [00:12<00:12, 11.03it/s] [2024-06-06 23:24:21] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (4096,), dtype: float16
29%|██▊ | 56/195 [00:13<00:12, 11.03it/s] 30%|██▉ | 58/195 [00:13<00:15, 8.56it/s] [2024-06-06 23:24:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
30%|██▉ | 58/195 [00:13<00:15, 8.56it/s] [2024-06-06 23:24:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
30%|██▉ | 58/195 [00:13<00:15, 8.56it/s] [2024-06-06 23:24:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
30%|██▉ | 58/195 [00:13<00:15, 8.56it/s] [2024-06-06 23:24:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
30%|██▉ | 58/195 [00:13<00:15, 8.56it/s] [2024-06-06 23:24:21] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00001-of-00004.safetensors
30%|██▉ | 58/195 [00:13<00:15, 8.56it/s] [2024-06-06 23:24:21] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00002-of-00004.safetensors
30%|██▉ | 58/195 [00:13<00:15, 8.56it/s] [2024-06-06 23:24:21] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (4096,), dtype: float16
30%|██▉ | 58/195 [00:13<00:15, 8.56it/s] 31%|███▏ | 61/195 [00:13<00:14, 9.43it/s] [2024-06-06 23:24:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
31%|███▏ | 61/195 [00:13<00:14, 9.43it/s] [2024-06-06 23:24:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
31%|███▏ | 61/195 [00:13<00:14, 9.43it/s] [2024-06-06 23:24:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
31%|███▏ | 61/195 [00:13<00:14, 9.43it/s] [2024-06-06 23:24:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
31%|███▏ | 61/195 [00:13<00:14, 9.43it/s] 32%|███▏ | 63/195 [00:13<00:19, 6.84it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (4096,), dtype: float16
32%|███▏ | 63/195 [00:13<00:19, 6.84it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
32%|███▏ | 63/195 [00:13<00:19, 6.84it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
32%|███▏ | 63/195 [00:13<00:19, 6.84it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
32%|███▏ | 63/195 [00:13<00:19, 6.84it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
32%|███▏ | 63/195 [00:13<00:19, 6.84it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (4096,), dtype: float16
32%|███▏ | 63/195 [00:13<00:19, 6.84it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
32%|███▏ | 63/195 [00:13<00:19, 6.84it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
32%|███▏ | 63/195 [00:14<00:19, 6.84it/s] 35%|███▍ | 68/195 [00:14<00:11, 10.59it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
35%|███▍ | 68/195 [00:14<00:11, 10.59it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
35%|███▍ | 68/195 [00:14<00:11, 10.59it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (4096,), dtype: float16
35%|███▍ | 68/195 [00:14<00:11, 10.59it/s] 36%|███▌ | 70/195 [00:14<00:14, 8.45it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
36%|███▌ | 70/195 [00:14<00:14, 8.45it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
36%|███▌ | 70/195 [00:14<00:14, 8.45it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
36%|███▌ | 70/195 [00:14<00:14, 8.45it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
36%|███▌ | 70/195 [00:14<00:14, 8.45it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (4096,), dtype: float16
36%|███▌ | 70/195 [00:14<00:14, 8.45it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
36%|███▌ | 70/195 [00:14<00:14, 8.45it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
36%|███▌ | 70/195 [00:14<00:14, 8.45it/s] 38%|███▊ | 74/195 [00:14<00:11, 10.92it/s] [2024-06-06 23:24:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
38%|███▊ | 74/195 [00:14<00:11, 10.92it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
38%|███▊ | 74/195 [00:14<00:11, 10.92it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (4096,), dtype: float16
38%|███▊ | 74/195 [00:15<00:11, 10.92it/s] 39%|███▉ | 76/195 [00:15<00:13, 8.60it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
39%|███▉ | 76/195 [00:15<00:13, 8.60it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
39%|███▉ | 76/195 [00:15<00:13, 8.60it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
39%|███▉ | 76/195 [00:15<00:13, 8.60it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
39%|███▉ | 76/195 [00:15<00:13, 8.60it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (4096,), dtype: float16
39%|███▉ | 76/195 [00:15<00:13, 8.60it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
39%|███▉ | 76/195 [00:15<00:13, 8.60it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
39%|███▉ | 76/195 [00:15<00:13, 8.60it/s] 41%|████ | 80/195 [00:15<00:10, 11.43it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
41%|████ | 80/195 [00:15<00:10, 11.43it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
41%|████ | 80/195 [00:15<00:10, 11.43it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (4096,), dtype: float16
41%|████ | 80/195 [00:15<00:10, 11.43it/s] 42%|████▏ | 82/195 [00:15<00:13, 8.67it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
42%|████▏ | 82/195 [00:15<00:13, 8.67it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
42%|████▏ | 82/195 [00:15<00:13, 8.67it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
42%|████▏ | 82/195 [00:15<00:13, 8.67it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
42%|████▏ | 82/195 [00:15<00:13, 8.67it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (4096,), dtype: float16
42%|████▏ | 82/195 [00:15<00:13, 8.67it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
42%|████▏ | 82/195 [00:15<00:13, 8.67it/s] [2024-06-06 23:24:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
42%|████▏ | 82/195 [00:15<00:13, 8.67it/s] 44%|████▍ | 86/195 [00:15<00:09, 11.53it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
44%|████▍ | 86/195 [00:15<00:09, 11.53it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
44%|████▍ | 86/195 [00:16<00:09, 11.53it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (4096,), dtype: float16
44%|████▍ | 86/195 [00:16<00:09, 11.53it/s] 45%|████▌ | 88/195 [00:16<00:12, 8.82it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
45%|████▌ | 88/195 [00:16<00:12, 8.82it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
45%|████▌ | 88/195 [00:16<00:12, 8.82it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
45%|████▌ | 88/195 [00:16<00:12, 8.82it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
45%|████▌ | 88/195 [00:16<00:12, 8.82it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (4096,), dtype: float16
45%|████▌ | 88/195 [00:16<00:12, 8.82it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
45%|████▌ | 88/195 [00:16<00:12, 8.82it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
45%|████▌ | 88/195 [00:16<00:12, 8.82it/s] 47%|████▋ | 92/195 [00:16<00:08, 11.66it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
47%|████▋ | 92/195 [00:16<00:08, 11.66it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
47%|████▋ | 92/195 [00:16<00:08, 11.66it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (4096,), dtype: float16
47%|████▋ | 92/195 [00:16<00:08, 11.66it/s] 48%|████▊ | 94/195 [00:16<00:11, 8.96it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
48%|████▊ | 94/195 [00:16<00:11, 8.96it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
48%|████▊ | 94/195 [00:16<00:11, 8.96it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
48%|████▊ | 94/195 [00:16<00:11, 8.96it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
48%|████▊ | 94/195 [00:16<00:11, 8.96it/s] [2024-06-06 23:24:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (4096,), dtype: float16
48%|████▊ | 94/195 [00:16<00:11, 8.96it/s] [2024-06-06 23:24:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
48%|████▊ | 94/195 [00:16<00:11, 8.96it/s] [2024-06-06 23:24:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
48%|████▊ | 94/195 [00:17<00:11, 8.96it/s] 50%|█████ | 98/195 [00:17<00:08, 11.57it/s] [2024-06-06 23:24:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
50%|█████ | 98/195 [00:17<00:08, 11.57it/s] [2024-06-06 23:24:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
50%|█████ | 98/195 [00:17<00:08, 11.57it/s] [2024-06-06 23:24:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (4096,), dtype: float16
50%|█████ | 98/195 [00:17<00:08, 11.57it/s] 51%|█████▏ | 100/195 [00:17<00:10, 8.78it/s] [2024-06-06 23:24:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
51%|█████▏ | 100/195 [00:17<00:10, 8.78it/s] [2024-06-06 23:24:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
51%|█████▏ | 100/195 [00:17<00:10, 8.78it/s] [2024-06-06 23:24:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
51%|█████▏ | 100/195 [00:17<00:10, 8.78it/s] [2024-06-06 23:24:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
51%|█████▏ | 100/195 [00:17<00:10, 8.78it/s] [2024-06-06 23:24:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (4096,), dtype: float16
51%|█████▏ | 100/195 [00:17<00:10, 8.78it/s] [2024-06-06 23:24:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
51%|█████▏ | 100/195 [00:17<00:10, 8.78it/s] [2024-06-06 23:24:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
51%|█████▏ | 100/195 [00:17<00:10, 8.78it/s] 53%|█████▎ | 104/195 [00:17<00:07, 11.48it/s] [2024-06-06 23:24:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
53%|█████▎ | 104/195 [00:17<00:07, 11.48it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
53%|█████▎ | 104/195 [00:17<00:07, 11.48it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (4096,), dtype: float16
53%|█████▎ | 104/195 [00:18<00:07, 11.48it/s] 54%|█████▍ | 106/195 [00:18<00:09, 9.11it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
54%|█████▍ | 106/195 [00:18<00:09, 9.11it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
54%|█████▍ | 106/195 [00:18<00:09, 9.11it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
54%|█████▍ | 106/195 [00:18<00:09, 9.11it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
54%|█████▍ | 106/195 [00:18<00:09, 9.11it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (4096,), dtype: float16
54%|█████▍ | 106/195 [00:18<00:09, 9.11it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
54%|█████▍ | 106/195 [00:18<00:09, 9.11it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
54%|█████▍ | 106/195 [00:18<00:09, 9.11it/s] 56%|█████▋ | 110/195 [00:18<00:07, 12.07it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
56%|█████▋ | 110/195 [00:18<00:07, 12.07it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
56%|█████▋ | 110/195 [00:18<00:07, 12.07it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (4096,), dtype: float16
56%|█████▋ | 110/195 [00:18<00:07, 12.07it/s] 57%|█████▋ | 112/195 [00:18<00:09, 9.10it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
57%|█████▋ | 112/195 [00:18<00:09, 9.10it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
57%|█████▋ | 112/195 [00:18<00:09, 9.10it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
57%|█████▋ | 112/195 [00:18<00:09, 9.10it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
57%|█████▋ | 112/195 [00:18<00:09, 9.10it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (4096,), dtype: float16
57%|█████▋ | 112/195 [00:18<00:09, 9.10it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
57%|█████▋ | 112/195 [00:18<00:09, 9.10it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
57%|█████▋ | 112/195 [00:18<00:09, 9.10it/s] 59%|█████▉ | 116/195 [00:18<00:06, 12.08it/s] [2024-06-06 23:24:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
59%|█████▉ | 116/195 [00:18<00:06, 12.08it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
59%|█████▉ | 116/195 [00:19<00:06, 12.08it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (4096,), dtype: float16
59%|█████▉ | 116/195 [00:19<00:06, 12.08it/s] 61%|██████ | 118/195 [00:19<00:08, 9.20it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
61%|██████ | 118/195 [00:19<00:08, 9.20it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
61%|██████ | 118/195 [00:19<00:08, 9.20it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
61%|██████ | 118/195 [00:19<00:08, 9.20it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
61%|██████ | 118/195 [00:19<00:08, 9.20it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00003-of-00004.safetensors
61%|██████ | 118/195 [00:19<00:08, 9.20it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
61%|██████ | 118/195 [00:19<00:08, 9.20it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
61%|██████ | 118/195 [00:19<00:08, 9.20it/s] 62%|██████▏ | 121/195 [00:19<00:08, 8.94it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
62%|██████▏ | 121/195 [00:19<00:08, 8.94it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
62%|██████▏ | 121/195 [00:19<00:08, 8.94it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
62%|██████▏ | 121/195 [00:19<00:08, 8.94it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
62%|██████▏ | 121/195 [00:19<00:08, 8.94it/s] 63%|██████▎ | 123/195 [00:19<00:07, 9.59it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (4096,), dtype: float16
63%|██████▎ | 123/195 [00:19<00:07, 9.59it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
63%|██████▎ | 123/195 [00:19<00:07, 9.59it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
63%|██████▎ | 123/195 [00:19<00:07, 9.59it/s] 64%|██████▍ | 125/195 [00:19<00:06, 10.81it/s] [2024-06-06 23:24:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
64%|██████▍ | 125/195 [00:19<00:06, 10.81it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
64%|██████▍ | 125/195 [00:20<00:06, 10.81it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (4096,), dtype: float16
64%|██████▍ | 125/195 [00:20<00:06, 10.81it/s] 65%|██████▌ | 127/195 [00:20<00:07, 9.28it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
65%|██████▌ | 127/195 [00:20<00:07, 9.28it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
65%|██████▌ | 127/195 [00:20<00:07, 9.28it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
65%|██████▌ | 127/195 [00:20<00:07, 9.28it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
65%|██████▌ | 127/195 [00:20<00:07, 9.28it/s] 66%|██████▌ | 129/195 [00:20<00:06, 10.45it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (4096,), dtype: float16
66%|██████▌ | 129/195 [00:20<00:06, 10.45it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
66%|██████▌ | 129/195 [00:20<00:06, 10.45it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
66%|██████▌ | 129/195 [00:20<00:06, 10.45it/s] 67%|██████▋ | 131/195 [00:20<00:05, 11.64it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (4096,), dtype: float16
67%|██████▋ | 131/195 [00:20<00:05, 11.64it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (4096,), dtype: float16
67%|██████▋ | 131/195 [00:20<00:05, 11.64it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
67%|██████▋ | 131/195 [00:20<00:05, 11.64it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
67%|██████▋ | 131/195 [00:20<00:05, 11.64it/s] 69%|██████▊ | 134/195 [00:20<00:04, 14.39it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
69%|██████▊ | 134/195 [00:20<00:04, 14.39it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
69%|██████▊ | 134/195 [00:20<00:04, 14.39it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (4096,), dtype: float16
69%|██████▊ | 134/195 [00:20<00:04, 14.39it/s] 70%|██████▉ | 136/195 [00:20<00:05, 10.91it/s] [2024-06-06 23:24:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
70%|██████▉ | 136/195 [00:20<00:05, 10.91it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
70%|██████▉ | 136/195 [00:20<00:05, 10.91it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
70%|██████▉ | 136/195 [00:20<00:05, 10.91it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
70%|██████▉ | 136/195 [00:20<00:05, 10.91it/s] 71%|███████ | 138/195 [00:20<00:05, 11.26it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (4096,), dtype: float16
71%|███████ | 138/195 [00:20<00:05, 11.26it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
71%|███████ | 138/195 [00:20<00:05, 11.26it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
71%|███████ | 138/195 [00:21<00:05, 11.26it/s] 72%|███████▏ | 140/195 [00:21<00:04, 12.07it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
72%|███████▏ | 140/195 [00:21<00:04, 12.07it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
72%|███████▏ | 140/195 [00:21<00:04, 12.07it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (4096,), dtype: float16
72%|███████▏ | 140/195 [00:21<00:04, 12.07it/s] 73%|███████▎ | 142/195 [00:21<00:05, 9.48it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
73%|███████▎ | 142/195 [00:21<00:05, 9.48it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
73%|███████▎ | 142/195 [00:21<00:05, 9.48it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
73%|███████▎ | 142/195 [00:21<00:05, 9.48it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
73%|███████▎ | 142/195 [00:21<00:05, 9.48it/s] 74%|███████▍ | 144/195 [00:21<00:04, 10.23it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (4096,), dtype: float16
74%|███████▍ | 144/195 [00:21<00:04, 10.23it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
74%|███████▍ | 144/195 [00:21<00:04, 10.23it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
74%|███████▍ | 144/195 [00:21<00:04, 10.23it/s] 75%|███████▍ | 146/195 [00:21<00:04, 11.16it/s] [2024-06-06 23:24:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
75%|███████▍ | 146/195 [00:21<00:04, 11.16it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
75%|███████▍ | 146/195 [00:21<00:04, 11.16it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (4096,), dtype: float16
75%|███████▍ | 146/195 [00:22<00:04, 11.16it/s] 76%|███████▌ | 148/195 [00:22<00:05, 8.98it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
76%|███████▌ | 148/195 [00:22<00:05, 8.98it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
76%|███████▌ | 148/195 [00:22<00:05, 8.98it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
76%|███████▌ | 148/195 [00:22<00:05, 8.98it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
76%|███████▌ | 148/195 [00:22<00:05, 8.98it/s] 77%|███████▋ | 150/195 [00:22<00:04, 9.88it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (4096,), dtype: float16
77%|███████▋ | 150/195 [00:22<00:04, 9.88it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
77%|███████▋ | 150/195 [00:22<00:04, 9.88it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
77%|███████▋ | 150/195 [00:22<00:04, 9.88it/s] 78%|███████▊ | 152/195 [00:22<00:03, 10.82it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
78%|███████▊ | 152/195 [00:22<00:03, 10.82it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
78%|███████▊ | 152/195 [00:22<00:03, 10.82it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (4096,), dtype: float16
78%|███████▊ | 152/195 [00:22<00:03, 10.82it/s] 79%|███████▉ | 154/195 [00:22<00:04, 9.10it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
79%|███████▉ | 154/195 [00:22<00:04, 9.10it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
79%|███████▉ | 154/195 [00:22<00:04, 9.10it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
79%|███████▉ | 154/195 [00:22<00:04, 9.10it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
79%|███████▉ | 154/195 [00:22<00:04, 9.10it/s] 80%|████████ | 156/195 [00:22<00:03, 10.01it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (4096,), dtype: float16
80%|████████ | 156/195 [00:22<00:03, 10.01it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
80%|████████ | 156/195 [00:22<00:03, 10.01it/s] [2024-06-06 23:24:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
80%|████████ | 156/195 [00:22<00:03, 10.01it/s] 81%|████████ | 158/195 [00:22<00:03, 11.10it/s] [2024-06-06 23:24:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
81%|████████ | 158/195 [00:22<00:03, 11.10it/s] [2024-06-06 23:24:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
81%|████████ | 158/195 [00:23<00:03, 11.10it/s] [2024-06-06 23:24:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (4096,), dtype: float16
81%|████████ | 158/195 [00:23<00:03, 11.10it/s] 82%|████████▏ | 160/195 [00:23<00:03, 9.04it/s] [2024-06-06 23:24:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
82%|████████▏ | 160/195 [00:23<00:03, 9.04it/s] [2024-06-06 23:24:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
82%|████████▏ | 160/195 [00:23<00:03, 9.04it/s] [2024-06-06 23:24:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
82%|████████▏ | 160/195 [00:23<00:03, 9.04it/s] [2024-06-06 23:24:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
82%|████████▏ | 160/195 [00:23<00:03, 9.04it/s] 83%|████████▎ | 162/195 [00:23<00:03, 9.93it/s] [2024-06-06 23:24:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (4096,), dtype: float16
83%|████████▎ | 162/195 [00:23<00:03, 9.93it/s] [2024-06-06 23:24:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
83%|████████▎ | 162/195 [00:23<00:03, 9.93it/s] [2024-06-06 23:24:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
83%|████████▎ | 162/195 [00:23<00:03, 9.93it/s] 84%|████████▍ | 164/195 [00:23<00:02, 11.02it/s] [2024-06-06 23:24:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
84%|████████▍ | 164/195 [00:23<00:02, 11.02it/s] [2024-06-06 23:24:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
84%|████████▍ | 164/195 [00:23<00:02, 11.02it/s] [2024-06-06 23:24:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (4096,), dtype: float16
84%|████████▍ | 164/195 [00:23<00:02, 11.02it/s] 85%|████████▌ | 166/195 [00:23<00:03, 9.20it/s] [2024-06-06 23:24:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
85%|████████▌ | 166/195 [00:23<00:03, 9.20it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
85%|████████▌ | 166/195 [00:23<00:03, 9.20it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
85%|████████▌ | 166/195 [00:23<00:03, 9.20it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
85%|████████▌ | 166/195 [00:23<00:03, 9.20it/s] 86%|████████▌ | 168/195 [00:23<00:02, 10.29it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (4096,), dtype: float16
86%|████████▌ | 168/195 [00:23<00:02, 10.29it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
86%|████████▌ | 168/195 [00:23<00:02, 10.29it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
86%|████████▌ | 168/195 [00:24<00:02, 10.29it/s] 87%|████████▋ | 170/195 [00:24<00:02, 11.64it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
87%|████████▋ | 170/195 [00:24<00:02, 11.64it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
87%|████████▋ | 170/195 [00:24<00:02, 11.64it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (4096,), dtype: float16
87%|████████▋ | 170/195 [00:24<00:02, 11.64it/s] 88%|████████▊ | 172/195 [00:24<00:02, 9.49it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
88%|████████▊ | 172/195 [00:24<00:02, 9.49it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
88%|████████▊ | 172/195 [00:24<00:02, 9.49it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
88%|████████▊ | 172/195 [00:24<00:02, 9.49it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
88%|████████▊ | 172/195 [00:24<00:02, 9.49it/s] 89%|████████▉ | 174/195 [00:24<00:01, 10.79it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.input_layernorm.weight", shape: (4096,), dtype: float16
89%|████████▉ | 174/195 [00:24<00:01, 10.79it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
89%|████████▉ | 174/195 [00:24<00:01, 10.79it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
89%|████████▉ | 174/195 [00:24<00:01, 10.79it/s] 90%|█████████ | 176/195 [00:24<00:01, 11.77it/s] [2024-06-06 23:24:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
90%|█████████ | 176/195 [00:24<00:01, 11.77it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
90%|█████████ | 176/195 [00:24<00:01, 11.77it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.post_attention_layernorm.weight", shape: (4096,), dtype: float16
90%|█████████ | 176/195 [00:24<00:01, 11.77it/s] 91%|█████████▏| 178/195 [00:24<00:01, 9.68it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
91%|█████████▏| 178/195 [00:24<00:01, 9.68it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
91%|█████████▏| 178/195 [00:25<00:01, 9.68it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
91%|█████████▏| 178/195 [00:25<00:01, 9.68it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
91%|█████████▏| 178/195 [00:25<00:01, 9.68it/s] 92%|█████████▏| 180/195 [00:25<00:01, 10.96it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.input_layernorm.weight", shape: (4096,), dtype: float16
92%|█████████▏| 180/195 [00:25<00:01, 10.96it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
92%|█████████▏| 180/195 [00:25<00:01, 10.96it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
92%|█████████▏| 180/195 [00:25<00:01, 10.96it/s] 93%|█████████▎| 182/195 [00:25<00:01, 11.88it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
93%|█████████▎| 182/195 [00:25<00:01, 11.88it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
93%|█████████▎| 182/195 [00:25<00:01, 11.88it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.post_attention_layernorm.weight", shape: (4096,), dtype: float16
93%|█████████▎| 182/195 [00:25<00:01, 11.88it/s] 94%|█████████▍| 184/195 [00:25<00:01, 9.66it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
94%|█████████▍| 184/195 [00:25<00:01, 9.66it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
94%|█████████▍| 184/195 [00:25<00:01, 9.66it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
94%|█████████▍| 184/195 [00:25<00:01, 9.66it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
94%|█████████▍| 184/195 [00:25<00:01, 9.66it/s] 95%|█████████▌| 186/195 [00:25<00:00, 10.94it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.input_layernorm.weight", shape: (4096,), dtype: float16
95%|█████████▌| 186/195 [00:25<00:00, 10.94it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_weight", shape: (4096, 1436), dtype: uint32
95%|█████████▌| 186/195 [00:25<00:00, 10.94it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_scale", shape: (4096, 359), dtype: float16
95%|█████████▌| 186/195 [00:25<00:00, 10.94it/s] 96%|█████████▋| 188/195 [00:25<00:00, 11.83it/s] [2024-06-06 23:24:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
96%|█████████▋| 188/195 [00:25<00:00, 11.83it/s] [2024-06-06 23:24:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
96%|█████████▋| 188/195 [00:26<00:00, 11.83it/s] [2024-06-06 23:24:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.post_attention_layernorm.weight", shape: (4096,), dtype: float16
96%|█████████▋| 188/195 [00:26<00:00, 11.83it/s] 97%|█████████▋| 190/195 [00:26<00:00, 9.56it/s] [2024-06-06 23:24:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
97%|█████████▋| 190/195 [00:26<00:00, 9.56it/s] [2024-06-06 23:24:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
97%|█████████▋| 190/195 [00:26<00:00, 9.56it/s] [2024-06-06 23:24:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
97%|█████████▋| 190/195 [00:26<00:00, 9.56it/s] [2024-06-06 23:24:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
97%|█████████▋| 190/195 [00:26<00:00, 9.56it/s] 98%|█████████▊| 192/195 [00:26<00:00, 10.36it/s] [2024-06-06 23:24:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_weight", shape: (28672, 412), dtype: uint32
98%|█████████▊| 192/195 [00:26<00:00, 10.36it/s] [2024-06-06 23:24:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_scale", shape: (28672, 103), dtype: float16
98%|█████████▊| 192/195 [00:26<00:00, 10.36it/s] [2024-06-06 23:24:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_weight", shape: (6144, 412), dtype: uint32
98%|█████████▊| 192/195 [00:26<00:00, 10.36it/s] [2024-06-06 23:24:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_scale", shape: (6144, 103), dtype: float16
98%|█████████▊| 192/195 [00:26<00:00, 10.36it/s] 99%|█████████▉| 194/195 [00:26<00:00, 7.82it/s] [2024-06-06 23:24:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_weight", shape: (4096, 412), dtype: uint32
99%|█████████▉| 194/195 [00:26<00:00, 7.82it/s] [2024-06-06 23:24:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float16
99%|█████████▉| 194/195 [00:26<00:00, 7.82it/s] 100%|██████████| 195/195 [00:26<00:00, 7.33it/s]
[2024-06-06 23:24:34] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00002-of-00004.safetensors
[2024-06-06 23:24:34] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00003-of-00004.safetensors
[2024-06-06 23:24:35] INFO stats.py:77: Time usage: HF loading: 1.389 sec; Pre-quantization mapping: 4.106 sec; Quantization: 3.158 sec
[2024-06-06 23:24:35] INFO stats.py:91: RAM usage: Peak RAM: 9.235 GB. Total bytes loaded from disk: 14.958 GB
[2024-06-06 23:24:35] INFO convert_weight.py:155: Parameter size after quantization: 3.382 GB
[2024-06-06 23:24:35] INFO convert_weight.py:160: Total parameters: 8,030,523,392
[2024-06-06 23:24:35] INFO convert_weight.py:161: Bits per parameter: 3.618
[2024-06-06 23:24:35] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC
All finished, 100 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q3f16_1-MLC/ndarray-cache.json