Initial commit

c59abc4 verified 5 months ago

141 kB

	/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Hermes-2-Pro-Llama-3-8B --quantization q0f16 --conv-template llama-3 --output /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC
	[2024-06-04 03:23:40] INFO auto_config.py:116: [92mFound[0m model configuration: /models/Hermes-2-Pro-Llama-3-8B/config.json
	[2024-06-04 03:23:40] INFO auto_config.py:154: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override.
	[2024-06-04 03:23:40] INFO llama_model.py:52: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (8192)
	[2024-06-04 03:23:40] INFO llama_model.py:72: [1mprefill_chunk_size[0m defaults to 2048
	[2024-06-04 03:23:40] INFO config.py:107: Overriding [1mmax_batch_size[0m from 1 to 80
	[2024-06-04 03:23:40] INFO gen_config.py:143: [generation_config.json] Setting [1mbos_token_id[0m: 128000
	[2024-06-04 03:23:40] INFO gen_config.py:143: [generation_config.json] Setting [1meos_token_id[0m: 128003
	[2024-06-04 03:23:40] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer.model
	[2024-06-04 03:23:40] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC/tokenizer.json[0m
	[2024-06-04 03:23:40] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/vocab.json
	[2024-06-04 03:23:40] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/merges.txt
	[2024-06-04 03:23:40] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/added_tokens.json
	[2024-06-04 03:23:40] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer_config.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC/tokenizer_config.json[0m
	[2024-06-04 03:23:40] 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 03:23:40] INFO gen_config.py:32: [System default] Setting [1mpad_token_id[0m: 0
	[2024-06-04 03:23:40] INFO gen_config.py:32: [System default] Setting [1mtemperature[0m: 1.0
	[2024-06-04 03:23:40] INFO gen_config.py:32: [System default] Setting [1mpresence_penalty[0m: 0.0
	[2024-06-04 03:23:40] INFO gen_config.py:32: [System default] Setting [1mfrequency_penalty[0m: 0.0
	[2024-06-04 03:23:40] INFO gen_config.py:32: [System default] Setting [1mrepetition_penalty[0m: 1.0
	[2024-06-04 03:23:40] INFO gen_config.py:32: [System default] Setting [1mtop_p[0m: 1.0
	[2024-06-04 03:23:40] INFO gen_config.py:32: [System default] Setting [1mmean_gen_len[0m: 128
	[2024-06-04 03:23:40] INFO gen_config.py:32: [System default] Setting [1mmax_gen_len[0m: 512
	[2024-06-04 03:23:40] INFO gen_config.py:32: [System default] Setting [1mshift_fill_factor[0m: 0.3
	[2024-06-04 03:23:40] INFO gen_config.py:223: Dumping configuration file to: [1m/models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC/mlc-chat-config.json[0m
	/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Hermes-2-Pro-Llama-3-8B --quantization q0f16 --output /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC
	[2024-06-04 03:23:41] INFO auto_config.py:116: [92mFound[0m model configuration: /models/Hermes-2-Pro-Llama-3-8B/config.json
	[2024-06-04 03:23:43] INFO auto_device.py:79: [92mFound[0m device: cuda:0
	[2024-06-04 03:23:44] INFO auto_device.py:88: [91mNot found[0m device: rocm:0
	[2024-06-04 03:23:45] INFO auto_device.py:88: [91mNot found[0m device: metal:0
	[2024-06-04 03:23:47] INFO auto_device.py:79: [92mFound[0m device: vulkan:0
	[2024-06-04 03:23:47] INFO auto_device.py:79: [92mFound[0m device: vulkan:1
	[2024-06-04 03:23:47] INFO auto_device.py:79: [92mFound[0m device: vulkan:2
	[2024-06-04 03:23:47] INFO auto_device.py:79: [92mFound[0m device: vulkan:3
	[2024-06-04 03:23:48] INFO auto_device.py:88: [91mNot found[0m device: opencl:0
	[2024-06-04 03:23:48] INFO auto_device.py:35: Using device: [1mcuda:0[0m
	[2024-06-04 03:23:48] INFO auto_weight.py:71: Finding weights in: /models/Hermes-2-Pro-Llama-3-8B
	[2024-06-04 03:23:48] INFO auto_weight.py:137: [91mNot found[0m Huggingface PyTorch
	[2024-06-04 03:23:48] INFO auto_weight.py:144: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: /models/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json
	[2024-06-04 03:23:48] INFO auto_weight.py:107: Using source weight configuration: [1m/models/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json[0m. Use `--source` to override.
	[2024-06-04 03:23:48] INFO auto_weight.py:111: Using source weight format: [1mhuggingface-safetensor[0m. Use `--source-format` to override.
	[2024-06-04 03:23:48] INFO auto_config.py:154: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override.
	[2024-06-04 03:23:48] INFO llama_model.py:52: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (8192)
	[2024-06-04 03:23:48] INFO llama_model.py:72: [1mprefill_chunk_size[0m defaults to 2048
	[1mWeight conversion with arguments:[0m
	[1m--config[0m /models/Hermes-2-Pro-Llama-3-8B/config.json
	[1m--quantization[0m NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16')
	[1m--model-type[0m llama
	[1m--device[0m cuda:0
	[1m--source[0m /models/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json
	[1m--source-format[0m huggingface-safetensor
	[1m--output[0m /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC
	Start storing to cache /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC
	0%\| \| 0/195 [00:00<?, ?it/s] [2024-06-04 03:23:50] 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 03:23:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mlm_head.weight[0m", shape: (128288, 4096), dtype: float16
	0%\| \| 0/195 [00:02<?, ?it/s] 1%\| \| 1/195 [00:06<22:09, 6.85s/it] [2024-06-04 03:23:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.31.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	1%\| \| 1/195 [00:06<22:09, 6.85s/it] 1%\| \| 2/195 [00:06<09:18, 2.90s/it] [2024-06-04 03:23:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.31.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	1%\| \| 2/195 [00:07<09:18, 2.90s/it] 2%\|▏ \| 3/195 [00:07<05:32, 1.73s/it] [2024-06-04 03:23:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.31.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	2%\|▏ \| 3/195 [00:07<05:32, 1.73s/it] [2024-06-04 03:23:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.norm.weight[0m", shape: (4096,), dtype: float16
	2%\|▏ \| 3/195 [00:07<05:32, 1.73s/it] [2024-06-04 03:23:58] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00004-of-00004.safetensors
	2%\|▏ \| 3/195 [00:07<05:32, 1.73s/it] [2024-06-04 03:23:58] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00001-of-00004.safetensors
	2%\|▏ \| 3/195 [00:07<05:32, 1.73s/it] [2024-06-04 03:23:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.embed_tokens.weight[0m", shape: (128288, 4096), dtype: float16
	2%\|▏ \| 3/195 [00:08<05:32, 1.73s/it] 3%\|▎ \| 6/195 [00:12<05:06, 1.62s/it] [2024-06-04 03:24:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	3%\|▎ \| 6/195 [00:12<05:06, 1.62s/it] 4%\|▎ \| 7/195 [00:12<03:56, 1.26s/it] [2024-06-04 03:24:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	4%\|▎ \| 7/195 [00:12<03:56, 1.26s/it] 4%\|▍ \| 8/195 [00:12<03:12, 1.03s/it] [2024-06-04 03:24:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	4%\|▍ \| 8/195 [00:12<03:12, 1.03s/it] 5%\|▍ \| 9/195 [00:13<02:56, 1.05it/s] [2024-06-04 03:24:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	5%\|▍ \| 9/195 [00:13<02:56, 1.05it/s] [2024-06-04 03:24:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	5%\|▍ \| 9/195 [00:13<02:56, 1.05it/s] 6%\|▌ \| 11/195 [00:13<01:46, 1.73it/s] [2024-06-04 03:24:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	6%\|▌ \| 11/195 [00:13<01:46, 1.73it/s] 6%\|▌ \| 12/195 [00:13<01:25, 2.15it/s] [2024-06-04 03:24:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	6%\|▌ \| 12/195 [00:13<01:25, 2.15it/s] [2024-06-04 03:24:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	6%\|▌ \| 12/195 [00:13<01:25, 2.15it/s] 7%\|▋ \| 14/195 [00:13<01:03, 2.87it/s] [2024-06-04 03:24:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	7%\|▋ \| 14/195 [00:13<01:03, 2.87it/s] 8%\|▊ \| 15/195 [00:14<01:17, 2.33it/s] [2024-06-04 03:24:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	8%\|▊ \| 15/195 [00:14<01:17, 2.33it/s] [2024-06-04 03:24:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	8%\|▊ \| 15/195 [00:14<01:17, 2.33it/s] 9%\|▊ \| 17/195 [00:14<00:52, 3.38it/s] [2024-06-04 03:24:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	9%\|▊ \| 17/195 [00:14<00:52, 3.38it/s] 9%\|▉ \| 18/195 [00:14<00:44, 3.94it/s] [2024-06-04 03:24:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	9%\|▉ \| 18/195 [00:14<00:44, 3.94it/s] [2024-06-04 03:24:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	9%\|▉ \| 18/195 [00:14<00:44, 3.94it/s] 10%\|█ \| 20/195 [00:15<00:38, 4.52it/s] [2024-06-04 03:24:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	10%\|█ \| 20/195 [00:15<00:38, 4.52it/s] 11%\|█ \| 21/195 [00:15<00:56, 3.10it/s] [2024-06-04 03:24:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	11%\|█ \| 21/195 [00:15<00:56, 3.10it/s] [2024-06-04 03:24:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	11%\|█ \| 21/195 [00:15<00:56, 3.10it/s] 12%\|█▏ \| 23/195 [00:16<00:39, 4.33it/s] [2024-06-04 03:24:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	12%\|█▏ \| 23/195 [00:16<00:39, 4.33it/s] 12%\|█▏ \| 24/195 [00:16<00:34, 4.92it/s] [2024-06-04 03:24:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	12%\|█▏ \| 24/195 [00:16<00:34, 4.92it/s] [2024-06-04 03:24:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	12%\|█▏ \| 24/195 [00:16<00:34, 4.92it/s] 13%\|█▎ \| 26/195 [00:16<00:31, 5.31it/s] [2024-06-04 03:24:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	13%\|█▎ \| 26/195 [00:16<00:31, 5.31it/s] 14%\|█▍ \| 27/195 [00:17<00:49, 3.40it/s] [2024-06-04 03:24:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	14%\|█▍ \| 27/195 [00:17<00:49, 3.40it/s] [2024-06-04 03:24:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	14%\|█▍ \| 27/195 [00:17<00:49, 3.40it/s] 15%\|█▍ \| 29/195 [00:17<00:35, 4.69it/s] [2024-06-04 03:24:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	15%\|█▍ \| 29/195 [00:17<00:35, 4.69it/s] [2024-06-04 03:24:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	15%\|█▍ \| 29/195 [00:17<00:35, 4.69it/s] 16%\|█▌ \| 31/195 [00:17<00:25, 6.39it/s] [2024-06-04 03:24:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	16%\|█▌ \| 31/195 [00:17<00:25, 6.39it/s] [2024-06-04 03:24:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	16%\|█▌ \| 31/195 [00:18<00:25, 6.39it/s] 17%\|█▋ \| 33/195 [00:19<01:01, 2.64it/s] [2024-06-04 03:24:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	17%\|█▋ \| 33/195 [00:19<01:01, 2.64it/s] [2024-06-04 03:24:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	17%\|█▋ \| 33/195 [00:19<01:01, 2.64it/s] 18%\|█▊ \| 35/195 [00:19<00:45, 3.52it/s] [2024-06-04 03:24:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	18%\|█▊ \| 35/195 [00:19<00:45, 3.52it/s] 18%\|█▊ \| 36/195 [00:19<00:39, 3.99it/s] [2024-06-04 03:24:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	18%\|█▊ \| 36/195 [00:19<00:39, 3.99it/s] [2024-06-04 03:24:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	18%\|█▊ \| 36/195 [00:19<00:39, 3.99it/s] 19%\|█▉ \| 38/195 [00:19<00:34, 4.53it/s] [2024-06-04 03:24:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	19%\|█▉ \| 38/195 [00:20<00:34, 4.53it/s] 20%\|██ \| 39/195 [00:21<01:12, 2.15it/s] [2024-06-04 03:24:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	20%\|██ \| 39/195 [00:21<01:12, 2.15it/s] [2024-06-04 03:24:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	20%\|██ \| 39/195 [00:21<01:12, 2.15it/s] 21%\|██ \| 41/195 [00:21<00:50, 3.05it/s] [2024-06-04 03:24:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	21%\|██ \| 41/195 [00:21<00:50, 3.05it/s] 22%\|██▏ \| 42/195 [00:21<00:43, 3.55it/s] [2024-06-04 03:24:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	22%\|██▏ \| 42/195 [00:21<00:43, 3.55it/s] [2024-06-04 03:24:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	22%\|██▏ \| 42/195 [00:21<00:43, 3.55it/s] 23%\|██▎ \| 44/195 [00:21<00:36, 4.18it/s] [2024-06-04 03:24:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	23%\|██▎ \| 44/195 [00:22<00:36, 4.18it/s] 23%\|██▎ \| 45/195 [00:23<01:12, 2.06it/s] [2024-06-04 03:24:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	23%\|██▎ \| 45/195 [00:23<01:12, 2.06it/s] [2024-06-04 03:24:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	23%\|██▎ \| 45/195 [00:23<01:12, 2.06it/s] 24%\|██▍ \| 47/195 [00:23<00:49, 2.97it/s] [2024-06-04 03:24:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	24%\|██▍ \| 47/195 [00:23<00:49, 2.97it/s] 25%\|██▍ \| 48/195 [00:23<00:42, 3.48it/s] [2024-06-04 03:24:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	25%\|██▍ \| 48/195 [00:23<00:42, 3.48it/s] [2024-06-04 03:24:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	25%\|██▍ \| 48/195 [00:23<00:42, 3.48it/s] 26%\|██▌ \| 50/195 [00:23<00:35, 4.14it/s] [2024-06-04 03:24:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	26%\|██▌ \| 50/195 [00:24<00:35, 4.14it/s] 26%\|██▌ \| 51/195 [00:25<01:14, 1.93it/s] [2024-06-04 03:24:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	26%\|██▌ \| 51/195 [00:25<01:14, 1.93it/s] [2024-06-04 03:24:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	26%\|██▌ \| 51/195 [00:25<01:14, 1.93it/s] 27%\|██▋ \| 53/195 [00:25<00:50, 2.79it/s] [2024-06-04 03:24:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	27%\|██▋ \| 53/195 [00:25<00:50, 2.79it/s] 28%\|██▊ \| 54/195 [00:25<00:42, 3.29it/s] [2024-06-04 03:24:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	28%\|██▊ \| 54/195 [00:25<00:42, 3.29it/s] [2024-06-04 03:24:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	28%\|██▊ \| 54/195 [00:25<00:42, 3.29it/s] 29%\|██▊ \| 56/195 [00:25<00:35, 3.96it/s] [2024-06-04 03:24:17] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	29%\|██▊ \| 56/195 [00:26<00:35, 3.96it/s] 29%\|██▉ \| 57/195 [00:27<01:10, 1.96it/s] [2024-06-04 03:24:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	29%\|██▉ \| 57/195 [00:27<01:10, 1.96it/s] [2024-06-04 03:24:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	29%\|██▉ \| 57/195 [00:27<01:10, 1.96it/s] 30%\|███ \| 59/195 [00:27<00:47, 2.84it/s] [2024-06-04 03:24:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	30%\|███ \| 59/195 [00:27<00:47, 2.84it/s] 31%\|███ \| 60/195 [00:27<00:40, 3.34it/s] [2024-06-04 03:24:18] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00001-of-00004.safetensors
	31%\|███ \| 60/195 [00:27<00:40, 3.34it/s] [2024-06-04 03:24:18] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00002-of-00004.safetensors
	31%\|███ \| 60/195 [00:27<00:40, 3.34it/s] [2024-06-04 03:24:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	31%\|███ \| 60/195 [00:27<00:40, 3.34it/s] 31%\|███▏ \| 61/195 [00:27<00:37, 3.54it/s] [2024-06-04 03:24:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	31%\|███▏ \| 61/195 [00:27<00:37, 3.54it/s] 32%\|███▏ \| 62/195 [00:28<00:39, 3.34it/s] [2024-06-04 03:24:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	32%\|███▏ \| 62/195 [00:28<00:39, 3.34it/s] 32%\|███▏ \| 63/195 [00:29<01:14, 1.78it/s] [2024-06-04 03:24:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	32%\|███▏ \| 63/195 [00:29<01:14, 1.78it/s] [2024-06-04 03:24:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	32%\|███▏ \| 63/195 [00:29<01:14, 1.78it/s] 33%\|███▎ \| 65/195 [00:29<00:46, 2.78it/s] [2024-06-04 03:24:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	33%\|███▎ \| 65/195 [00:29<00:46, 2.78it/s] 34%\|███▍ \| 66/195 [00:29<00:38, 3.33it/s] [2024-06-04 03:24:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	34%\|███▍ \| 66/195 [00:29<00:38, 3.33it/s] [2024-06-04 03:24:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	34%\|███▍ \| 66/195 [00:29<00:38, 3.33it/s] 35%\|███▍ \| 68/195 [00:30<00:31, 4.03it/s] [2024-06-04 03:24:21] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	35%\|███▍ \| 68/195 [00:30<00:31, 4.03it/s] 35%\|███▌ \| 69/195 [00:31<01:05, 1.93it/s] [2024-06-04 03:24:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	35%\|███▌ \| 69/195 [00:31<01:05, 1.93it/s] [2024-06-04 03:24:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	35%\|███▌ \| 69/195 [00:31<01:05, 1.93it/s] 36%\|███▋ \| 71/195 [00:31<00:43, 2.83it/s] [2024-06-04 03:24:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	36%\|███▋ \| 71/195 [00:31<00:43, 2.83it/s] 37%\|███▋ \| 72/195 [00:31<00:36, 3.32it/s] [2024-06-04 03:24:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	37%\|███▋ \| 72/195 [00:31<00:36, 3.32it/s] [2024-06-04 03:24:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	37%\|███▋ \| 72/195 [00:31<00:36, 3.32it/s] 38%\|███▊ \| 74/195 [00:32<00:30, 4.00it/s] [2024-06-04 03:24:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	38%\|███▊ \| 74/195 [00:32<00:30, 4.00it/s] 38%\|███▊ \| 75/195 [00:33<01:06, 1.79it/s] [2024-06-04 03:24:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	38%\|███▊ \| 75/195 [00:33<01:06, 1.79it/s] [2024-06-04 03:24:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	38%\|███▊ \| 75/195 [00:34<01:06, 1.79it/s] 39%\|███▉ \| 77/195 [00:34<00:44, 2.63it/s] [2024-06-04 03:24:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	39%\|███▉ \| 77/195 [00:34<00:44, 2.63it/s] 40%\|████ \| 78/195 [00:34<00:37, 3.11it/s] [2024-06-04 03:24:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	40%\|████ \| 78/195 [00:34<00:37, 3.11it/s] [2024-06-04 03:24:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	40%\|████ \| 78/195 [00:34<00:37, 3.11it/s] 41%\|████ \| 80/195 [00:34<00:30, 3.79it/s] [2024-06-04 03:24:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	41%\|████ \| 80/195 [00:35<00:30, 3.79it/s] 42%\|████▏ \| 81/195 [00:35<00:57, 1.97it/s] [2024-06-04 03:24:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	42%\|████▏ \| 81/195 [00:35<00:57, 1.97it/s] [2024-06-04 03:24:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	42%\|████▏ \| 81/195 [00:36<00:57, 1.97it/s] 43%\|████▎ \| 83/195 [00:36<00:39, 2.85it/s] [2024-06-04 03:24:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	43%\|████▎ \| 83/195 [00:36<00:39, 2.85it/s] 43%\|████▎ \| 84/195 [00:36<00:33, 3.35it/s] [2024-06-04 03:24:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	43%\|████▎ \| 84/195 [00:36<00:33, 3.35it/s] [2024-06-04 03:24:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	43%\|████▎ \| 84/195 [00:36<00:33, 3.35it/s] 44%\|████▍ \| 86/195 [00:36<00:27, 4.01it/s] [2024-06-04 03:24:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	44%\|████▍ \| 86/195 [00:37<00:27, 4.01it/s] 45%\|████▍ \| 87/195 [00:37<00:52, 2.08it/s] [2024-06-04 03:24:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	45%\|████▍ \| 87/195 [00:37<00:52, 2.08it/s] [2024-06-04 03:24:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	45%\|████▍ \| 87/195 [00:38<00:52, 2.08it/s] 46%\|████▌ \| 89/195 [00:38<00:35, 3.00it/s] [2024-06-04 03:24:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	46%\|████▌ \| 89/195 [00:38<00:35, 3.00it/s] 46%\|████▌ \| 90/195 [00:38<00:29, 3.51it/s] [2024-06-04 03:24:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	46%\|████▌ \| 90/195 [00:38<00:29, 3.51it/s] [2024-06-04 03:24:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	46%\|████▌ \| 90/195 [00:38<00:29, 3.51it/s] 47%\|████▋ \| 92/195 [00:38<00:24, 4.13it/s] [2024-06-04 03:24:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	47%\|████▋ \| 92/195 [00:39<00:24, 4.13it/s] 48%\|████▊ \| 93/195 [00:39<00:48, 2.10it/s] [2024-06-04 03:24:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	48%\|████▊ \| 93/195 [00:39<00:48, 2.10it/s] [2024-06-04 03:24:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	48%\|████▊ \| 93/195 [00:39<00:48, 2.10it/s] 49%\|████▊ \| 95/195 [00:40<00:33, 3.02it/s] [2024-06-04 03:24:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	49%\|████▊ \| 95/195 [00:40<00:33, 3.02it/s] 49%\|████▉ \| 96/195 [00:40<00:27, 3.54it/s] [2024-06-04 03:24:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	49%\|████▉ \| 96/195 [00:40<00:27, 3.54it/s] [2024-06-04 03:24:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	49%\|████▉ \| 96/195 [00:40<00:27, 3.54it/s] 50%\|█████ \| 98/195 [00:40<00:23, 4.13it/s] [2024-06-04 03:24:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	50%\|█████ \| 98/195 [00:41<00:23, 4.13it/s] 51%\|█████ \| 99/195 [00:41<00:41, 2.31it/s] [2024-06-04 03:24:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	51%\|█████ \| 99/195 [00:41<00:41, 2.31it/s] [2024-06-04 03:24:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	51%\|█████ \| 99/195 [00:41<00:41, 2.31it/s] 52%\|█████▏ \| 101/195 [00:41<00:28, 3.31it/s] [2024-06-04 03:24:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	52%\|█████▏ \| 101/195 [00:41<00:28, 3.31it/s] 52%\|█████▏ \| 102/195 [00:41<00:24, 3.85it/s] [2024-06-04 03:24:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	52%\|█████▏ \| 102/195 [00:41<00:24, 3.85it/s] [2024-06-04 03:24:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	52%\|█████▏ \| 102/195 [00:42<00:24, 3.85it/s] 53%\|█████▎ \| 104/195 [00:42<00:20, 4.46it/s] [2024-06-04 03:24:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	53%\|█████▎ \| 104/195 [00:43<00:20, 4.46it/s] 54%\|█████▍ \| 105/195 [00:43<00:43, 2.05it/s] [2024-06-04 03:24:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	54%\|█████▍ \| 105/195 [00:43<00:43, 2.05it/s] [2024-06-04 03:24:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	54%\|█████▍ \| 105/195 [00:43<00:43, 2.05it/s] 55%\|█████▍ \| 107/195 [00:43<00:29, 2.96it/s] [2024-06-04 03:24:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	55%\|█████▍ \| 107/195 [00:43<00:29, 2.96it/s] 55%\|█████▌ \| 108/195 [00:44<00:25, 3.47it/s] [2024-06-04 03:24:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	55%\|█████▌ \| 108/195 [00:44<00:25, 3.47it/s] [2024-06-04 03:24:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	55%\|█████▌ \| 108/195 [00:44<00:25, 3.47it/s] 56%\|█████▋ \| 110/195 [00:44<00:20, 4.09it/s] [2024-06-04 03:24:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	56%\|█████▋ \| 110/195 [00:44<00:20, 4.09it/s] 57%\|█████▋ \| 111/195 [00:45<00:37, 2.25it/s] [2024-06-04 03:24:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	57%\|█████▋ \| 111/195 [00:45<00:37, 2.25it/s] [2024-06-04 03:24:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	57%\|█████▋ \| 111/195 [00:45<00:37, 2.25it/s] 58%\|█████▊ \| 113/195 [00:45<00:25, 3.22it/s] [2024-06-04 03:24:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	58%\|█████▊ \| 113/195 [00:45<00:25, 3.22it/s] 58%\|█████▊ \| 114/195 [00:45<00:21, 3.75it/s] [2024-06-04 03:24:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	58%\|█████▊ \| 114/195 [00:45<00:21, 3.75it/s] [2024-06-04 03:24:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	58%\|█████▊ \| 114/195 [00:45<00:21, 3.75it/s] 59%\|█████▉ \| 116/195 [00:46<00:18, 4.33it/s] [2024-06-04 03:24:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	59%\|█████▉ \| 116/195 [00:46<00:18, 4.33it/s] 60%\|██████ \| 117/195 [00:47<00:35, 2.22it/s] [2024-06-04 03:24:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	60%\|██████ \| 117/195 [00:47<00:35, 2.22it/s] [2024-06-04 03:24:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	60%\|██████ \| 117/195 [00:47<00:35, 2.22it/s] 61%\|██████ \| 119/195 [00:47<00:23, 3.18it/s] [2024-06-04 03:24:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	61%\|██████ \| 119/195 [00:47<00:23, 3.18it/s] 62%\|██████▏ \| 120/195 [00:47<00:20, 3.70it/s] [2024-06-04 03:24:38] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00003-of-00004.safetensors
	62%\|██████▏ \| 120/195 [00:47<00:20, 3.70it/s] [2024-06-04 03:24:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	62%\|██████▏ \| 120/195 [00:48<00:20, 3.70it/s] 62%\|██████▏ \| 121/195 [00:48<00:32, 2.26it/s] [2024-06-04 03:24:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	62%\|██████▏ \| 121/195 [00:48<00:32, 2.26it/s] 63%\|██████▎ \| 122/195 [00:49<00:29, 2.49it/s] [2024-06-04 03:24:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	63%\|██████▎ \| 122/195 [00:49<00:29, 2.49it/s] 63%\|██████▎ \| 123/195 [00:49<00:23, 3.10it/s] [2024-06-04 03:24:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	63%\|██████▎ \| 123/195 [00:49<00:23, 3.10it/s] [2024-06-04 03:24:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	63%\|██████▎ \| 123/195 [00:49<00:23, 3.10it/s] 64%\|██████▍ \| 125/195 [00:49<00:18, 3.88it/s] [2024-06-04 03:24:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	64%\|██████▍ \| 125/195 [00:50<00:18, 3.88it/s] 65%\|██████▍ \| 126/195 [00:50<00:33, 2.07it/s] [2024-06-04 03:24:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	65%\|██████▍ \| 126/195 [00:50<00:33, 2.07it/s] [2024-06-04 03:24:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	65%\|██████▍ \| 126/195 [00:50<00:33, 2.07it/s] 66%\|██████▌ \| 128/195 [00:50<00:21, 3.08it/s] [2024-06-04 03:24:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	66%\|██████▌ \| 128/195 [00:50<00:21, 3.08it/s] 66%\|██████▌ \| 129/195 [00:51<00:18, 3.63it/s] [2024-06-04 03:24:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	66%\|██████▌ \| 129/195 [00:51<00:18, 3.63it/s] [2024-06-04 03:24:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	66%\|██████▌ \| 129/195 [00:51<00:18, 3.63it/s] 67%\|██████▋ \| 131/195 [00:51<00:15, 4.25it/s] [2024-06-04 03:24:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	67%\|██████▋ \| 131/195 [00:51<00:15, 4.25it/s] [2024-06-04 03:24:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	67%\|██████▋ \| 131/195 [00:51<00:15, 4.25it/s] [2024-06-04 03:24:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	67%\|██████▋ \| 131/195 [00:51<00:15, 4.25it/s] 69%\|██████▊ \| 134/195 [00:51<00:11, 5.46it/s] [2024-06-04 03:24:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	69%\|██████▊ \| 134/195 [00:52<00:11, 5.46it/s] 69%\|██████▉ \| 135/195 [00:53<00:24, 2.41it/s] [2024-06-04 03:24:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	69%\|██████▉ \| 135/195 [00:53<00:24, 2.41it/s] [2024-06-04 03:24:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	69%\|██████▉ \| 135/195 [00:53<00:24, 2.41it/s] 70%\|███████ \| 137/195 [00:53<00:17, 3.27it/s] [2024-06-04 03:24:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	70%\|███████ \| 137/195 [00:53<00:17, 3.27it/s] 71%\|███████ \| 138/195 [00:53<00:15, 3.75it/s] [2024-06-04 03:24:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	71%\|███████ \| 138/195 [00:53<00:15, 3.75it/s] [2024-06-04 03:24:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	71%\|███████ \| 138/195 [00:53<00:15, 3.75it/s] 72%\|███████▏ \| 140/195 [00:53<00:12, 4.30it/s] [2024-06-04 03:24:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	72%\|███████▏ \| 140/195 [00:54<00:12, 4.30it/s] 72%\|███████▏ \| 141/195 [00:55<00:23, 2.25it/s] [2024-06-04 03:24:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	72%\|███████▏ \| 141/195 [00:55<00:23, 2.25it/s] [2024-06-04 03:24:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	72%\|███████▏ \| 141/195 [00:55<00:23, 2.25it/s] 73%\|███████▎ \| 143/195 [00:55<00:16, 3.18it/s] [2024-06-04 03:24:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	73%\|███████▎ \| 143/195 [00:55<00:16, 3.18it/s] 74%\|███████▍ \| 144/195 [00:55<00:13, 3.69it/s] [2024-06-04 03:24:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	74%\|███████▍ \| 144/195 [00:55<00:13, 3.69it/s] [2024-06-04 03:24:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	74%\|███████▍ \| 144/195 [00:55<00:13, 3.69it/s] 75%\|███████▍ \| 146/195 [00:55<00:11, 4.24it/s] [2024-06-04 03:24:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	75%\|███████▍ \| 146/195 [00:56<00:11, 4.24it/s] 75%\|███████▌ \| 147/195 [00:56<00:21, 2.25it/s] [2024-06-04 03:24:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	75%\|███████▌ \| 147/195 [00:56<00:21, 2.25it/s] [2024-06-04 03:24:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	75%\|███████▌ \| 147/195 [00:57<00:21, 2.25it/s] 76%\|███████▋ \| 149/195 [00:57<00:14, 3.20it/s] [2024-06-04 03:24:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	76%\|███████▋ \| 149/195 [00:57<00:14, 3.20it/s] 77%\|███████▋ \| 150/195 [00:57<00:12, 3.72it/s] [2024-06-04 03:24:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	77%\|███████▋ \| 150/195 [00:57<00:12, 3.72it/s] [2024-06-04 03:24:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	77%\|███████▋ \| 150/195 [00:57<00:12, 3.72it/s] 78%\|███████▊ \| 152/195 [00:57<00:10, 4.29it/s] [2024-06-04 03:24:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	78%\|███████▊ \| 152/195 [00:57<00:10, 4.29it/s] 78%\|███████▊ \| 153/195 [00:58<00:16, 2.57it/s] [2024-06-04 03:24:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	78%\|███████▊ \| 153/195 [00:58<00:16, 2.57it/s] [2024-06-04 03:24:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	78%\|███████▊ \| 153/195 [00:58<00:16, 2.57it/s] 79%\|███████▉ \| 155/195 [00:58<00:11, 3.63it/s] [2024-06-04 03:24:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	79%\|███████▉ \| 155/195 [00:58<00:11, 3.63it/s] 80%\|████████ \| 156/195 [00:58<00:09, 4.18it/s] [2024-06-04 03:24:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	80%\|████████ \| 156/195 [00:58<00:09, 4.18it/s] [2024-06-04 03:24:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	80%\|████████ \| 156/195 [00:58<00:09, 4.18it/s] 81%\|████████ \| 158/195 [00:59<00:07, 4.71it/s] [2024-06-04 03:24:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	81%\|████████ \| 158/195 [01:00<00:07, 4.71it/s] 82%\|████████▏ \| 159/195 [01:00<00:17, 2.07it/s] [2024-06-04 03:24:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	82%\|████████▏ \| 159/195 [01:00<00:17, 2.07it/s] [2024-06-04 03:24:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	82%\|████████▏ \| 159/195 [01:00<00:17, 2.07it/s] 83%\|████████▎ \| 161/195 [01:00<00:11, 2.98it/s] [2024-06-04 03:24:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	83%\|████████▎ \| 161/195 [01:00<00:11, 2.98it/s] 83%\|████████▎ \| 162/195 [01:00<00:09, 3.49it/s] [2024-06-04 03:24:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	83%\|████████▎ \| 162/195 [01:00<00:09, 3.49it/s] [2024-06-04 03:24:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	83%\|████████▎ \| 162/195 [01:01<00:09, 3.49it/s] 84%\|████████▍ \| 164/195 [01:01<00:07, 4.09it/s] [2024-06-04 03:24:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	84%\|████████▍ \| 164/195 [01:01<00:07, 4.09it/s] 85%\|████████▍ \| 165/195 [01:02<00:11, 2.70it/s] [2024-06-04 03:24:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	85%\|████████▍ \| 165/195 [01:02<00:11, 2.70it/s] [2024-06-04 03:24:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	85%\|████████▍ \| 165/195 [01:02<00:11, 2.70it/s] 86%\|████████▌ \| 167/195 [01:02<00:07, 3.78it/s] [2024-06-04 03:24:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	86%\|████████▌ \| 167/195 [01:02<00:07, 3.78it/s] 86%\|████████▌ \| 168/195 [01:02<00:06, 4.34it/s] [2024-06-04 03:24:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	86%\|████████▌ \| 168/195 [01:02<00:06, 4.34it/s] [2024-06-04 03:24:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	86%\|████████▌ \| 168/195 [01:02<00:06, 4.34it/s] 87%\|████████▋ \| 170/195 [01:02<00:05, 4.78it/s] [2024-06-04 03:24:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	87%\|████████▋ \| 170/195 [01:03<00:05, 4.78it/s] 88%\|████████▊ \| 171/195 [01:03<00:09, 2.58it/s] [2024-06-04 03:24:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	88%\|████████▊ \| 171/195 [01:03<00:09, 2.58it/s] [2024-06-04 03:24:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	88%\|████████▊ \| 171/195 [01:03<00:09, 2.58it/s] 89%\|████████▊ \| 173/195 [01:04<00:06, 3.65it/s] [2024-06-04 03:24:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	89%\|████████▊ \| 173/195 [01:04<00:06, 3.65it/s] 89%\|████████▉ \| 174/195 [01:04<00:04, 4.21it/s] [2024-06-04 03:24:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.28.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	89%\|████████▉ \| 174/195 [01:04<00:04, 4.21it/s] [2024-06-04 03:24:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.28.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	89%\|████████▉ \| 174/195 [01:04<00:04, 4.21it/s] 90%\|█████████ \| 176/195 [01:04<00:04, 4.69it/s] [2024-06-04 03:24:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.28.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	90%\|█████████ \| 176/195 [01:04<00:04, 4.69it/s] 91%\|█████████ \| 177/195 [01:05<00:05, 3.14it/s] [2024-06-04 03:24:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.28.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	91%\|█████████ \| 177/195 [01:05<00:05, 3.14it/s] [2024-06-04 03:24:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.28.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	91%\|█████████ \| 177/195 [01:05<00:05, 3.14it/s] 92%\|█████████▏\| 179/195 [01:05<00:03, 4.35it/s] [2024-06-04 03:24:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.28.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	92%\|█████████▏\| 179/195 [01:05<00:03, 4.35it/s] 92%\|█████████▏\| 180/195 [01:05<00:03, 4.94it/s] [2024-06-04 03:24:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.29.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	92%\|█████████▏\| 180/195 [01:05<00:03, 4.94it/s] [2024-06-04 03:24:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.29.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	92%\|█████████▏\| 180/195 [01:05<00:03, 4.94it/s] 93%\|█████████▎\| 182/195 [01:05<00:02, 5.33it/s] [2024-06-04 03:24:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.29.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	93%\|█████████▎\| 182/195 [01:05<00:02, 5.33it/s] 94%\|█████████▍\| 183/195 [01:06<00:03, 3.20it/s] [2024-06-04 03:24:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.29.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	94%\|█████████▍\| 183/195 [01:06<00:03, 3.20it/s] [2024-06-04 03:24:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.29.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	94%\|█████████▍\| 183/195 [01:06<00:03, 3.20it/s] 95%\|█████████▍\| 185/195 [01:06<00:02, 4.41it/s] [2024-06-04 03:24:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.29.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	95%\|█████████▍\| 185/195 [01:06<00:02, 4.41it/s] 95%\|█████████▌\| 186/195 [01:06<00:01, 5.00it/s] [2024-06-04 03:24:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.30.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	95%\|█████████▌\| 186/195 [01:06<00:01, 5.00it/s] [2024-06-04 03:24:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.30.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	95%\|█████████▌\| 186/195 [01:06<00:01, 5.00it/s] 96%\|█████████▋\| 188/195 [01:07<00:01, 5.38it/s] [2024-06-04 03:24:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.30.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	96%\|█████████▋\| 188/195 [01:07<00:01, 5.38it/s] 97%\|█████████▋\| 189/195 [01:08<00:02, 2.55it/s] [2024-06-04 03:24:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.30.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	97%\|█████████▋\| 189/195 [01:08<00:02, 2.55it/s] [2024-06-04 03:24:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.30.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	97%\|█████████▋\| 189/195 [01:08<00:02, 2.55it/s] 98%\|█████████▊\| 191/195 [01:08<00:01, 3.61it/s] [2024-06-04 03:24:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.30.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	98%\|█████████▊\| 191/195 [01:08<00:01, 3.61it/s] 98%\|█████████▊\| 192/195 [01:08<00:00, 4.16it/s] [2024-06-04 03:24:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.31.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	98%\|█████████▊\| 192/195 [01:08<00:00, 4.16it/s] 99%\|█████████▉\| 193/195 [01:09<00:00, 2.42it/s] [2024-06-04 03:25:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.31.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	99%\|█████████▉\| 193/195 [01:09<00:00, 2.42it/s] 99%\|█████████▉\| 194/195 [01:09<00:00, 2.68it/s] [2024-06-04 03:25:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.31.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	99%\|█████████▉\| 194/195 [01:09<00:00, 2.68it/s] 100%\|██████████\| 195/195 [01:09<00:00, 3.31it/s] 100%\|██████████\| 195/195 [01:09<00:00, 2.79it/s]
	[2024-06-04 03:25:00] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00002-of-00004.safetensors
	[2024-06-04 03:25:01] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00003-of-00004.safetensors
	[2024-06-04 03:25:01] INFO stats.py:77: [92mTime usage[0m: HF loading: 1.232 sec; Pre-quantization mapping: 19.674 sec; Quantization: 0.000 sec
	[2024-06-04 03:25:01] INFO stats.py:91: [92mRAM usage[0m: Peak RAM: 9.235 GB. Total bytes loaded from disk: 14.958 GB
	[2024-06-04 03:25:01] INFO convert_weight.py:155: [92mParameter size[0m after quantization: 14.958 GB
	[2024-06-04 03:25:01] INFO convert_weight.py:160: [92mTotal parameters[0m: 8,030,523,392
	[2024-06-04 03:25:01] INFO convert_weight.py:161: [92mBits per parameter[0m: 16.000
	[2024-06-04 03:25:01] INFO convert_weight.py:166: Saved to directory: [1m/models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC[0m

	All finished, 131 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC/ndarray-cache.json
	/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Hermes-2-Pro-Llama-3-8B --quantization q0f16 --conv-template hermes2_pro_llama3 --output /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC
	[2024-06-06 23:19:12] INFO auto_config.py:116: [92mFound[0m model configuration: /models/Hermes-2-Pro-Llama-3-8B/config.json
	[2024-06-06 23:19:12] INFO auto_config.py:154: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override.
	[2024-06-06 23:19:12] INFO llama_model.py:52: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (8192)
	[2024-06-06 23:19:12] INFO llama_model.py:72: [1mprefill_chunk_size[0m defaults to 2048
	[2024-06-06 23:19:12] INFO config.py:107: Overriding [1mmax_batch_size[0m from 1 to 80
	[2024-06-06 23:19:12] INFO gen_config.py:143: [generation_config.json] Setting [1mbos_token_id[0m: 128000
	[2024-06-06 23:19:12] INFO gen_config.py:143: [generation_config.json] Setting [1meos_token_id[0m: 128003
	[2024-06-06 23:19:12] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer.model
	[2024-06-06 23:19:12] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC/tokenizer.json[0m
	[2024-06-06 23:19:12] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/vocab.json
	[2024-06-06 23:19:12] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/merges.txt
	[2024-06-06 23:19:12] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/added_tokens.json
	[2024-06-06 23:19:12] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer_config.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC/tokenizer_config.json[0m
	[2024-06-06 23:19:12] 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 23:19:12] INFO gen_config.py:32: [System default] Setting [1mpad_token_id[0m: 0
	[2024-06-06 23:19:12] INFO gen_config.py:32: [System default] Setting [1mtemperature[0m: 1.0
	[2024-06-06 23:19:12] INFO gen_config.py:32: [System default] Setting [1mpresence_penalty[0m: 0.0
	[2024-06-06 23:19:12] INFO gen_config.py:32: [System default] Setting [1mfrequency_penalty[0m: 0.0
	[2024-06-06 23:19:12] INFO gen_config.py:32: [System default] Setting [1mrepetition_penalty[0m: 1.0
	[2024-06-06 23:19:12] INFO gen_config.py:32: [System default] Setting [1mtop_p[0m: 1.0
	[2024-06-06 23:19:12] INFO gen_config.py:223: Dumping configuration file to: [1m/models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC/mlc-chat-config.json[0m
	/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Hermes-2-Pro-Llama-3-8B --quantization q0f16 --output /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC
	[2024-06-06 23:19:14] INFO auto_config.py:116: [92mFound[0m model configuration: /models/Hermes-2-Pro-Llama-3-8B/config.json
	[2024-06-06 23:19:15] INFO auto_device.py:79: [92mFound[0m device: cuda:0
	[2024-06-06 23:19:17] INFO auto_device.py:88: [91mNot found[0m device: rocm:0
	[2024-06-06 23:19:18] INFO auto_device.py:88: [91mNot found[0m device: metal:0
	[2024-06-06 23:19:20] INFO auto_device.py:79: [92mFound[0m device: vulkan:0
	[2024-06-06 23:19:20] INFO auto_device.py:79: [92mFound[0m device: vulkan:1
	[2024-06-06 23:19:20] INFO auto_device.py:79: [92mFound[0m device: vulkan:2
	[2024-06-06 23:19:20] INFO auto_device.py:79: [92mFound[0m device: vulkan:3
	[2024-06-06 23:19:21] INFO auto_device.py:88: [91mNot found[0m device: opencl:0
	[2024-06-06 23:19:21] INFO auto_device.py:35: Using device: [1mcuda:0[0m
	[2024-06-06 23:19:21] INFO auto_weight.py:71: Finding weights in: /models/Hermes-2-Pro-Llama-3-8B
	[2024-06-06 23:19:21] INFO auto_weight.py:137: [91mNot found[0m Huggingface PyTorch
	[2024-06-06 23:19:21] INFO auto_weight.py:144: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: /models/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json
	[2024-06-06 23:19:21] INFO auto_weight.py:107: Using source weight configuration: [1m/models/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json[0m. Use `--source` to override.
	[2024-06-06 23:19:21] INFO auto_weight.py:111: Using source weight format: [1mhuggingface-safetensor[0m. Use `--source-format` to override.
	[2024-06-06 23:19:21] INFO auto_config.py:154: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override.
	[2024-06-06 23:19:21] INFO llama_model.py:52: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (8192)
	[2024-06-06 23:19:21] INFO llama_model.py:72: [1mprefill_chunk_size[0m defaults to 2048
	[1mWeight conversion with arguments:[0m
	[1m--config[0m /models/Hermes-2-Pro-Llama-3-8B/config.json
	[1m--quantization[0m NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16')
	[1m--model-type[0m llama
	[1m--device[0m cuda:0
	[1m--source[0m /models/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json
	[1m--source-format[0m huggingface-safetensor
	[1m--output[0m /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC
	Start storing to cache /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC
	0%\| \| 0/195 [00:00<?, ?it/s] [2024-06-06 23:19:23] 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 23:19:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mlm_head.weight[0m", shape: (128288, 4096), dtype: float16
	0%\| \| 0/195 [00:02<?, ?it/s] 1%\| \| 1/195 [00:09<30:00, 9.28s/it] [2024-06-06 23:19:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.31.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	1%\| \| 1/195 [00:09<30:00, 9.28s/it] 1%\| \| 2/195 [00:09<12:31, 3.90s/it] [2024-06-06 23:19:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.31.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	1%\| \| 2/195 [00:09<12:31, 3.90s/it] 2%\|▏ \| 3/195 [00:09<07:38, 2.39s/it] [2024-06-06 23:19:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.31.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	2%\|▏ \| 3/195 [00:09<07:38, 2.39s/it] [2024-06-06 23:19:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.norm.weight[0m", shape: (4096,), dtype: float16
	2%\|▏ \| 3/195 [00:10<07:38, 2.39s/it] [2024-06-06 23:19:33] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00004-of-00004.safetensors
	2%\|▏ \| 3/195 [00:10<07:38, 2.39s/it] [2024-06-06 23:19:33] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00001-of-00004.safetensors
	2%\|▏ \| 3/195 [00:10<07:38, 2.39s/it] [2024-06-06 23:19:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.embed_tokens.weight[0m", shape: (128288, 4096), dtype: float16
	2%\|▏ \| 3/195 [00:10<07:38, 2.39s/it] 3%\|▎ \| 6/195 [00:15<06:36, 2.10s/it] [2024-06-06 23:19:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	3%\|▎ \| 6/195 [00:15<06:36, 2.10s/it] [2024-06-06 23:19:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	3%\|▎ \| 6/195 [00:15<06:36, 2.10s/it] 4%\|▍ \| 8/195 [00:16<04:25, 1.42s/it] [2024-06-06 23:19:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	4%\|▍ \| 8/195 [00:16<04:25, 1.42s/it] 5%\|▍ \| 9/195 [00:17<04:16, 1.38s/it] [2024-06-06 23:19:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	5%\|▍ \| 9/195 [00:17<04:16, 1.38s/it] [2024-06-06 23:19:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	5%\|▍ \| 9/195 [00:17<04:16, 1.38s/it] 6%\|▌ \| 11/195 [00:18<02:46, 1.11it/s] [2024-06-06 23:19:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	6%\|▌ \| 11/195 [00:18<02:46, 1.11it/s] 6%\|▌ \| 12/195 [00:18<02:17, 1.33it/s] [2024-06-06 23:19:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	6%\|▌ \| 12/195 [00:18<02:17, 1.33it/s] [2024-06-06 23:19:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	6%\|▌ \| 12/195 [00:18<02:17, 1.33it/s] 7%\|▋ \| 14/195 [00:18<01:44, 1.73it/s] [2024-06-06 23:19:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	7%\|▋ \| 14/195 [00:18<01:44, 1.73it/s] 8%\|▊ \| 15/195 [00:20<02:07, 1.41it/s] [2024-06-06 23:19:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	8%\|▊ \| 15/195 [00:20<02:07, 1.41it/s] [2024-06-06 23:19:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	8%\|▊ \| 15/195 [00:20<02:07, 1.41it/s] 9%\|▊ \| 17/195 [00:20<01:28, 2.01it/s] [2024-06-06 23:19:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	9%\|▊ \| 17/195 [00:20<01:28, 2.01it/s] 9%\|▉ \| 18/195 [00:20<01:16, 2.33it/s] [2024-06-06 23:19:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	9%\|▉ \| 18/195 [00:20<01:16, 2.33it/s] [2024-06-06 23:19:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	9%\|▉ \| 18/195 [00:20<01:16, 2.33it/s] 10%\|█ \| 20/195 [00:21<01:06, 2.62it/s] [2024-06-06 23:19:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	10%\|█ \| 20/195 [00:21<01:06, 2.62it/s] 11%\|█ \| 21/195 [00:22<01:35, 1.82it/s] [2024-06-06 23:19:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	11%\|█ \| 21/195 [00:22<01:35, 1.82it/s] [2024-06-06 23:19:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	11%\|█ \| 21/195 [00:22<01:35, 1.82it/s] 12%\|█▏ \| 23/195 [00:22<01:07, 2.54it/s] [2024-06-06 23:19:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	12%\|█▏ \| 23/195 [00:22<01:07, 2.54it/s] 12%\|█▏ \| 24/195 [00:22<00:59, 2.85it/s] [2024-06-06 23:19:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	12%\|█▏ \| 24/195 [00:22<00:59, 2.85it/s] [2024-06-06 23:19:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	12%\|█▏ \| 24/195 [00:22<00:59, 2.85it/s] 13%\|█▎ \| 26/195 [00:23<00:55, 3.06it/s] [2024-06-06 23:19:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	13%\|█▎ \| 26/195 [00:23<00:55, 3.06it/s] 14%\|█▍ \| 27/195 [00:24<01:25, 1.97it/s] [2024-06-06 23:19:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	14%\|█▍ \| 27/195 [00:24<01:25, 1.97it/s] [2024-06-06 23:19:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	14%\|█▍ \| 27/195 [00:24<01:25, 1.97it/s] 15%\|█▍ \| 29/195 [00:24<01:00, 2.74it/s] [2024-06-06 23:19:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	15%\|█▍ \| 29/195 [00:24<01:00, 2.74it/s] 15%\|█▌ \| 30/195 [00:24<00:53, 3.07it/s] [2024-06-06 23:19:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	15%\|█▌ \| 30/195 [00:24<00:53, 3.07it/s] [2024-06-06 23:19:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	15%\|█▌ \| 30/195 [00:24<00:53, 3.07it/s] 16%\|█▋ \| 32/195 [00:25<00:50, 3.25it/s] [2024-06-06 23:19:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	16%\|█▋ \| 32/195 [00:25<00:50, 3.25it/s] 17%\|█▋ \| 33/195 [00:26<01:26, 1.88it/s] [2024-06-06 23:19:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	17%\|█▋ \| 33/195 [00:26<01:26, 1.88it/s] [2024-06-06 23:19:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	17%\|█▋ \| 33/195 [00:26<01:26, 1.88it/s] 18%\|█▊ \| 35/195 [00:27<01:00, 2.63it/s] [2024-06-06 23:19:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	18%\|█▊ \| 35/195 [00:27<01:00, 2.63it/s] 18%\|█▊ \| 36/195 [00:27<00:53, 2.97it/s] [2024-06-06 23:19:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	18%\|█▊ \| 36/195 [00:27<00:53, 2.97it/s] [2024-06-06 23:19:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	18%\|█▊ \| 36/195 [00:27<00:53, 2.97it/s] 19%\|█▉ \| 38/195 [00:27<00:49, 3.16it/s] [2024-06-06 23:19:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	19%\|█▉ \| 38/195 [00:28<00:49, 3.16it/s] 20%\|██ \| 39/195 [00:29<01:45, 1.48it/s] [2024-06-06 23:19:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	20%\|██ \| 39/195 [00:29<01:45, 1.48it/s] [2024-06-06 23:19:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	20%\|██ \| 39/195 [00:29<01:45, 1.48it/s] 21%\|██ \| 41/195 [00:30<01:13, 2.10it/s] [2024-06-06 23:19:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	21%\|██ \| 41/195 [00:30<01:13, 2.10it/s] 22%\|██▏ \| 42/195 [00:30<01:03, 2.43it/s] [2024-06-06 23:19:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	22%\|██▏ \| 42/195 [00:30<01:03, 2.43it/s] [2024-06-06 23:19:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	22%\|██▏ \| 42/195 [00:30<01:03, 2.43it/s] 23%\|██▎ \| 44/195 [00:30<00:54, 2.75it/s] [2024-06-06 23:19:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	23%\|██▎ \| 44/195 [00:31<00:54, 2.75it/s] 23%\|██▎ \| 45/195 [00:32<01:34, 1.58it/s] [2024-06-06 23:19:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	23%\|██▎ \| 45/195 [00:32<01:34, 1.58it/s] [2024-06-06 23:19:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	23%\|██▎ \| 45/195 [00:32<01:34, 1.58it/s] 24%\|██▍ \| 47/195 [00:32<01:06, 2.23it/s] [2024-06-06 23:19:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	24%\|██▍ \| 47/195 [00:32<01:06, 2.23it/s] 25%\|██▍ \| 48/195 [00:32<00:57, 2.54it/s] [2024-06-06 23:19:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	25%\|██▍ \| 48/195 [00:32<00:57, 2.54it/s] [2024-06-06 23:19:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	25%\|██▍ \| 48/195 [00:33<00:57, 2.54it/s] 26%\|██▌ \| 50/195 [00:33<00:50, 2.84it/s] [2024-06-06 23:19:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	26%\|██▌ \| 50/195 [00:33<00:50, 2.84it/s] 26%\|██▌ \| 51/195 [00:35<01:28, 1.63it/s] [2024-06-06 23:19:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	26%\|██▌ \| 51/195 [00:35<01:28, 1.63it/s] [2024-06-06 23:19:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	26%\|██▌ \| 51/195 [00:35<01:28, 1.63it/s] 27%\|██▋ \| 53/195 [00:35<01:01, 2.32it/s] [2024-06-06 23:19:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	27%\|██▋ \| 53/195 [00:35<01:01, 2.32it/s] 28%\|██▊ \| 54/195 [00:35<00:52, 2.68it/s] [2024-06-06 23:19:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	28%\|██▊ \| 54/195 [00:35<00:52, 2.68it/s] [2024-06-06 23:19:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	28%\|██▊ \| 54/195 [00:35<00:52, 2.68it/s] 29%\|██▊ \| 56/195 [00:36<00:47, 2.94it/s] [2024-06-06 23:20:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	29%\|██▊ \| 56/195 [00:36<00:47, 2.94it/s] 29%\|██▉ \| 57/195 [00:38<01:34, 1.46it/s] [2024-06-06 23:20:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	29%\|██▉ \| 57/195 [00:38<01:34, 1.46it/s] [2024-06-06 23:20:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	29%\|██▉ \| 57/195 [00:38<01:34, 1.46it/s] 30%\|███ \| 59/195 [00:38<01:05, 2.09it/s] [2024-06-06 23:20:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	30%\|███ \| 59/195 [00:38<01:05, 2.09it/s] 31%\|███ \| 60/195 [00:38<00:56, 2.40it/s] [2024-06-06 23:20:02] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00001-of-00004.safetensors
	31%\|███ \| 60/195 [00:38<00:56, 2.40it/s] [2024-06-06 23:20:02] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00002-of-00004.safetensors
	31%\|███ \| 60/195 [00:38<00:56, 2.40it/s] [2024-06-06 23:20:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	31%\|███ \| 60/195 [00:38<00:56, 2.40it/s] 31%\|███▏ \| 61/195 [00:38<00:49, 2.71it/s] [2024-06-06 23:20:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	31%\|███▏ \| 61/195 [00:38<00:49, 2.71it/s] 32%\|███▏ \| 62/195 [00:39<00:56, 2.34it/s] [2024-06-06 23:20:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	32%\|███▏ \| 62/195 [00:40<00:56, 2.34it/s] 32%\|███▏ \| 63/195 [00:41<01:58, 1.12it/s] [2024-06-06 23:20:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	32%\|███▏ \| 63/195 [00:41<01:58, 1.12it/s] [2024-06-06 23:20:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	32%\|███▏ \| 63/195 [00:41<01:58, 1.12it/s] 33%\|███▎ \| 65/195 [00:41<01:14, 1.74it/s] [2024-06-06 23:20:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	33%\|███▎ \| 65/195 [00:41<01:14, 1.74it/s] 34%\|███▍ \| 66/195 [00:42<01:02, 2.06it/s] [2024-06-06 23:20:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	34%\|███▍ \| 66/195 [00:42<01:02, 2.06it/s] [2024-06-06 23:20:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	34%\|███▍ \| 66/195 [00:42<01:02, 2.06it/s] 35%\|███▍ \| 68/195 [00:42<00:51, 2.45it/s] [2024-06-06 23:20:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	35%\|███▍ \| 68/195 [00:43<00:51, 2.45it/s] 35%\|███▌ \| 69/195 [00:44<01:30, 1.40it/s] [2024-06-06 23:20:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	35%\|███▌ \| 69/195 [00:44<01:30, 1.40it/s] [2024-06-06 23:20:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	35%\|███▌ \| 69/195 [00:44<01:30, 1.40it/s] 36%\|███▋ \| 71/195 [00:44<01:01, 2.03it/s] [2024-06-06 23:20:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	36%\|███▋ \| 71/195 [00:44<01:01, 2.03it/s] 37%\|███▋ \| 72/195 [00:44<00:52, 2.36it/s] [2024-06-06 23:20:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	37%\|███▋ \| 72/195 [00:44<00:52, 2.36it/s] [2024-06-06 23:20:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	37%\|███▋ \| 72/195 [00:44<00:52, 2.36it/s] 38%\|███▊ \| 74/195 [00:45<00:45, 2.65it/s] [2024-06-06 23:20:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	38%\|███▊ \| 74/195 [00:46<00:45, 2.65it/s] 38%\|███▊ \| 75/195 [00:47<01:18, 1.52it/s] [2024-06-06 23:20:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	38%\|███▊ \| 75/195 [00:47<01:18, 1.52it/s] [2024-06-06 23:20:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	38%\|███▊ \| 75/195 [00:47<01:18, 1.52it/s] 39%\|███▉ \| 77/195 [00:47<00:54, 2.16it/s] [2024-06-06 23:20:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	39%\|███▉ \| 77/195 [00:47<00:54, 2.16it/s] 40%\|████ \| 78/195 [00:47<00:47, 2.49it/s] [2024-06-06 23:20:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	40%\|████ \| 78/195 [00:47<00:47, 2.49it/s] [2024-06-06 23:20:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	40%\|████ \| 78/195 [00:47<00:47, 2.49it/s] 41%\|████ \| 80/195 [00:48<00:41, 2.75it/s] [2024-06-06 23:20:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	41%\|████ \| 80/195 [00:48<00:41, 2.75it/s] 42%\|████▏ \| 81/195 [00:49<01:11, 1.59it/s] [2024-06-06 23:20:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	42%\|████▏ \| 81/195 [00:49<01:11, 1.59it/s] [2024-06-06 23:20:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	42%\|████▏ \| 81/195 [00:49<01:11, 1.59it/s] 43%\|████▎ \| 83/195 [00:50<00:49, 2.26it/s] [2024-06-06 23:20:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	43%\|████▎ \| 83/195 [00:50<00:49, 2.26it/s] 43%\|████▎ \| 84/195 [00:50<00:42, 2.59it/s] [2024-06-06 23:20:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	43%\|████▎ \| 84/195 [00:50<00:42, 2.59it/s] [2024-06-06 23:20:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	43%\|████▎ \| 84/195 [00:50<00:42, 2.59it/s] 44%\|████▍ \| 86/195 [00:50<00:38, 2.86it/s] [2024-06-06 23:20:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	44%\|████▍ \| 86/195 [00:51<00:38, 2.86it/s] 45%\|████▍ \| 87/195 [00:52<01:09, 1.56it/s] [2024-06-06 23:20:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	45%\|████▍ \| 87/195 [00:52<01:09, 1.56it/s] [2024-06-06 23:20:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	45%\|████▍ \| 87/195 [00:52<01:09, 1.56it/s] 46%\|████▌ \| 89/195 [00:52<00:48, 2.21it/s] [2024-06-06 23:20:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	46%\|████▌ \| 89/195 [00:52<00:48, 2.21it/s] 46%\|████▌ \| 90/195 [00:53<00:41, 2.53it/s] [2024-06-06 23:20:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	46%\|████▌ \| 90/195 [00:53<00:41, 2.53it/s] [2024-06-06 23:20:17] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	46%\|████▌ \| 90/195 [00:53<00:41, 2.53it/s] 47%\|████▋ \| 92/195 [00:53<00:36, 2.83it/s] [2024-06-06 23:20:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	47%\|████▋ \| 92/195 [00:54<00:36, 2.83it/s] 48%\|████▊ \| 93/195 [00:55<01:07, 1.52it/s] [2024-06-06 23:20:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	48%\|████▊ \| 93/195 [00:55<01:07, 1.52it/s] [2024-06-06 23:20:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	48%\|████▊ \| 93/195 [00:55<01:07, 1.52it/s] 49%\|████▊ \| 95/195 [00:55<00:46, 2.14it/s] [2024-06-06 23:20:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	49%\|████▊ \| 95/195 [00:55<00:46, 2.14it/s] 49%\|████▉ \| 96/195 [00:55<00:40, 2.47it/s] [2024-06-06 23:20:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	49%\|████▉ \| 96/195 [00:55<00:40, 2.47it/s] [2024-06-06 23:20:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	49%\|████▉ \| 96/195 [00:55<00:40, 2.47it/s] 50%\|█████ \| 98/195 [00:56<00:35, 2.75it/s] [2024-06-06 23:20:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	50%\|█████ \| 98/195 [00:57<00:35, 2.75it/s] 51%\|█████ \| 99/195 [00:58<01:03, 1.51it/s] [2024-06-06 23:20:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	51%\|█████ \| 99/195 [00:58<01:03, 1.51it/s] [2024-06-06 23:20:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	51%\|█████ \| 99/195 [00:58<01:03, 1.51it/s] 52%\|█████▏ \| 101/195 [00:58<00:43, 2.14it/s] [2024-06-06 23:20:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	52%\|█████▏ \| 101/195 [00:58<00:43, 2.14it/s] 52%\|█████▏ \| 102/195 [00:58<00:37, 2.47it/s] [2024-06-06 23:20:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	52%\|█████▏ \| 102/195 [00:58<00:37, 2.47it/s] [2024-06-06 23:20:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	52%\|█████▏ \| 102/195 [00:58<00:37, 2.47it/s] 53%\|█████▎ \| 104/195 [00:59<00:33, 2.74it/s] [2024-06-06 23:20:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	53%\|█████▎ \| 104/195 [00:59<00:33, 2.74it/s] 54%\|█████▍ \| 105/195 [01:01<01:00, 1.48it/s] [2024-06-06 23:20:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	54%\|█████▍ \| 105/195 [01:01<01:00, 1.48it/s] [2024-06-06 23:20:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	54%\|█████▍ \| 105/195 [01:01<01:00, 1.48it/s] 55%\|█████▍ \| 107/195 [01:01<00:41, 2.12it/s] [2024-06-06 23:20:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	55%\|█████▍ \| 107/195 [01:01<00:41, 2.12it/s] 55%\|█████▌ \| 108/195 [01:01<00:35, 2.44it/s] [2024-06-06 23:20:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	55%\|█████▌ \| 108/195 [01:01<00:35, 2.44it/s] [2024-06-06 23:20:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	55%\|█████▌ \| 108/195 [01:01<00:35, 2.44it/s] 56%\|█████▋ \| 110/195 [01:02<00:31, 2.73it/s] [2024-06-06 23:20:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	56%\|█████▋ \| 110/195 [01:02<00:31, 2.73it/s] 57%\|█████▋ \| 111/195 [01:04<00:56, 1.48it/s] [2024-06-06 23:20:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	57%\|█████▋ \| 111/195 [01:04<00:56, 1.48it/s] [2024-06-06 23:20:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	57%\|█████▋ \| 111/195 [01:04<00:56, 1.48it/s] 58%\|█████▊ \| 113/195 [01:04<00:38, 2.11it/s] [2024-06-06 23:20:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	58%\|█████▊ \| 113/195 [01:04<00:38, 2.11it/s] 58%\|█████▊ \| 114/195 [01:04<00:33, 2.43it/s] [2024-06-06 23:20:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	58%\|█████▊ \| 114/195 [01:04<00:33, 2.43it/s] [2024-06-06 23:20:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	58%\|█████▊ \| 114/195 [01:04<00:33, 2.43it/s] 59%\|█████▉ \| 116/195 [01:05<00:28, 2.75it/s] [2024-06-06 23:20:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	59%\|█████▉ \| 116/195 [01:05<00:28, 2.75it/s] 60%\|██████ \| 117/195 [01:07<00:54, 1.43it/s] [2024-06-06 23:20:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	60%\|██████ \| 117/195 [01:07<00:54, 1.43it/s] [2024-06-06 23:20:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	60%\|██████ \| 117/195 [01:07<00:54, 1.43it/s] 61%\|██████ \| 119/195 [01:07<00:37, 2.04it/s] [2024-06-06 23:20:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	61%\|██████ \| 119/195 [01:07<00:37, 2.04it/s] 62%\|██████▏ \| 120/195 [01:07<00:31, 2.36it/s] [2024-06-06 23:20:31] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00003-of-00004.safetensors
	62%\|██████▏ \| 120/195 [01:07<00:31, 2.36it/s] [2024-06-06 23:20:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	62%\|██████▏ \| 120/195 [01:08<00:31, 2.36it/s] 62%\|██████▏ \| 121/195 [01:09<00:55, 1.32it/s] [2024-06-06 23:20:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	62%\|██████▏ \| 121/195 [01:09<00:55, 1.32it/s] 63%\|██████▎ \| 122/195 [01:09<00:50, 1.46it/s] [2024-06-06 23:20:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	63%\|██████▎ \| 122/195 [01:09<00:50, 1.46it/s] 63%\|██████▎ \| 123/195 [01:10<00:39, 1.81it/s] [2024-06-06 23:20:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	63%\|██████▎ \| 123/195 [01:10<00:39, 1.81it/s] [2024-06-06 23:20:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	63%\|██████▎ \| 123/195 [01:10<00:39, 1.81it/s] 64%\|██████▍ \| 125/195 [01:10<00:31, 2.24it/s] [2024-06-06 23:20:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	64%\|██████▍ \| 125/195 [01:11<00:31, 2.24it/s] 65%\|██████▍ \| 126/195 [01:12<00:57, 1.20it/s] [2024-06-06 23:20:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	65%\|██████▍ \| 126/195 [01:12<00:57, 1.20it/s] [2024-06-06 23:20:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	65%\|██████▍ \| 126/195 [01:12<00:57, 1.20it/s] 66%\|██████▌ \| 128/195 [01:12<00:37, 1.80it/s] [2024-06-06 23:20:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	66%\|██████▌ \| 128/195 [01:13<00:37, 1.80it/s] 66%\|██████▌ \| 129/195 [01:13<00:31, 2.11it/s] [2024-06-06 23:20:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	66%\|██████▌ \| 129/195 [01:13<00:31, 2.11it/s] [2024-06-06 23:20:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	66%\|██████▌ \| 129/195 [01:13<00:31, 2.11it/s] 67%\|██████▋ \| 131/195 [01:13<00:26, 2.45it/s] [2024-06-06 23:20:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	67%\|██████▋ \| 131/195 [01:13<00:26, 2.45it/s] [2024-06-06 23:20:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	67%\|██████▋ \| 131/195 [01:13<00:26, 2.45it/s] [2024-06-06 23:20:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	67%\|██████▋ \| 131/195 [01:13<00:26, 2.45it/s] 69%\|██████▊ \| 134/195 [01:14<00:19, 3.21it/s] [2024-06-06 23:20:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	69%\|██████▊ \| 134/195 [01:14<00:19, 3.21it/s] 69%\|██████▉ \| 135/195 [01:16<00:34, 1.72it/s] [2024-06-06 23:20:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	69%\|██████▉ \| 135/195 [01:16<00:34, 1.72it/s] [2024-06-06 23:20:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	69%\|██████▉ \| 135/195 [01:16<00:34, 1.72it/s] 70%\|███████ \| 137/195 [01:16<00:24, 2.33it/s] [2024-06-06 23:20:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	70%\|███████ \| 137/195 [01:16<00:24, 2.33it/s] 71%\|███████ \| 138/195 [01:16<00:21, 2.62it/s] [2024-06-06 23:20:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	71%\|███████ \| 138/195 [01:16<00:21, 2.62it/s] [2024-06-06 23:20:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	71%\|███████ \| 138/195 [01:16<00:21, 2.62it/s] 72%\|███████▏ \| 140/195 [01:17<00:18, 2.90it/s] [2024-06-06 23:20:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	72%\|███████▏ \| 140/195 [01:18<00:18, 2.90it/s] 72%\|███████▏ \| 141/195 [01:19<00:36, 1.49it/s] [2024-06-06 23:20:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	72%\|███████▏ \| 141/195 [01:19<00:36, 1.49it/s] [2024-06-06 23:20:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	72%\|███████▏ \| 141/195 [01:19<00:36, 1.49it/s] 73%\|███████▎ \| 143/195 [01:19<00:24, 2.10it/s] [2024-06-06 23:20:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	73%\|███████▎ \| 143/195 [01:19<00:24, 2.10it/s] 74%\|███████▍ \| 144/195 [01:19<00:21, 2.41it/s] [2024-06-06 23:20:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	74%\|███████▍ \| 144/195 [01:19<00:21, 2.41it/s] [2024-06-06 23:20:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	74%\|███████▍ \| 144/195 [01:19<00:21, 2.41it/s] 75%\|███████▍ \| 146/195 [01:20<00:17, 2.73it/s] [2024-06-06 23:20:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	75%\|███████▍ \| 146/195 [01:20<00:17, 2.73it/s] 75%\|███████▌ \| 147/195 [01:22<00:34, 1.37it/s] [2024-06-06 23:20:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	75%\|███████▌ \| 147/195 [01:22<00:34, 1.37it/s] [2024-06-06 23:20:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	75%\|███████▌ \| 147/195 [01:22<00:34, 1.37it/s] 76%\|███████▋ \| 149/195 [01:22<00:23, 1.96it/s] [2024-06-06 23:20:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	76%\|███████▋ \| 149/195 [01:22<00:23, 1.96it/s] 77%\|███████▋ \| 150/195 [01:22<00:19, 2.28it/s] [2024-06-06 23:20:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	77%\|███████▋ \| 150/195 [01:22<00:19, 2.28it/s] [2024-06-06 23:20:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	77%\|███████▋ \| 150/195 [01:22<00:19, 2.28it/s] 78%\|███████▊ \| 152/195 [01:23<00:16, 2.59it/s] [2024-06-06 23:20:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	78%\|███████▊ \| 152/195 [01:23<00:16, 2.59it/s] 78%\|███████▊ \| 153/195 [01:25<00:28, 1.48it/s] [2024-06-06 23:20:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	78%\|███████▊ \| 153/195 [01:25<00:28, 1.48it/s] [2024-06-06 23:20:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	78%\|███████▊ \| 153/195 [01:25<00:28, 1.48it/s] 79%\|███████▉ \| 155/195 [01:25<00:18, 2.11it/s] [2024-06-06 23:20:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	79%\|███████▉ \| 155/195 [01:25<00:18, 2.11it/s] 80%\|████████ \| 156/195 [01:25<00:16, 2.43it/s] [2024-06-06 23:20:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	80%\|████████ \| 156/195 [01:25<00:16, 2.43it/s] [2024-06-06 23:20:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	80%\|████████ \| 156/195 [01:25<00:16, 2.43it/s] 81%\|████████ \| 158/195 [01:26<00:13, 2.72it/s] [2024-06-06 23:20:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	81%\|████████ \| 158/195 [01:26<00:13, 2.72it/s] 82%\|████████▏ \| 159/195 [01:28<00:24, 1.44it/s] [2024-06-06 23:20:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	82%\|████████▏ \| 159/195 [01:28<00:24, 1.44it/s] [2024-06-06 23:20:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	82%\|████████▏ \| 159/195 [01:28<00:24, 1.44it/s] 83%\|████████▎ \| 161/195 [01:28<00:16, 2.05it/s] [2024-06-06 23:20:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	83%\|████████▎ \| 161/195 [01:28<00:16, 2.05it/s] 83%\|████████▎ \| 162/195 [01:28<00:13, 2.37it/s] [2024-06-06 23:20:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	83%\|████████▎ \| 162/195 [01:28<00:13, 2.37it/s] [2024-06-06 23:20:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	83%\|████████▎ \| 162/195 [01:28<00:13, 2.37it/s] 84%\|████████▍ \| 164/195 [01:29<00:11, 2.70it/s] [2024-06-06 23:20:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	84%\|████████▍ \| 164/195 [01:29<00:11, 2.70it/s] 85%\|████████▍ \| 165/195 [01:31<00:21, 1.42it/s] [2024-06-06 23:20:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	85%\|████████▍ \| 165/195 [01:31<00:21, 1.42it/s] [2024-06-06 23:20:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	85%\|████████▍ \| 165/195 [01:31<00:21, 1.42it/s] 86%\|████████▌ \| 167/195 [01:31<00:13, 2.02it/s] [2024-06-06 23:20:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	86%\|████████▌ \| 167/195 [01:31<00:13, 2.02it/s] 86%\|████████▌ \| 168/195 [01:31<00:11, 2.33it/s] [2024-06-06 23:20:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	86%\|████████▌ \| 168/195 [01:31<00:11, 2.33it/s] [2024-06-06 23:20:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	86%\|████████▌ \| 168/195 [01:31<00:11, 2.33it/s] 87%\|████████▋ \| 170/195 [01:32<00:09, 2.63it/s] [2024-06-06 23:20:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	87%\|████████▋ \| 170/195 [01:32<00:09, 2.63it/s] 88%\|████████▊ \| 171/195 [01:34<00:17, 1.37it/s] [2024-06-06 23:20:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	88%\|████████▊ \| 171/195 [01:34<00:17, 1.37it/s] [2024-06-06 23:20:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	88%\|████████▊ \| 171/195 [01:34<00:17, 1.37it/s] 89%\|████████▊ \| 173/195 [01:34<00:11, 1.96it/s] [2024-06-06 23:20:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	89%\|████████▊ \| 173/195 [01:34<00:11, 1.96it/s] 89%\|████████▉ \| 174/195 [01:34<00:09, 2.27it/s] [2024-06-06 23:20:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.28.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	89%\|████████▉ \| 174/195 [01:34<00:09, 2.27it/s] [2024-06-06 23:20:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.28.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	89%\|████████▉ \| 174/195 [01:34<00:09, 2.27it/s] 90%\|█████████ \| 176/195 [01:35<00:07, 2.58it/s] [2024-06-06 23:20:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.28.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	90%\|█████████ \| 176/195 [01:35<00:07, 2.58it/s] 91%\|█████████ \| 177/195 [01:37<00:12, 1.44it/s] [2024-06-06 23:21:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.28.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	91%\|█████████ \| 177/195 [01:37<00:12, 1.44it/s] [2024-06-06 23:21:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.28.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	91%\|█████████ \| 177/195 [01:37<00:12, 1.44it/s] 92%\|█████████▏\| 179/195 [01:37<00:07, 2.06it/s] [2024-06-06 23:21:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.28.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	92%\|█████████▏\| 179/195 [01:37<00:07, 2.06it/s] 92%\|█████████▏\| 180/195 [01:37<00:06, 2.36it/s] [2024-06-06 23:21:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.29.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	92%\|█████████▏\| 180/195 [01:37<00:06, 2.36it/s] [2024-06-06 23:21:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.29.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	92%\|█████████▏\| 180/195 [01:37<00:06, 2.36it/s] 93%\|█████████▎\| 182/195 [01:38<00:04, 2.68it/s] [2024-06-06 23:21:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.29.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	93%\|█████████▎\| 182/195 [01:38<00:04, 2.68it/s] 94%\|█████████▍\| 183/195 [01:40<00:08, 1.37it/s] [2024-06-06 23:21:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.29.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	94%\|█████████▍\| 183/195 [01:40<00:08, 1.37it/s] [2024-06-06 23:21:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.29.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	94%\|█████████▍\| 183/195 [01:40<00:08, 1.37it/s] 95%\|█████████▍\| 185/195 [01:40<00:05, 1.96it/s] [2024-06-06 23:21:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.29.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	95%\|█████████▍\| 185/195 [01:40<00:05, 1.96it/s] 95%\|█████████▌\| 186/195 [01:40<00:03, 2.28it/s] [2024-06-06 23:21:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.30.input_layernorm.weight[0m", shape: (4096,), dtype: float16
	95%\|█████████▌\| 186/195 [01:40<00:03, 2.28it/s] [2024-06-06 23:21:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.30.mlp.down_proj.weight[0m", shape: (4096, 14336), dtype: float16
	95%\|█████████▌\| 186/195 [01:40<00:03, 2.28it/s] 96%\|█████████▋\| 188/195 [01:41<00:02, 2.57it/s] [2024-06-06 23:21:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.30.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	96%\|█████████▋\| 188/195 [01:42<00:02, 2.57it/s] 97%\|█████████▋\| 189/195 [01:43<00:04, 1.38it/s] [2024-06-06 23:21:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.30.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float16
	97%\|█████████▋\| 189/195 [01:43<00:04, 1.38it/s] [2024-06-06 23:21:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.30.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	97%\|█████████▋\| 189/195 [01:43<00:04, 1.38it/s] 98%\|█████████▊\| 191/195 [01:43<00:02, 1.98it/s] [2024-06-06 23:21:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.30.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	98%\|█████████▊\| 191/195 [01:43<00:02, 1.98it/s] 98%\|█████████▊\| 192/195 [01:43<00:01, 2.29it/s] [2024-06-06 23:21:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.31.mlp.gate_up_proj.weight[0m", shape: (28672, 4096), dtype: float16
	98%\|█████████▊\| 192/195 [01:44<00:01, 2.29it/s] 99%\|█████████▉\| 193/195 [01:45<00:01, 1.35it/s] [2024-06-06 23:21:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.31.self_attn.qkv_proj.weight[0m", shape: (6144, 4096), dtype: float16
	99%\|█████████▉\| 193/195 [01:45<00:01, 1.35it/s] 99%\|█████████▉\| 194/195 [01:45<00:00, 1.53it/s] [2024-06-06 23:21:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.31.self_attn.o_proj.weight[0m", shape: (4096, 4096), dtype: float16
	99%\|█████████▉\| 194/195 [01:45<00:00, 1.53it/s] 100%\|██████████\| 195/195 [01:46<00:00, 1.89it/s] 100%\|██████████\| 195/195 [01:46<00:00, 1.84it/s]
	[2024-06-06 23:21:09] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00002-of-00004.safetensors
	[2024-06-06 23:21:10] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00003-of-00004.safetensors
	[2024-06-06 23:21:10] INFO stats.py:77: [92mTime usage[0m: HF loading: 1.354 sec; Pre-quantization mapping: 21.990 sec; Quantization: 0.000 sec
	[2024-06-06 23:21:10] INFO stats.py:91: [92mRAM usage[0m: Peak RAM: 9.235 GB. Total bytes loaded from disk: 14.958 GB
	[2024-06-06 23:21:10] INFO convert_weight.py:155: [92mParameter size[0m after quantization: 14.958 GB
	[2024-06-06 23:21:10] INFO convert_weight.py:160: [92mTotal parameters[0m: 8,030,523,392
	[2024-06-06 23:21:10] INFO convert_weight.py:161: [92mBits per parameter[0m: 16.000
	[2024-06-06 23:21:10] INFO convert_weight.py:166: Saved to directory: [1m/models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC[0m

	All finished, 131 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q0f16-MLC/ndarray-cache.json