Hugging Face's logo

mlc-ai
/
Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC

MLC-LLM
web-llm
Model card Files Community
Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC / logs.txt
riczhou's picture
riczhou
Initial commit
9968c61 verified
raw
history blame contribute delete
211 kB
/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Hermes-2-Pro-Llama-3-8B --quantization q4f32_1 --conv-template llama-3 --output /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC
[2024-06-04 03:21:43] INFO auto_config.py:116: Found model configuration: /models/Hermes-2-Pro-Llama-3-8B/config.json
[2024-06-04 03:21:43] INFO auto_config.py:154: Found model type: llama. Use `--model-type` to override.
[2024-06-04 03:21:43] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (8192)
[2024-06-04 03:21:43] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
[2024-06-04 03:21:43] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-04 03:21:43] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 128000
[2024-06-04 03:21:43] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: 128003
[2024-06-04 03:21:43] INFO gen_config.py:157: Not found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer.model
[2024-06-04 03:21:43] INFO gen_config.py:155: Found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC/tokenizer.json
[2024-06-04 03:21:43] INFO gen_config.py:157: Not found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/vocab.json
[2024-06-04 03:21:43] INFO gen_config.py:157: Not found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/merges.txt
[2024-06-04 03:21:43] INFO gen_config.py:157: Not found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/added_tokens.json
[2024-06-04 03:21:43] INFO gen_config.py:155: Found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC/tokenizer_config.json
[2024-06-04 03:21:43] 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 03:21:43] INFO gen_config.py:32: [System default] Setting pad_token_id: 0
[2024-06-04 03:21:43] INFO gen_config.py:32: [System default] Setting temperature: 1.0
[2024-06-04 03:21:43] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-04 03:21:43] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-04 03:21:43] INFO gen_config.py:32: [System default] Setting repetition_penalty: 1.0
[2024-06-04 03:21:43] INFO gen_config.py:32: [System default] Setting top_p: 1.0
[2024-06-04 03:21:43] INFO gen_config.py:32: [System default] Setting mean_gen_len: 128
[2024-06-04 03:21:43] INFO gen_config.py:32: [System default] Setting max_gen_len: 512
[2024-06-04 03:21:43] INFO gen_config.py:32: [System default] Setting shift_fill_factor: 0.3
[2024-06-04 03:21:43] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC/mlc-chat-config.json
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Hermes-2-Pro-Llama-3-8B --quantization q4f32_1 --output /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC
[2024-06-04 03:21:45] INFO auto_config.py:116: Found model configuration: /models/Hermes-2-Pro-Llama-3-8B/config.json
[2024-06-04 03:21:46] INFO auto_device.py:79: Found device: cuda:0
[2024-06-04 03:21:48] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-04 03:21:49] INFO auto_device.py:88: Not found device: metal:0
[2024-06-04 03:21:51] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-04 03:21:51] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-04 03:21:51] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-04 03:21:51] INFO auto_device.py:79: Found device: vulkan:3
[2024-06-04 03:21:52] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-04 03:21:52] INFO auto_device.py:35: Using device: cuda:0
[2024-06-04 03:21:52] INFO auto_weight.py:71: Finding weights in: /models/Hermes-2-Pro-Llama-3-8B
[2024-06-04 03:21:52] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-04 03:21:52] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /models/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json
[2024-06-04 03:21:52] INFO auto_weight.py:107: Using source weight configuration: /models/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json. Use `--source` to override.
[2024-06-04 03:21:52] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-04 03:21:52] INFO auto_config.py:154: Found model type: llama. Use `--model-type` to override.
[2024-06-04 03:21:52] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (8192)
[2024-06-04 03:21:52] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
Weight conversion with arguments:
--config /models/Hermes-2-Pro-Llama-3-8B/config.json
--quantization GroupQuantize(name='q4f32_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float32', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7)
--model-type llama
--device cuda:0
--source /models/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json
--source-format huggingface-safetensor
--output /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC
0%| | 0/195 [00:00<?, ?it/s] [2024-06-04 03:21:56] 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 03:22:00] INFO group_quantization.py:217: Compiling quantize function for key: ((128288, 4096), float32, cuda, axis=1, output_transpose=False)
0%| | 0/195 [00:03<?, ?it/s] [2024-06-04 03:22:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_weight", shape: (128288, 512), dtype: uint32
0%| | 0/195 [00:04<?, ?it/s] [2024-06-04 03:22:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_scale", shape: (128288, 128), dtype: float32
0%| | 0/195 [00:04<?, ?it/s] 1%| | 1/195 [00:05<16:26, 5.08s/it] [2024-06-04 03:22:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.input_layernorm.weight", shape: (4096,), dtype: float32
1%| | 1/195 [00:05<16:26, 5.08s/it] [2024-06-04 03:22:01] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 14336), float32, cuda, axis=1, output_transpose=False)
1%| | 1/195 [00:05<16:26, 5.08s/it] [2024-06-04 03:22:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
1%| | 1/195 [00:05<16:26, 5.08s/it] [2024-06-04 03:22:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
1%| | 1/195 [00:05<16:26, 5.08s/it] 2%|▏ | 3/195 [00:05<05:06, 1.59s/it] [2024-06-04 03:22:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.post_attention_layernorm.weight", shape: (4096,), dtype: float32
2%|▏ | 3/195 [00:05<05:06, 1.59s/it] [2024-06-04 03:22:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (4096,), dtype: float32
2%|▏ | 3/195 [00:05<05:06, 1.59s/it] [2024-06-04 03:22:02] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00004-of-00004.safetensors
2%|▏ | 3/195 [00:05<05:06, 1.59s/it] [2024-06-04 03:22:02] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00001-of-00004.safetensors
2%|▏ | 3/195 [00:05<05:06, 1.59s/it] [2024-06-04 03:22:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (128288, 512), dtype: uint32
2%|▏ | 3/195 [00:07<05:06, 1.59s/it] [2024-06-04 03:22:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (128288, 128), dtype: float32
2%|▏ | 3/195 [00:08<05:06, 1.59s/it] 3%|▎ | 6/195 [00:08<03:36, 1.15s/it] [2024-06-04 03:22:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (4096,), dtype: float32
3%|▎ | 6/195 [00:08<03:36, 1.15s/it] [2024-06-04 03:22:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
3%|▎ | 6/195 [00:08<03:36, 1.15s/it] [2024-06-04 03:22:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
3%|▎ | 6/195 [00:08<03:36, 1.15s/it] 4%|▍ | 8/195 [00:08<02:24, 1.30it/s] [2024-06-04 03:22:05] INFO group_quantization.py:217: Compiling quantize function for key: ((28672, 4096), float32, cuda, axis=1, output_transpose=False)
4%|▍ | 8/195 [00:09<02:24, 1.30it/s] [2024-06-04 03:22:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
4%|▍ | 8/195 [00:09<02:24, 1.30it/s] [2024-06-04 03:22:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
4%|▍ | 8/195 [00:09<02:24, 1.30it/s] 5%|▍ | 9/195 [00:09<02:30, 1.24it/s] [2024-06-04 03:22:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (4096,), dtype: float32
5%|▍ | 9/195 [00:09<02:30, 1.24it/s] [2024-06-04 03:22:06] INFO group_quantization.py:217: Compiling quantize function for key: ((6144, 4096), float32, cuda, axis=1, output_transpose=False)
5%|▍ | 9/195 [00:09<02:30, 1.24it/s] [2024-06-04 03:22:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
5%|▍ | 9/195 [00:10<02:30, 1.24it/s] [2024-06-04 03:22:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
5%|▍ | 9/195 [00:10<02:30, 1.24it/s] 6%|▌ | 11/195 [00:10<01:51, 1.66it/s] [2024-06-04 03:22:06] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 4096), float32, cuda, axis=1, output_transpose=False)
6%|▌ | 11/195 [00:10<01:51, 1.66it/s] [2024-06-04 03:22:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
6%|▌ | 11/195 [00:10<01:51, 1.66it/s] [2024-06-04 03:22:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
6%|▌ | 11/195 [00:10<01:51, 1.66it/s] 6%|▌ | 12/195 [00:10<01:47, 1.71it/s] [2024-06-04 03:22:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (4096,), dtype: float32
6%|▌ | 12/195 [00:10<01:47, 1.71it/s] [2024-06-04 03:22:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
6%|▌ | 12/195 [00:10<01:47, 1.71it/s] [2024-06-04 03:22:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
6%|▌ | 12/195 [00:10<01:47, 1.71it/s] 7%|▋ | 14/195 [00:10<01:14, 2.44it/s] [2024-06-04 03:22:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
7%|▋ | 14/195 [00:11<01:14, 2.44it/s] [2024-06-04 03:22:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
7%|▋ | 14/195 [00:11<01:14, 2.44it/s] 8%|▊ | 15/195 [00:11<01:17, 2.33it/s] [2024-06-04 03:22:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (4096,), dtype: float32
8%|▊ | 15/195 [00:11<01:17, 2.33it/s] [2024-06-04 03:22:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
8%|▊ | 15/195 [00:11<01:17, 2.33it/s] [2024-06-04 03:22:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
8%|▊ | 15/195 [00:11<01:17, 2.33it/s] 9%|▊ | 17/195 [00:11<00:52, 3.38it/s] [2024-06-04 03:22:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
9%|▊ | 17/195 [00:11<00:52, 3.38it/s] [2024-06-04 03:22:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
9%|▊ | 17/195 [00:11<00:52, 3.38it/s] [2024-06-04 03:22:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (4096,), dtype: float32
9%|▊ | 17/195 [00:11<00:52, 3.38it/s] [2024-06-04 03:22:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
9%|▊ | 17/195 [00:11<00:52, 3.38it/s] [2024-06-04 03:22:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
9%|▊ | 17/195 [00:11<00:52, 3.38it/s] 10%|█ | 20/195 [00:11<00:36, 4.85it/s] [2024-06-04 03:22:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
10%|█ | 20/195 [00:12<00:36, 4.85it/s] [2024-06-04 03:22:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
10%|█ | 20/195 [00:12<00:36, 4.85it/s] 11%|█ | 21/195 [00:12<00:44, 3.87it/s] [2024-06-04 03:22:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (4096,), dtype: float32
11%|█ | 21/195 [00:12<00:44, 3.87it/s] [2024-06-04 03:22:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
11%|█ | 21/195 [00:12<00:44, 3.87it/s] [2024-06-04 03:22:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
11%|█ | 21/195 [00:12<00:44, 3.87it/s] 12%|█▏ | 23/195 [00:12<00:33, 5.19it/s] [2024-06-04 03:22:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
12%|█▏ | 23/195 [00:12<00:33, 5.19it/s] [2024-06-04 03:22:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
12%|█▏ | 23/195 [00:12<00:33, 5.19it/s] [2024-06-04 03:22:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (4096,), dtype: float32
12%|█▏ | 23/195 [00:12<00:33, 5.19it/s] [2024-06-04 03:22:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
12%|█▏ | 23/195 [00:12<00:33, 5.19it/s] [2024-06-04 03:22:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
12%|█▏ | 23/195 [00:12<00:33, 5.19it/s] 13%|█▎ | 26/195 [00:12<00:25, 6.53it/s] [2024-06-04 03:22:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
13%|█▎ | 26/195 [00:13<00:25, 6.53it/s] [2024-06-04 03:22:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
13%|█▎ | 26/195 [00:13<00:25, 6.53it/s] 14%|█▍ | 27/195 [00:13<00:37, 4.51it/s] [2024-06-04 03:22:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (4096,), dtype: float32
14%|█▍ | 27/195 [00:13<00:37, 4.51it/s] [2024-06-04 03:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
14%|█▍ | 27/195 [00:13<00:37, 4.51it/s] [2024-06-04 03:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
14%|█▍ | 27/195 [00:13<00:37, 4.51it/s] [2024-06-04 03:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
14%|█▍ | 27/195 [00:13<00:37, 4.51it/s] [2024-06-04 03:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
14%|█▍ | 27/195 [00:13<00:37, 4.51it/s] 15%|█▌ | 30/195 [00:13<00:24, 6.68it/s] [2024-06-04 03:22:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (4096,), dtype: float32
15%|█▌ | 30/195 [00:13<00:24, 6.68it/s] [2024-06-04 03:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
15%|█▌ | 30/195 [00:13<00:24, 6.68it/s] [2024-06-04 03:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
15%|█▌ | 30/195 [00:13<00:24, 6.68it/s] 16%|█▋ | 32/195 [00:13<00:24, 6.69it/s] [2024-06-04 03:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
16%|█▋ | 32/195 [00:14<00:24, 6.69it/s] [2024-06-04 03:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
16%|█▋ | 32/195 [00:14<00:24, 6.69it/s] 17%|█▋ | 33/195 [00:14<00:34, 4.76it/s] [2024-06-04 03:22:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (4096,), dtype: float32
17%|█▋ | 33/195 [00:14<00:34, 4.76it/s] [2024-06-04 03:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
17%|█▋ | 33/195 [00:14<00:34, 4.76it/s] [2024-06-04 03:22:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
17%|█▋ | 33/195 [00:14<00:34, 4.76it/s] [2024-06-04 03:22:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
17%|█▋ | 33/195 [00:14<00:34, 4.76it/s] [2024-06-04 03:22:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
17%|█▋ | 33/195 [00:14<00:34, 4.76it/s] 18%|█▊ | 36/195 [00:14<00:23, 6.78it/s] [2024-06-04 03:22:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (4096,), dtype: float32
18%|█▊ | 36/195 [00:14<00:23, 6.78it/s] [2024-06-04 03:22:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
18%|█▊ | 36/195 [00:14<00:23, 6.78it/s] [2024-06-04 03:22:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
18%|█▊ | 36/195 [00:14<00:23, 6.78it/s] 19%|█▉ | 38/195 [00:14<00:21, 7.25it/s] [2024-06-04 03:22:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
19%|█▉ | 38/195 [00:15<00:21, 7.25it/s] [2024-06-04 03:22:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
19%|█▉ | 38/195 [00:15<00:21, 7.25it/s] 20%|██ | 39/195 [00:15<00:31, 5.03it/s] [2024-06-04 03:22:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (4096,), dtype: float32
20%|██ | 39/195 [00:15<00:31, 5.03it/s] [2024-06-04 03:22:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
20%|██ | 39/195 [00:15<00:31, 5.03it/s] [2024-06-04 03:22:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
20%|██ | 39/195 [00:15<00:31, 5.03it/s] 21%|██ | 41/195 [00:15<00:24, 6.34it/s] [2024-06-04 03:22:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
21%|██ | 41/195 [00:15<00:24, 6.34it/s] [2024-06-04 03:22:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
21%|██ | 41/195 [00:15<00:24, 6.34it/s] [2024-06-04 03:22:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (4096,), dtype: float32
21%|██ | 41/195 [00:15<00:24, 6.34it/s] [2024-06-04 03:22:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
21%|██ | 41/195 [00:15<00:24, 6.34it/s] [2024-06-04 03:22:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
21%|██ | 41/195 [00:15<00:24, 6.34it/s] 23%|██▎ | 44/195 [00:15<00:19, 7.59it/s] [2024-06-04 03:22:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
23%|██▎ | 44/195 [00:15<00:19, 7.59it/s] [2024-06-04 03:22:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
23%|██▎ | 44/195 [00:16<00:19, 7.59it/s] 23%|██▎ | 45/195 [00:16<00:28, 5.21it/s] [2024-06-04 03:22:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (4096,), dtype: float32
23%|██▎ | 45/195 [00:16<00:28, 5.21it/s] [2024-06-04 03:22:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
23%|██▎ | 45/195 [00:16<00:28, 5.21it/s] [2024-06-04 03:22:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
23%|██▎ | 45/195 [00:16<00:28, 5.21it/s] 24%|██▍ | 47/195 [00:16<00:22, 6.66it/s] [2024-06-04 03:22:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
24%|██▍ | 47/195 [00:16<00:22, 6.66it/s] [2024-06-04 03:22:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
24%|██▍ | 47/195 [00:16<00:22, 6.66it/s] [2024-06-04 03:22:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (4096,), dtype: float32
24%|██▍ | 47/195 [00:16<00:22, 6.66it/s] [2024-06-04 03:22:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
24%|██▍ | 47/195 [00:16<00:22, 6.66it/s] [2024-06-04 03:22:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
24%|██▍ | 47/195 [00:16<00:22, 6.66it/s] 26%|██▌ | 50/195 [00:16<00:18, 7.70it/s] [2024-06-04 03:22:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
26%|██▌ | 50/195 [00:17<00:18, 7.70it/s] [2024-06-04 03:22:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
26%|██▌ | 50/195 [00:17<00:18, 7.70it/s] [2024-06-04 03:22:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (4096,), dtype: float32
26%|██▌ | 50/195 [00:17<00:18, 7.70it/s] 27%|██▋ | 52/195 [00:17<00:27, 5.25it/s] [2024-06-04 03:22:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
27%|██▋ | 52/195 [00:17<00:27, 5.25it/s] [2024-06-04 03:22:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
27%|██▋ | 52/195 [00:17<00:27, 5.25it/s] [2024-06-04 03:22:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
27%|██▋ | 52/195 [00:17<00:27, 5.25it/s] [2024-06-04 03:22:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
27%|██▋ | 52/195 [00:17<00:27, 5.25it/s] 28%|██▊ | 54/195 [00:17<00:21, 6.43it/s] [2024-06-04 03:22:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (4096,), dtype: float32
28%|██▊ | 54/195 [00:17<00:21, 6.43it/s] [2024-06-04 03:22:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
28%|██▊ | 54/195 [00:17<00:21, 6.43it/s] [2024-06-04 03:22:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
28%|██▊ | 54/195 [00:17<00:21, 6.43it/s] 29%|██▊ | 56/195 [00:17<00:21, 6.50it/s] [2024-06-04 03:22:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
29%|██▊ | 56/195 [00:18<00:21, 6.50it/s] [2024-06-04 03:22:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
29%|██▊ | 56/195 [00:18<00:21, 6.50it/s] 29%|██▉ | 57/195 [00:18<00:31, 4.35it/s] [2024-06-04 03:22:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (4096,), dtype: float32
29%|██▉ | 57/195 [00:18<00:31, 4.35it/s] [2024-06-04 03:22:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
29%|██▉ | 57/195 [00:18<00:31, 4.35it/s] [2024-06-04 03:22:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
29%|██▉ | 57/195 [00:18<00:31, 4.35it/s] [2024-06-04 03:22:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
29%|██▉ | 57/195 [00:18<00:31, 4.35it/s] [2024-06-04 03:22:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
29%|██▉ | 57/195 [00:18<00:31, 4.35it/s] 31%|███ | 60/195 [00:18<00:21, 6.29it/s] [2024-06-04 03:22:15] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00001-of-00004.safetensors
31%|███ | 60/195 [00:18<00:21, 6.29it/s] [2024-06-04 03:22:15] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00002-of-00004.safetensors
31%|███ | 60/195 [00:18<00:21, 6.29it/s] [2024-06-04 03:22:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (4096,), dtype: float32
31%|███ | 60/195 [00:18<00:21, 6.29it/s] 31%|███▏ | 61/195 [00:18<00:25, 5.34it/s] [2024-06-04 03:22:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
31%|███▏ | 61/195 [00:18<00:25, 5.34it/s] [2024-06-04 03:22:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
31%|███▏ | 61/195 [00:19<00:25, 5.34it/s] 32%|███▏ | 62/195 [00:19<00:26, 5.09it/s] [2024-06-04 03:22:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
32%|███▏ | 62/195 [00:19<00:26, 5.09it/s] [2024-06-04 03:22:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
32%|███▏ | 62/195 [00:19<00:26, 5.09it/s] 32%|███▏ | 63/195 [00:19<00:43, 3.06it/s] [2024-06-04 03:22:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (4096,), dtype: float32
32%|███▏ | 63/195 [00:19<00:43, 3.06it/s] [2024-06-04 03:22:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
32%|███▏ | 63/195 [00:19<00:43, 3.06it/s] [2024-06-04 03:22:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
32%|███▏ | 63/195 [00:19<00:43, 3.06it/s] 33%|███▎ | 65/195 [00:19<00:30, 4.33it/s] [2024-06-04 03:22:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
33%|███▎ | 65/195 [00:20<00:30, 4.33it/s] [2024-06-04 03:22:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
33%|███▎ | 65/195 [00:20<00:30, 4.33it/s] [2024-06-04 03:22:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (4096,), dtype: float32
33%|███▎ | 65/195 [00:20<00:30, 4.33it/s] [2024-06-04 03:22:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
33%|███▎ | 65/195 [00:20<00:30, 4.33it/s] [2024-06-04 03:22:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
33%|███▎ | 65/195 [00:20<00:30, 4.33it/s] 35%|███▍ | 68/195 [00:20<00:21, 5.85it/s] [2024-06-04 03:22:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
35%|███▍ | 68/195 [00:20<00:21, 5.85it/s] [2024-06-04 03:22:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
35%|███▍ | 68/195 [00:20<00:21, 5.85it/s] 35%|███▌ | 69/195 [00:20<00:33, 3.77it/s] [2024-06-04 03:22:17] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (4096,), dtype: float32
35%|███▌ | 69/195 [00:20<00:33, 3.77it/s] [2024-06-04 03:22:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
35%|███▌ | 69/195 [00:21<00:33, 3.77it/s] [2024-06-04 03:22:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
35%|███▌ | 69/195 [00:21<00:33, 3.77it/s] 36%|███▋ | 71/195 [00:21<00:24, 5.06it/s] [2024-06-04 03:22:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
36%|███▋ | 71/195 [00:21<00:24, 5.06it/s] [2024-06-04 03:22:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
36%|███▋ | 71/195 [00:21<00:24, 5.06it/s] [2024-06-04 03:22:17] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (4096,), dtype: float32
36%|███▋ | 71/195 [00:21<00:24, 5.06it/s] [2024-06-04 03:22:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
36%|███▋ | 71/195 [00:21<00:24, 5.06it/s] [2024-06-04 03:22:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
36%|███▋ | 71/195 [00:21<00:24, 5.06it/s] 38%|███▊ | 74/195 [00:21<00:18, 6.42it/s] [2024-06-04 03:22:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
38%|███▊ | 74/195 [00:22<00:18, 6.42it/s] [2024-06-04 03:22:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
38%|███▊ | 74/195 [00:22<00:18, 6.42it/s] 38%|███▊ | 75/195 [00:22<00:33, 3.63it/s] [2024-06-04 03:22:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (4096,), dtype: float32
38%|███▊ | 75/195 [00:22<00:33, 3.63it/s] [2024-06-04 03:22:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
38%|███▊ | 75/195 [00:22<00:33, 3.63it/s] [2024-06-04 03:22:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
38%|███▊ | 75/195 [00:22<00:33, 3.63it/s] [2024-06-04 03:22:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
38%|███▊ | 75/195 [00:22<00:33, 3.63it/s] [2024-06-04 03:22:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
38%|███▊ | 75/195 [00:22<00:33, 3.63it/s] 40%|████ | 78/195 [00:22<00:21, 5.54it/s] [2024-06-04 03:22:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (4096,), dtype: float32
40%|████ | 78/195 [00:22<00:21, 5.54it/s] [2024-06-04 03:22:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
40%|████ | 78/195 [00:22<00:21, 5.54it/s] [2024-06-04 03:22:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
40%|████ | 78/195 [00:22<00:21, 5.54it/s] 41%|████ | 80/195 [00:22<00:19, 5.85it/s] [2024-06-04 03:22:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
41%|████ | 80/195 [00:23<00:19, 5.85it/s] [2024-06-04 03:22:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
41%|████ | 80/195 [00:23<00:19, 5.85it/s] 42%|████▏ | 81/195 [00:23<00:33, 3.38it/s] [2024-06-04 03:22:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (4096,), dtype: float32
42%|████▏ | 81/195 [00:23<00:33, 3.38it/s] [2024-06-04 03:22:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
42%|████▏ | 81/195 [00:23<00:33, 3.38it/s] [2024-06-04 03:22:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
42%|████▏ | 81/195 [00:23<00:33, 3.38it/s] [2024-06-04 03:22:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
42%|████▏ | 81/195 [00:23<00:33, 3.38it/s] [2024-06-04 03:22:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
42%|████▏ | 81/195 [00:23<00:33, 3.38it/s] 43%|████▎ | 84/195 [00:23<00:22, 5.04it/s] [2024-06-04 03:22:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (4096,), dtype: float32
43%|████▎ | 84/195 [00:23<00:22, 5.04it/s] [2024-06-04 03:22:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
43%|████▎ | 84/195 [00:23<00:22, 5.04it/s] [2024-06-04 03:22:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
43%|████▎ | 84/195 [00:24<00:22, 5.04it/s] 44%|████▍ | 86/195 [00:24<00:19, 5.68it/s] [2024-06-04 03:22:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
44%|████▍ | 86/195 [00:24<00:19, 5.68it/s] [2024-06-04 03:22:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
44%|████▍ | 86/195 [00:24<00:19, 5.68it/s] 45%|████▍ | 87/195 [00:24<00:31, 3.43it/s] [2024-06-04 03:22:21] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (4096,), dtype: float32
45%|████▍ | 87/195 [00:24<00:31, 3.43it/s] [2024-06-04 03:22:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
45%|████▍ | 87/195 [00:24<00:31, 3.43it/s] [2024-06-04 03:22:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
45%|████▍ | 87/195 [00:24<00:31, 3.43it/s] 46%|████▌ | 89/195 [00:25<00:23, 4.53it/s] [2024-06-04 03:22:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
46%|████▌ | 89/195 [00:25<00:23, 4.53it/s] [2024-06-04 03:22:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
46%|████▌ | 89/195 [00:25<00:23, 4.53it/s] [2024-06-04 03:22:21] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (4096,), dtype: float32
46%|████▌ | 89/195 [00:25<00:23, 4.53it/s] [2024-06-04 03:22:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
46%|████▌ | 89/195 [00:25<00:23, 4.53it/s] [2024-06-04 03:22:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
46%|████▌ | 89/195 [00:25<00:23, 4.53it/s] 47%|████▋ | 92/195 [00:25<00:17, 5.91it/s] [2024-06-04 03:22:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
47%|████▋ | 92/195 [00:25<00:17, 5.91it/s] [2024-06-04 03:22:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
47%|████▋ | 92/195 [00:26<00:17, 5.91it/s] 48%|████▊ | 93/195 [00:26<00:27, 3.68it/s] [2024-06-04 03:22:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (4096,), dtype: float32
48%|████▊ | 93/195 [00:26<00:27, 3.68it/s] [2024-06-04 03:22:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
48%|████▊ | 93/195 [00:26<00:27, 3.68it/s] [2024-06-04 03:22:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
48%|████▊ | 93/195 [00:26<00:27, 3.68it/s] 49%|████▊ | 95/195 [00:26<00:20, 4.87it/s] [2024-06-04 03:22:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
49%|████▊ | 95/195 [00:26<00:20, 4.87it/s] [2024-06-04 03:22:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
49%|████▊ | 95/195 [00:26<00:20, 4.87it/s] [2024-06-04 03:22:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (4096,), dtype: float32
49%|████▊ | 95/195 [00:26<00:20, 4.87it/s] [2024-06-04 03:22:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
49%|████▊ | 95/195 [00:26<00:20, 4.87it/s] [2024-06-04 03:22:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
49%|████▊ | 95/195 [00:26<00:20, 4.87it/s] 50%|█████ | 98/195 [00:26<00:15, 6.22it/s] [2024-06-04 03:22:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
50%|█████ | 98/195 [00:27<00:15, 6.22it/s] [2024-06-04 03:22:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
50%|█████ | 98/195 [00:27<00:15, 6.22it/s] 51%|█████ | 99/195 [00:27<00:27, 3.51it/s] [2024-06-04 03:22:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (4096,), dtype: float32
51%|█████ | 99/195 [00:27<00:27, 3.51it/s] [2024-06-04 03:22:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
51%|█████ | 99/195 [00:27<00:27, 3.51it/s] [2024-06-04 03:22:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
51%|█████ | 99/195 [00:27<00:27, 3.51it/s] [2024-06-04 03:22:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
51%|█████ | 99/195 [00:27<00:27, 3.51it/s] [2024-06-04 03:22:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
51%|█████ | 99/195 [00:27<00:27, 3.51it/s] 52%|█████▏ | 102/195 [00:27<00:17, 5.35it/s] [2024-06-04 03:22:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (4096,), dtype: float32
52%|█████▏ | 102/195 [00:27<00:17, 5.35it/s] [2024-06-04 03:22:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
52%|█████▏ | 102/195 [00:27<00:17, 5.35it/s] [2024-06-04 03:22:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
52%|█████▏ | 102/195 [00:27<00:17, 5.35it/s] 53%|█████▎ | 104/195 [00:27<00:16, 5.65it/s] [2024-06-04 03:22:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
53%|█████▎ | 104/195 [00:28<00:16, 5.65it/s] [2024-06-04 03:22:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
53%|█████▎ | 104/195 [00:28<00:16, 5.65it/s] [2024-06-04 03:22:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (4096,), dtype: float32
53%|█████▎ | 104/195 [00:28<00:16, 5.65it/s] 54%|█████▍ | 106/195 [00:28<00:20, 4.39it/s] [2024-06-04 03:22:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
54%|█████▍ | 106/195 [00:28<00:20, 4.39it/s] [2024-06-04 03:22:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
54%|█████▍ | 106/195 [00:28<00:20, 4.39it/s] [2024-06-04 03:22:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
54%|█████▍ | 106/195 [00:28<00:20, 4.39it/s] [2024-06-04 03:22:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
54%|█████▍ | 106/195 [00:28<00:20, 4.39it/s] 55%|█████▌ | 108/195 [00:28<00:16, 5.31it/s] [2024-06-04 03:22:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (4096,), dtype: float32
55%|█████▌ | 108/195 [00:28<00:16, 5.31it/s] [2024-06-04 03:22:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
55%|█████▌ | 108/195 [00:28<00:16, 5.31it/s] [2024-06-04 03:22:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
55%|█████▌ | 108/195 [00:29<00:16, 5.31it/s] 56%|█████▋ | 110/195 [00:29<00:14, 5.94it/s] [2024-06-04 03:22:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
56%|█████▋ | 110/195 [00:29<00:14, 5.94it/s] [2024-06-04 03:22:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
56%|█████▋ | 110/195 [00:29<00:14, 5.94it/s] 57%|█████▋ | 111/195 [00:29<00:24, 3.50it/s] [2024-06-04 03:22:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (4096,), dtype: float32
57%|█████▋ | 111/195 [00:29<00:24, 3.50it/s] [2024-06-04 03:22:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
57%|█████▋ | 111/195 [00:29<00:24, 3.50it/s] [2024-06-04 03:22:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
57%|█████▋ | 111/195 [00:29<00:24, 3.50it/s] 58%|█████▊ | 113/195 [00:30<00:17, 4.63it/s] [2024-06-04 03:22:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
58%|█████▊ | 113/195 [00:30<00:17, 4.63it/s] [2024-06-04 03:22:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
58%|█████▊ | 113/195 [00:30<00:17, 4.63it/s] [2024-06-04 03:22:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (4096,), dtype: float32
58%|█████▊ | 113/195 [00:30<00:17, 4.63it/s] [2024-06-04 03:22:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
58%|█████▊ | 113/195 [00:30<00:17, 4.63it/s] [2024-06-04 03:22:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
58%|█████▊ | 113/195 [00:30<00:17, 4.63it/s] 59%|█████▉ | 116/195 [00:30<00:13, 6.02it/s] [2024-06-04 03:22:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
59%|█████▉ | 116/195 [00:30<00:13, 6.02it/s] [2024-06-04 03:22:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
59%|█████▉ | 116/195 [00:31<00:13, 6.02it/s] 60%|██████ | 117/195 [00:31<00:21, 3.68it/s] [2024-06-04 03:22:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (4096,), dtype: float32
60%|██████ | 117/195 [00:31<00:21, 3.68it/s] [2024-06-04 03:22:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
60%|██████ | 117/195 [00:31<00:21, 3.68it/s] [2024-06-04 03:22:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
60%|██████ | 117/195 [00:31<00:21, 3.68it/s] 61%|██████ | 119/195 [00:31<00:15, 4.89it/s] [2024-06-04 03:22:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
61%|██████ | 119/195 [00:31<00:15, 4.89it/s] [2024-06-04 03:22:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
61%|██████ | 119/195 [00:31<00:15, 4.89it/s] [2024-06-04 03:22:27] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00003-of-00004.safetensors
61%|██████ | 119/195 [00:31<00:15, 4.89it/s] [2024-06-04 03:22:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
61%|██████ | 119/195 [00:31<00:15, 4.89it/s] [2024-06-04 03:22:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
61%|██████ | 119/195 [00:31<00:15, 4.89it/s] 62%|██████▏ | 121/195 [00:31<00:18, 3.99it/s] [2024-06-04 03:22:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
62%|██████▏ | 121/195 [00:32<00:18, 3.99it/s] [2024-06-04 03:22:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
62%|██████▏ | 121/195 [00:32<00:18, 3.99it/s] 63%|██████▎ | 122/195 [00:32<00:16, 4.33it/s] [2024-06-04 03:22:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
63%|██████▎ | 122/195 [00:32<00:16, 4.33it/s] [2024-06-04 03:22:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
63%|██████▎ | 122/195 [00:32<00:16, 4.33it/s] [2024-06-04 03:22:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (4096,), dtype: float32
63%|██████▎ | 122/195 [00:32<00:16, 4.33it/s] [2024-06-04 03:22:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
63%|██████▎ | 122/195 [00:32<00:16, 4.33it/s] [2024-06-04 03:22:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
63%|██████▎ | 122/195 [00:32<00:16, 4.33it/s] 64%|██████▍ | 125/195 [00:32<00:12, 5.77it/s] [2024-06-04 03:22:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
64%|██████▍ | 125/195 [00:32<00:12, 5.77it/s] [2024-06-04 03:22:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
64%|██████▍ | 125/195 [00:32<00:12, 5.77it/s] 65%|██████▍ | 126/195 [00:33<00:17, 3.99it/s] [2024-06-04 03:22:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (4096,), dtype: float32
65%|██████▍ | 126/195 [00:33<00:17, 3.99it/s] [2024-06-04 03:22:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
65%|██████▍ | 126/195 [00:33<00:17, 3.99it/s] [2024-06-04 03:22:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
65%|██████▍ | 126/195 [00:33<00:17, 3.99it/s] [2024-06-04 03:22:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
65%|██████▍ | 126/195 [00:33<00:17, 3.99it/s] [2024-06-04 03:22:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
65%|██████▍ | 126/195 [00:33<00:17, 3.99it/s] 66%|██████▌ | 129/195 [00:33<00:10, 6.12it/s] [2024-06-04 03:22:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (4096,), dtype: float32
66%|██████▌ | 129/195 [00:33<00:10, 6.12it/s] [2024-06-04 03:22:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
66%|██████▌ | 129/195 [00:33<00:10, 6.12it/s] [2024-06-04 03:22:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
66%|██████▌ | 129/195 [00:33<00:10, 6.12it/s] 67%|██████▋ | 131/195 [00:33<00:10, 6.23it/s] [2024-06-04 03:22:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (4096,), dtype: float32
67%|██████▋ | 131/195 [00:33<00:10, 6.23it/s] [2024-06-04 03:22:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (4096,), dtype: float32
67%|██████▋ | 131/195 [00:33<00:10, 6.23it/s] [2024-06-04 03:22:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
67%|██████▋ | 131/195 [00:33<00:10, 6.23it/s] [2024-06-04 03:22:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
67%|██████▋ | 131/195 [00:33<00:10, 6.23it/s] 69%|██████▊ | 134/195 [00:33<00:08, 7.59it/s] [2024-06-04 03:22:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
69%|██████▊ | 134/195 [00:34<00:08, 7.59it/s] [2024-06-04 03:22:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
69%|██████▊ | 134/195 [00:34<00:08, 7.59it/s] [2024-06-04 03:22:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (4096,), dtype: float32
69%|██████▊ | 134/195 [00:34<00:08, 7.59it/s] 70%|██████▉ | 136/195 [00:34<00:10, 5.46it/s] [2024-06-04 03:22:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
70%|██████▉ | 136/195 [00:34<00:10, 5.46it/s] [2024-06-04 03:22:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
70%|██████▉ | 136/195 [00:34<00:10, 5.46it/s] [2024-06-04 03:22:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
70%|██████▉ | 136/195 [00:34<00:10, 5.46it/s] [2024-06-04 03:22:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
70%|██████▉ | 136/195 [00:34<00:10, 5.46it/s] 71%|███████ | 138/195 [00:34<00:09, 6.29it/s] [2024-06-04 03:22:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (4096,), dtype: float32
71%|███████ | 138/195 [00:34<00:09, 6.29it/s] [2024-06-04 03:22:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
71%|███████ | 138/195 [00:34<00:09, 6.29it/s] [2024-06-04 03:22:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
71%|███████ | 138/195 [00:34<00:09, 6.29it/s] 72%|███████▏ | 140/195 [00:34<00:08, 6.79it/s] [2024-06-04 03:22:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
72%|███████▏ | 140/195 [00:35<00:08, 6.79it/s] [2024-06-04 03:22:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
72%|███████▏ | 140/195 [00:35<00:08, 6.79it/s] 72%|███████▏ | 141/195 [00:35<00:12, 4.26it/s] [2024-06-04 03:22:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (4096,), dtype: float32
72%|███████▏ | 141/195 [00:35<00:12, 4.26it/s] [2024-06-04 03:22:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
72%|███████▏ | 141/195 [00:35<00:12, 4.26it/s] [2024-06-04 03:22:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
72%|███████▏ | 141/195 [00:35<00:12, 4.26it/s] 73%|███████▎ | 143/195 [00:35<00:09, 5.50it/s] [2024-06-04 03:22:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
73%|███████▎ | 143/195 [00:35<00:09, 5.50it/s] [2024-06-04 03:22:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
73%|███████▎ | 143/195 [00:35<00:09, 5.50it/s] [2024-06-04 03:22:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (4096,), dtype: float32
73%|███████▎ | 143/195 [00:35<00:09, 5.50it/s] [2024-06-04 03:22:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
73%|███████▎ | 143/195 [00:35<00:09, 5.50it/s] [2024-06-04 03:22:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
73%|███████▎ | 143/195 [00:35<00:09, 5.50it/s] 75%|███████▍ | 146/195 [00:35<00:07, 6.83it/s] [2024-06-04 03:22:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
75%|███████▍ | 146/195 [00:36<00:07, 6.83it/s] [2024-06-04 03:22:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
75%|███████▍ | 146/195 [00:36<00:07, 6.83it/s] 75%|███████▌ | 147/195 [00:36<00:10, 4.52it/s] [2024-06-04 03:22:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (4096,), dtype: float32
75%|███████▌ | 147/195 [00:36<00:10, 4.52it/s] [2024-06-04 03:22:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
75%|███████▌ | 147/195 [00:36<00:10, 4.52it/s] [2024-06-04 03:22:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
75%|███████▌ | 147/195 [00:36<00:10, 4.52it/s] 76%|███████▋ | 149/195 [00:36<00:07, 5.85it/s] [2024-06-04 03:22:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
76%|███████▋ | 149/195 [00:36<00:07, 5.85it/s] [2024-06-04 03:22:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
76%|███████▋ | 149/195 [00:36<00:07, 5.85it/s] [2024-06-04 03:22:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (4096,), dtype: float32
76%|███████▋ | 149/195 [00:36<00:07, 5.85it/s] [2024-06-04 03:22:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
76%|███████▋ | 149/195 [00:36<00:07, 5.85it/s] [2024-06-04 03:22:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
76%|███████▋ | 149/195 [00:36<00:07, 5.85it/s] 78%|███████▊ | 152/195 [00:36<00:06, 7.00it/s] [2024-06-04 03:22:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
78%|███████▊ | 152/195 [00:37<00:06, 7.00it/s] [2024-06-04 03:22:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
78%|███████▊ | 152/195 [00:37<00:06, 7.00it/s] 78%|███████▊ | 153/195 [00:37<00:09, 4.20it/s] [2024-06-04 03:22:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (4096,), dtype: float32
78%|███████▊ | 153/195 [00:37<00:09, 4.20it/s] [2024-06-04 03:22:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
78%|███████▊ | 153/195 [00:37<00:09, 4.20it/s] [2024-06-04 03:22:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
78%|███████▊ | 153/195 [00:37<00:09, 4.20it/s] [2024-06-04 03:22:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
78%|███████▊ | 153/195 [00:37<00:09, 4.20it/s] [2024-06-04 03:22:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
78%|███████▊ | 153/195 [00:37<00:09, 4.20it/s] 80%|████████ | 156/195 [00:37<00:06, 6.22it/s] [2024-06-04 03:22:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (4096,), dtype: float32
80%|████████ | 156/195 [00:37<00:06, 6.22it/s] [2024-06-04 03:22:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
80%|████████ | 156/195 [00:37<00:06, 6.22it/s] [2024-06-04 03:22:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
80%|████████ | 156/195 [00:38<00:06, 6.22it/s] 81%|████████ | 158/195 [00:38<00:05, 6.32it/s] [2024-06-04 03:22:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
81%|████████ | 158/195 [00:38<00:05, 6.32it/s] [2024-06-04 03:22:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
81%|████████ | 158/195 [00:38<00:05, 6.32it/s] 82%|████████▏ | 159/195 [00:38<00:08, 4.05it/s] [2024-06-04 03:22:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (4096,), dtype: float32
82%|████████▏ | 159/195 [00:38<00:08, 4.05it/s] [2024-06-04 03:22:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
82%|████████▏ | 159/195 [00:38<00:08, 4.05it/s] [2024-06-04 03:22:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
82%|████████▏ | 159/195 [00:38<00:08, 4.05it/s] [2024-06-04 03:22:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
82%|████████▏ | 159/195 [00:38<00:08, 4.05it/s] [2024-06-04 03:22:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
82%|████████▏ | 159/195 [00:38<00:08, 4.05it/s] 83%|████████▎ | 162/195 [00:38<00:05, 5.87it/s] [2024-06-04 03:22:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (4096,), dtype: float32
83%|████████▎ | 162/195 [00:38<00:05, 5.87it/s] [2024-06-04 03:22:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
83%|████████▎ | 162/195 [00:39<00:05, 5.87it/s] [2024-06-04 03:22:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
83%|████████▎ | 162/195 [00:39<00:05, 5.87it/s] 84%|████████▍ | 164/195 [00:39<00:04, 6.40it/s] [2024-06-04 03:22:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
84%|████████▍ | 164/195 [00:39<00:04, 6.40it/s] [2024-06-04 03:22:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
84%|████████▍ | 164/195 [00:40<00:04, 6.40it/s] 85%|████████▍ | 165/195 [00:40<00:08, 3.72it/s] [2024-06-04 03:22:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (4096,), dtype: float32
85%|████████▍ | 165/195 [00:40<00:08, 3.72it/s] [2024-06-04 03:22:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
85%|████████▍ | 165/195 [00:40<00:08, 3.72it/s] [2024-06-04 03:22:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
85%|████████▍ | 165/195 [00:40<00:08, 3.72it/s] 86%|████████▌ | 167/195 [00:40<00:05, 4.85it/s] [2024-06-04 03:22:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
86%|████████▌ | 167/195 [00:40<00:05, 4.85it/s] [2024-06-04 03:22:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
86%|████████▌ | 167/195 [00:40<00:05, 4.85it/s] [2024-06-04 03:22:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (4096,), dtype: float32
86%|████████▌ | 167/195 [00:40<00:05, 4.85it/s] [2024-06-04 03:22:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
86%|████████▌ | 167/195 [00:40<00:05, 4.85it/s] [2024-06-04 03:22:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
86%|████████▌ | 167/195 [00:40<00:05, 4.85it/s] 87%|████████▋ | 170/195 [00:40<00:04, 6.19it/s] [2024-06-04 03:22:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
87%|████████▋ | 170/195 [00:41<00:04, 6.19it/s] [2024-06-04 03:22:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
87%|████████▋ | 170/195 [00:41<00:04, 6.19it/s] 88%|████████▊ | 171/195 [00:41<00:06, 3.70it/s] [2024-06-04 03:22:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (4096,), dtype: float32
88%|████████▊ | 171/195 [00:41<00:06, 3.70it/s] [2024-06-04 03:22:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
88%|████████▊ | 171/195 [00:41<00:06, 3.70it/s] [2024-06-04 03:22:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
88%|████████▊ | 171/195 [00:41<00:06, 3.70it/s] 89%|████████▊ | 173/195 [00:41<00:04, 4.89it/s] [2024-06-04 03:22:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
89%|████████▊ | 173/195 [00:41<00:04, 4.89it/s] [2024-06-04 03:22:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
89%|████████▊ | 173/195 [00:41<00:04, 4.89it/s] [2024-06-04 03:22:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.input_layernorm.weight", shape: (4096,), dtype: float32
89%|████████▊ | 173/195 [00:41<00:04, 4.89it/s] [2024-06-04 03:22:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
89%|████████▊ | 173/195 [00:41<00:04, 4.89it/s] [2024-06-04 03:22:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
89%|████████▊ | 173/195 [00:41<00:04, 4.89it/s] 90%|█████████ | 176/195 [00:41<00:03, 6.18it/s] [2024-06-04 03:22:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
90%|█████████ | 176/195 [00:42<00:03, 6.18it/s] [2024-06-04 03:22:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
90%|█████████ | 176/195 [00:43<00:03, 6.18it/s] 91%|█████████ | 177/195 [00:43<00:06, 2.80it/s] [2024-06-04 03:22:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.post_attention_layernorm.weight", shape: (4096,), dtype: float32
91%|█████████ | 177/195 [00:43<00:06, 2.80it/s] [2024-06-04 03:22:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
91%|█████████ | 177/195 [00:43<00:06, 2.80it/s] [2024-06-04 03:22:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
91%|█████████ | 177/195 [00:43<00:06, 2.80it/s] [2024-06-04 03:22:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
91%|█████████ | 177/195 [00:43<00:06, 2.80it/s] [2024-06-04 03:22:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
91%|█████████ | 177/195 [00:43<00:06, 2.80it/s] 92%|█████████▏| 180/195 [00:43<00:03, 4.30it/s] [2024-06-04 03:22:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.input_layernorm.weight", shape: (4096,), dtype: float32
92%|█████████▏| 180/195 [00:43<00:03, 4.30it/s] [2024-06-04 03:22:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
92%|█████████▏| 180/195 [00:43<00:03, 4.30it/s] [2024-06-04 03:22:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
92%|█████████▏| 180/195 [00:43<00:03, 4.30it/s] 93%|█████████▎| 182/195 [00:43<00:02, 4.76it/s] [2024-06-04 03:22:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
93%|█████████▎| 182/195 [00:44<00:02, 4.76it/s] [2024-06-04 03:22:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
93%|█████████▎| 182/195 [00:44<00:02, 4.76it/s] 94%|█████████▍| 183/195 [00:44<00:04, 2.98it/s] [2024-06-04 03:22:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.post_attention_layernorm.weight", shape: (4096,), dtype: float32
94%|█████████▍| 183/195 [00:44<00:04, 2.98it/s] [2024-06-04 03:22:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
94%|█████████▍| 183/195 [00:44<00:04, 2.98it/s] [2024-06-04 03:22:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
94%|█████████▍| 183/195 [00:44<00:04, 2.98it/s] [2024-06-04 03:22:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
94%|█████████▍| 183/195 [00:44<00:04, 2.98it/s] [2024-06-04 03:22:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
94%|█████████▍| 183/195 [00:44<00:04, 2.98it/s] 95%|█████████▌| 186/195 [00:44<00:02, 4.49it/s] [2024-06-04 03:22:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.input_layernorm.weight", shape: (4096,), dtype: float32
95%|█████████▌| 186/195 [00:44<00:02, 4.49it/s] [2024-06-04 03:22:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
95%|█████████▌| 186/195 [00:44<00:02, 4.49it/s] [2024-06-04 03:22:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
95%|█████████▌| 186/195 [00:44<00:02, 4.49it/s] 96%|█████████▋| 188/195 [00:44<00:01, 5.15it/s] [2024-06-04 03:22:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
96%|█████████▋| 188/195 [00:45<00:01, 5.15it/s] [2024-06-04 03:22:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
96%|█████████▋| 188/195 [00:45<00:01, 5.15it/s] 97%|█████████▋| 189/195 [00:45<00:01, 3.05it/s] [2024-06-04 03:22:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.post_attention_layernorm.weight", shape: (4096,), dtype: float32
97%|█████████▋| 189/195 [00:45<00:01, 3.05it/s] [2024-06-04 03:22:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
97%|█████████▋| 189/195 [00:46<00:01, 3.05it/s] [2024-06-04 03:22:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
97%|█████████▋| 189/195 [00:46<00:01, 3.05it/s] 98%|█████████▊| 191/195 [00:46<00:00, 4.05it/s] [2024-06-04 03:22:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
98%|█████████▊| 191/195 [00:46<00:00, 4.05it/s] [2024-06-04 03:22:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
98%|█████████▊| 191/195 [00:46<00:00, 4.05it/s] [2024-06-04 03:22:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
98%|█████████▊| 191/195 [00:46<00:00, 4.05it/s] [2024-06-04 03:22:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
98%|█████████▊| 191/195 [00:47<00:00, 4.05it/s] 99%|█████████▉| 193/195 [00:47<00:00, 3.07it/s] [2024-06-04 03:22:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
99%|█████████▉| 193/195 [00:47<00:00, 3.07it/s] [2024-06-04 03:22:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
99%|█████████▉| 193/195 [00:47<00:00, 3.07it/s] [2024-06-04 03:22:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
99%|█████████▉| 193/195 [00:47<00:00, 3.07it/s] [2024-06-04 03:22:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
99%|█████████▉| 193/195 [00:47<00:00, 3.07it/s] 100%|██████████| 195/195 [00:47<00:00, 3.89it/s] 100%|██████████| 195/195 [00:47<00:00, 4.12it/s]
[2024-06-04 03:22:43] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00002-of-00004.safetensors
[2024-06-04 03:22:44] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00003-of-00004.safetensors
[2024-06-04 03:22:44] INFO stats.py:77: Time usage: HF loading: 1.332 sec; Pre-quantization mapping: 27.727 sec; Quantization: 3.047 sec
[2024-06-04 03:22:44] INFO stats.py:91: RAM usage: Peak RAM: 9.235 GB. Total bytes loaded from disk: 14.958 GB
[2024-06-04 03:22:44] INFO convert_weight.py:155: Parameter size after quantization: 4.675 GB
[2024-06-04 03:22:44] INFO convert_weight.py:160: Total parameters: 8,030,523,392
[2024-06-04 03:22:44] INFO convert_weight.py:161: Bits per parameter: 5.001
[2024-06-04 03:22:44] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC
All finished, 108 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC/ndarray-cache.json
Also saved a bf16 record to /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC/ndarray-cache-b16.json
/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Hermes-2-Pro-Llama-3-8B --quantization q4f32_1 --conv-template hermes2_pro_llama3 --output /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC
[2024-06-06 23:14:23] INFO auto_config.py:116: Found model configuration: /models/Hermes-2-Pro-Llama-3-8B/config.json
[2024-06-06 23:14:23] INFO auto_config.py:154: Found model type: llama. Use `--model-type` to override.
[2024-06-06 23:14:23] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (8192)
[2024-06-06 23:14:23] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
[2024-06-06 23:14:23] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-06 23:14:23] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 128000
[2024-06-06 23:14:23] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: 128003
[2024-06-06 23:14:23] INFO gen_config.py:157: Not found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer.model
[2024-06-06 23:14:23] INFO gen_config.py:155: Found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC/tokenizer.json
[2024-06-06 23:14:23] INFO gen_config.py:157: Not found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/vocab.json
[2024-06-06 23:14:23] INFO gen_config.py:157: Not found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/merges.txt
[2024-06-06 23:14:23] INFO gen_config.py:157: Not found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/added_tokens.json
[2024-06-06 23:14:23] INFO gen_config.py:155: Found tokenizer config: /models/Hermes-2-Pro-Llama-3-8B/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC/tokenizer_config.json
[2024-06-06 23:14:24] 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 23:14:24] INFO gen_config.py:32: [System default] Setting pad_token_id: 0
[2024-06-06 23:14:24] INFO gen_config.py:32: [System default] Setting temperature: 1.0
[2024-06-06 23:14:24] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-06 23:14:24] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-06 23:14:24] INFO gen_config.py:32: [System default] Setting repetition_penalty: 1.0
[2024-06-06 23:14:24] INFO gen_config.py:32: [System default] Setting top_p: 1.0
[2024-06-06 23:14:24] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC/mlc-chat-config.json
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Hermes-2-Pro-Llama-3-8B --quantization q4f32_1 --output /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC
[2024-06-06 23:14:25] INFO auto_config.py:116: Found model configuration: /models/Hermes-2-Pro-Llama-3-8B/config.json
[2024-06-06 23:14:26] INFO auto_device.py:79: Found device: cuda:0
[2024-06-06 23:14:28] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-06 23:14:29] INFO auto_device.py:88: Not found device: metal:0
[2024-06-06 23:14:31] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-06 23:14:31] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-06 23:14:31] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-06 23:14:31] INFO auto_device.py:79: Found device: vulkan:3
[2024-06-06 23:14:32] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-06 23:14:32] INFO auto_device.py:35: Using device: cuda:0
[2024-06-06 23:14:32] INFO auto_weight.py:71: Finding weights in: /models/Hermes-2-Pro-Llama-3-8B
[2024-06-06 23:14:32] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-06 23:14:32] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /models/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json
[2024-06-06 23:14:32] INFO auto_weight.py:107: Using source weight configuration: /models/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json. Use `--source` to override.
[2024-06-06 23:14:32] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-06 23:14:32] INFO auto_config.py:154: Found model type: llama. Use `--model-type` to override.
[2024-06-06 23:14:32] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (8192)
[2024-06-06 23:14:32] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
Weight conversion with arguments:
--config /models/Hermes-2-Pro-Llama-3-8B/config.json
--quantization GroupQuantize(name='q4f32_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float32', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7)
--model-type llama
--device cuda:0
--source /models/Hermes-2-Pro-Llama-3-8B/model.safetensors.index.json
--source-format huggingface-safetensor
--output /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC
0%| | 0/195 [00:00<?, ?it/s] [2024-06-06 23:14:36] 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 23:14:41] INFO group_quantization.py:217: Compiling quantize function for key: ((128288, 4096), float32, cuda, axis=1, output_transpose=False)
0%| | 0/195 [00:04<?, ?it/s] [2024-06-06 23:14:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_weight", shape: (128288, 512), dtype: uint32
0%| | 0/195 [00:05<?, ?it/s] [2024-06-06 23:14:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_scale", shape: (128288, 128), dtype: float32
0%| | 0/195 [00:06<?, ?it/s] 1%| | 1/195 [00:06<22:21, 6.91s/it] [2024-06-06 23:14:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.input_layernorm.weight", shape: (4096,), dtype: float32
1%| | 1/195 [00:06<22:21, 6.91s/it] [2024-06-06 23:14:44] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 14336), float32, cuda, axis=1, output_transpose=False)
1%| | 1/195 [00:07<22:21, 6.91s/it] [2024-06-06 23:14:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
1%| | 1/195 [00:07<22:21, 6.91s/it] [2024-06-06 23:14:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
1%| | 1/195 [00:07<22:21, 6.91s/it] 2%|▏ | 3/195 [00:07<06:53, 2.16s/it] [2024-06-06 23:14:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.31.post_attention_layernorm.weight", shape: (4096,), dtype: float32
2%|▏ | 3/195 [00:07<06:53, 2.16s/it] [2024-06-06 23:14:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (4096,), dtype: float32
2%|▏ | 3/195 [00:07<06:53, 2.16s/it] [2024-06-06 23:14:44] 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<06:53, 2.16s/it] [2024-06-06 23:14:44] 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<06:53, 2.16s/it] [2024-06-06 23:14:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (128288, 512), dtype: uint32
2%|▏ | 3/195 [00:10<06:53, 2.16s/it] [2024-06-06 23:14:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (128288, 128), dtype: float32
2%|▏ | 3/195 [00:11<06:53, 2.16s/it] 3%|▎ | 6/195 [00:11<05:10, 1.64s/it] [2024-06-06 23:14:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (4096,), dtype: float32
3%|▎ | 6/195 [00:11<05:10, 1.64s/it] [2024-06-06 23:14:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
3%|▎ | 6/195 [00:12<05:10, 1.64s/it] [2024-06-06 23:14:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
3%|▎ | 6/195 [00:12<05:10, 1.64s/it] 4%|▍ | 8/195 [00:12<03:27, 1.11s/it] [2024-06-06 23:14:50] INFO group_quantization.py:217: Compiling quantize function for key: ((28672, 4096), float32, cuda, axis=1, output_transpose=False)
4%|▍ | 8/195 [00:13<03:27, 1.11s/it] [2024-06-06 23:14:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
4%|▍ | 8/195 [00:13<03:27, 1.11s/it] [2024-06-06 23:14:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
4%|▍ | 8/195 [00:14<03:27, 1.11s/it] 5%|▍ | 9/195 [00:14<03:58, 1.28s/it] [2024-06-06 23:14:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (4096,), dtype: float32
5%|▍ | 9/195 [00:14<03:58, 1.28s/it] [2024-06-06 23:14:51] INFO group_quantization.py:217: Compiling quantize function for key: ((6144, 4096), float32, cuda, axis=1, output_transpose=False)
5%|▍ | 9/195 [00:14<03:58, 1.28s/it] [2024-06-06 23:14:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
5%|▍ | 9/195 [00:14<03:58, 1.28s/it] [2024-06-06 23:14:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
5%|▍ | 9/195 [00:14<03:58, 1.28s/it] 6%|▌ | 11/195 [00:14<02:52, 1.07it/s] [2024-06-06 23:14:51] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 4096), float32, cuda, axis=1, output_transpose=False)
6%|▌ | 11/195 [00:14<02:52, 1.07it/s] [2024-06-06 23:14:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
6%|▌ | 11/195 [00:15<02:52, 1.07it/s] [2024-06-06 23:14:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
6%|▌ | 11/195 [00:15<02:52, 1.07it/s] 6%|▌ | 12/195 [00:15<02:37, 1.16it/s] [2024-06-06 23:14:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (4096,), dtype: float32
6%|▌ | 12/195 [00:15<02:37, 1.16it/s] [2024-06-06 23:14:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
6%|▌ | 12/195 [00:15<02:37, 1.16it/s] [2024-06-06 23:14:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
6%|▌ | 12/195 [00:15<02:37, 1.16it/s] 7%|▋ | 14/195 [00:15<01:50, 1.63it/s] [2024-06-06 23:14:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
7%|▋ | 14/195 [00:17<01:50, 1.63it/s] [2024-06-06 23:14:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
7%|▋ | 14/195 [00:17<01:50, 1.63it/s] 8%|▊ | 15/195 [00:17<02:32, 1.18it/s] [2024-06-06 23:14:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (4096,), dtype: float32
8%|▊ | 15/195 [00:17<02:32, 1.18it/s] [2024-06-06 23:14:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
8%|▊ | 15/195 [00:17<02:32, 1.18it/s] [2024-06-06 23:14:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
8%|▊ | 15/195 [00:17<02:32, 1.18it/s] 9%|▊ | 17/195 [00:17<01:44, 1.70it/s] [2024-06-06 23:14:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
9%|▊ | 17/195 [00:17<01:44, 1.70it/s] [2024-06-06 23:14:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
9%|▊ | 17/195 [00:17<01:44, 1.70it/s] [2024-06-06 23:14:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (4096,), dtype: float32
9%|▊ | 17/195 [00:17<01:44, 1.70it/s] [2024-06-06 23:14:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
9%|▊ | 17/195 [00:18<01:44, 1.70it/s] [2024-06-06 23:14:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
9%|▊ | 17/195 [00:18<01:44, 1.70it/s] 10%|█ | 20/195 [00:18<01:09, 2.53it/s] [2024-06-06 23:14:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
10%|█ | 20/195 [00:20<01:09, 2.53it/s] [2024-06-06 23:14:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
10%|█ | 20/195 [00:20<01:09, 2.53it/s] 11%|█ | 21/195 [00:20<02:04, 1.40it/s] [2024-06-06 23:14:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (4096,), dtype: float32
11%|█ | 21/195 [00:20<02:04, 1.40it/s] [2024-06-06 23:14:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
11%|█ | 21/195 [00:20<02:04, 1.40it/s] [2024-06-06 23:14:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
11%|█ | 21/195 [00:20<02:04, 1.40it/s] 12%|█▏ | 23/195 [00:20<01:29, 1.92it/s] [2024-06-06 23:14:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
12%|█▏ | 23/195 [00:20<01:29, 1.92it/s] [2024-06-06 23:14:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
12%|█▏ | 23/195 [00:20<01:29, 1.92it/s] [2024-06-06 23:14:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (4096,), dtype: float32
12%|█▏ | 23/195 [00:20<01:29, 1.92it/s] [2024-06-06 23:14:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
12%|█▏ | 23/195 [00:21<01:29, 1.92it/s] [2024-06-06 23:14:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
12%|█▏ | 23/195 [00:21<01:29, 1.92it/s] 13%|█▎ | 26/195 [00:21<01:10, 2.41it/s] [2024-06-06 23:15:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
13%|█▎ | 26/195 [00:23<01:10, 2.41it/s] [2024-06-06 23:15:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
13%|█▎ | 26/195 [00:23<01:10, 2.41it/s] 14%|█▍ | 27/195 [00:23<01:59, 1.40it/s] [2024-06-06 23:15:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (4096,), dtype: float32
14%|█▍ | 27/195 [00:23<01:59, 1.40it/s] [2024-06-06 23:15:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
14%|█▍ | 27/195 [00:24<01:59, 1.40it/s] [2024-06-06 23:15:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
14%|█▍ | 27/195 [00:24<01:59, 1.40it/s] 15%|█▍ | 29/195 [00:24<01:27, 1.89it/s] [2024-06-06 23:15:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
15%|█▍ | 29/195 [00:24<01:27, 1.89it/s] [2024-06-06 23:15:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
15%|█▍ | 29/195 [00:24<01:27, 1.89it/s] [2024-06-06 23:15:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (4096,), dtype: float32
15%|█▍ | 29/195 [00:24<01:27, 1.89it/s] [2024-06-06 23:15:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
15%|█▍ | 29/195 [00:24<01:27, 1.89it/s] [2024-06-06 23:15:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
15%|█▍ | 29/195 [00:24<01:27, 1.89it/s] 16%|█▋ | 32/195 [00:24<01:04, 2.53it/s] [2024-06-06 23:15:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
16%|█▋ | 32/195 [00:27<01:04, 2.53it/s] [2024-06-06 23:15:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
16%|█▋ | 32/195 [00:27<01:04, 2.53it/s] 17%|█▋ | 33/195 [00:27<02:02, 1.32it/s] [2024-06-06 23:15:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (4096,), dtype: float32
17%|█▋ | 33/195 [00:27<02:02, 1.32it/s] [2024-06-06 23:15:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
17%|█▋ | 33/195 [00:27<02:02, 1.32it/s] [2024-06-06 23:15:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
17%|█▋ | 33/195 [00:27<02:02, 1.32it/s] 18%|█▊ | 35/195 [00:27<01:27, 1.83it/s] [2024-06-06 23:15:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
18%|█▊ | 35/195 [00:27<01:27, 1.83it/s] [2024-06-06 23:15:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
18%|█▊ | 35/195 [00:27<01:27, 1.83it/s] 18%|█▊ | 36/195 [00:27<01:16, 2.09it/s] [2024-06-06 23:15:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (4096,), dtype: float32
18%|█▊ | 36/195 [00:27<01:16, 2.09it/s] [2024-06-06 23:15:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
18%|█▊ | 36/195 [00:28<01:16, 2.09it/s] [2024-06-06 23:15:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
18%|█▊ | 36/195 [00:28<01:16, 2.09it/s] 19%|█▉ | 38/195 [00:28<01:01, 2.57it/s] [2024-06-06 23:15:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
19%|█▉ | 38/195 [00:30<01:01, 2.57it/s] [2024-06-06 23:15:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
19%|█▉ | 38/195 [00:30<01:01, 2.57it/s] 20%|██ | 39/195 [00:30<01:59, 1.30it/s] [2024-06-06 23:15:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (4096,), dtype: float32
20%|██ | 39/195 [00:30<01:59, 1.30it/s] [2024-06-06 23:15:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
20%|██ | 39/195 [00:30<01:59, 1.30it/s] [2024-06-06 23:15:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
20%|██ | 39/195 [00:30<01:59, 1.30it/s] 21%|██ | 41/195 [00:30<01:27, 1.76it/s] [2024-06-06 23:15:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
21%|██ | 41/195 [00:31<01:27, 1.76it/s] [2024-06-06 23:15:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
21%|██ | 41/195 [00:31<01:27, 1.76it/s] [2024-06-06 23:15:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (4096,), dtype: float32
21%|██ | 41/195 [00:31<01:27, 1.76it/s] [2024-06-06 23:15:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
21%|██ | 41/195 [00:31<01:27, 1.76it/s] [2024-06-06 23:15:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
21%|██ | 41/195 [00:31<01:27, 1.76it/s] 23%|██▎ | 44/195 [00:31<00:58, 2.57it/s] [2024-06-06 23:15:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
23%|██▎ | 44/195 [00:33<00:58, 2.57it/s] [2024-06-06 23:15:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
23%|██▎ | 44/195 [00:34<00:58, 2.57it/s] 23%|██▎ | 45/195 [00:34<01:56, 1.28it/s] [2024-06-06 23:15:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (4096,), dtype: float32
23%|██▎ | 45/195 [00:34<01:56, 1.28it/s] [2024-06-06 23:15:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
23%|██▎ | 45/195 [00:34<01:56, 1.28it/s] [2024-06-06 23:15:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
23%|██▎ | 45/195 [00:34<01:56, 1.28it/s] 24%|██▍ | 47/195 [00:34<01:26, 1.70it/s] [2024-06-06 23:15:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
24%|██▍ | 47/195 [00:34<01:26, 1.70it/s] [2024-06-06 23:15:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
24%|██▍ | 47/195 [00:34<01:26, 1.70it/s] [2024-06-06 23:15:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (4096,), dtype: float32
24%|██▍ | 47/195 [00:34<01:26, 1.70it/s] [2024-06-06 23:15:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
24%|██▍ | 47/195 [00:34<01:26, 1.70it/s] [2024-06-06 23:15:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
24%|██▍ | 47/195 [00:35<01:26, 1.70it/s] 26%|██▌ | 50/195 [00:35<01:01, 2.36it/s] [2024-06-06 23:15:13] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
26%|██▌ | 50/195 [00:37<01:01, 2.36it/s] [2024-06-06 23:15:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
26%|██▌ | 50/195 [00:37<01:01, 2.36it/s] 26%|██▌ | 51/195 [00:37<01:48, 1.33it/s] [2024-06-06 23:15:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (4096,), dtype: float32
26%|██▌ | 51/195 [00:37<01:48, 1.33it/s] [2024-06-06 23:15:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
26%|██▌ | 51/195 [00:37<01:48, 1.33it/s] [2024-06-06 23:15:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
26%|██▌ | 51/195 [00:37<01:48, 1.33it/s] 27%|██▋ | 53/195 [00:37<01:17, 1.84it/s] [2024-06-06 23:15:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
27%|██▋ | 53/195 [00:37<01:17, 1.84it/s] [2024-06-06 23:15:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
27%|██▋ | 53/195 [00:37<01:17, 1.84it/s] [2024-06-06 23:15:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (4096,), dtype: float32
27%|██▋ | 53/195 [00:37<01:17, 1.84it/s] [2024-06-06 23:15:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
27%|██▋ | 53/195 [00:38<01:17, 1.84it/s] [2024-06-06 23:15:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
27%|██▋ | 53/195 [00:38<01:17, 1.84it/s] 29%|██▊ | 56/195 [00:38<00:57, 2.43it/s] [2024-06-06 23:15:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
29%|██▊ | 56/195 [00:40<00:57, 2.43it/s] [2024-06-06 23:15:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
29%|██▊ | 56/195 [00:40<00:57, 2.43it/s] 29%|██▉ | 57/195 [00:40<01:44, 1.32it/s] [2024-06-06 23:15:17] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (4096,), dtype: float32
29%|██▉ | 57/195 [00:40<01:44, 1.32it/s] [2024-06-06 23:15:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
29%|██▉ | 57/195 [00:41<01:44, 1.32it/s] [2024-06-06 23:15:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
29%|██▉ | 57/195 [00:41<01:44, 1.32it/s] 30%|███ | 59/195 [00:41<01:14, 1.83it/s] [2024-06-06 23:15:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
30%|███ | 59/195 [00:41<01:14, 1.83it/s] [2024-06-06 23:15:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
30%|███ | 59/195 [00:41<01:14, 1.83it/s] 31%|███ | 60/195 [00:41<01:04, 2.09it/s] [2024-06-06 23:15:18] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00001-of-00004.safetensors
31%|███ | 60/195 [00:41<01:04, 2.09it/s] [2024-06-06 23:15:18] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00002-of-00004.safetensors
31%|███ | 60/195 [00:41<01:04, 2.09it/s] [2024-06-06 23:15:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (4096,), dtype: float32
31%|███ | 60/195 [00:41<01:04, 2.09it/s] 31%|███▏ | 61/195 [00:41<00:58, 2.29it/s] [2024-06-06 23:15:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
31%|███▏ | 61/195 [00:41<00:58, 2.29it/s] [2024-06-06 23:15:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
31%|███▏ | 61/195 [00:41<00:58, 2.29it/s] 32%|███▏ | 62/195 [00:41<00:59, 2.23it/s] [2024-06-06 23:15:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
32%|███▏ | 62/195 [00:44<00:59, 2.23it/s] [2024-06-06 23:15:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
32%|███▏ | 62/195 [00:44<00:59, 2.23it/s] 32%|███▏ | 63/195 [00:44<02:05, 1.05it/s] [2024-06-06 23:15:21] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (4096,), dtype: float32
32%|███▏ | 63/195 [00:44<02:05, 1.05it/s] [2024-06-06 23:15:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
32%|███▏ | 63/195 [00:44<02:05, 1.05it/s] [2024-06-06 23:15:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
32%|███▏ | 63/195 [00:44<02:05, 1.05it/s] 33%|███▎ | 65/195 [00:44<01:21, 1.60it/s] [2024-06-06 23:15:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
33%|███▎ | 65/195 [00:44<01:21, 1.60it/s] [2024-06-06 23:15:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
33%|███▎ | 65/195 [00:44<01:21, 1.60it/s] [2024-06-06 23:15:21] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (4096,), dtype: float32
33%|███▎ | 65/195 [00:44<01:21, 1.60it/s] [2024-06-06 23:15:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
33%|███▎ | 65/195 [00:45<01:21, 1.60it/s] [2024-06-06 23:15:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
33%|███▎ | 65/195 [00:45<01:21, 1.60it/s] 35%|███▍ | 68/195 [00:45<00:53, 2.37it/s] [2024-06-06 23:15:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
35%|███▍ | 68/195 [00:47<00:53, 2.37it/s] [2024-06-06 23:15:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
35%|███▍ | 68/195 [00:48<00:53, 2.37it/s] 35%|███▌ | 69/195 [00:48<01:44, 1.20it/s] [2024-06-06 23:15:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (4096,), dtype: float32
35%|███▌ | 69/195 [00:48<01:44, 1.20it/s] [2024-06-06 23:15:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
35%|███▌ | 69/195 [00:48<01:44, 1.20it/s] [2024-06-06 23:15:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
35%|███▌ | 69/195 [00:48<01:44, 1.20it/s] 36%|███▋ | 71/195 [00:48<01:13, 1.69it/s] [2024-06-06 23:15:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
36%|███▋ | 71/195 [00:48<01:13, 1.69it/s] [2024-06-06 23:15:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
36%|███▋ | 71/195 [00:48<01:13, 1.69it/s] [2024-06-06 23:15:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (4096,), dtype: float32
36%|███▋ | 71/195 [00:48<01:13, 1.69it/s] [2024-06-06 23:15:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
36%|███▋ | 71/195 [00:48<01:13, 1.69it/s] [2024-06-06 23:15:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
36%|███▋ | 71/195 [00:48<01:13, 1.69it/s] 38%|███▊ | 74/195 [00:48<00:50, 2.39it/s] [2024-06-06 23:15:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
38%|███▊ | 74/195 [00:50<00:50, 2.39it/s] [2024-06-06 23:15:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
38%|███▊ | 74/195 [00:51<00:50, 2.39it/s] 38%|███▊ | 75/195 [00:51<01:31, 1.31it/s] [2024-06-06 23:15:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (4096,), dtype: float32
38%|███▊ | 75/195 [00:51<01:31, 1.31it/s] [2024-06-06 23:15:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
38%|███▊ | 75/195 [00:51<01:31, 1.31it/s] [2024-06-06 23:15:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
38%|███▊ | 75/195 [00:51<01:31, 1.31it/s] 39%|███▉ | 77/195 [00:51<01:04, 1.83it/s] [2024-06-06 23:15:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
39%|███▉ | 77/195 [00:51<01:04, 1.83it/s] [2024-06-06 23:15:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
39%|███▉ | 77/195 [00:51<01:04, 1.83it/s] [2024-06-06 23:15:28] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (4096,), dtype: float32
39%|███▉ | 77/195 [00:51<01:04, 1.83it/s] [2024-06-06 23:15:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
39%|███▉ | 77/195 [00:51<01:04, 1.83it/s] [2024-06-06 23:15:28] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
39%|███▉ | 77/195 [00:51<01:04, 1.83it/s] 41%|████ | 80/195 [00:52<00:46, 2.48it/s] [2024-06-06 23:15:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
41%|████ | 80/195 [00:54<00:46, 2.48it/s] [2024-06-06 23:15:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
41%|████ | 80/195 [00:54<00:46, 2.48it/s] 42%|████▏ | 81/195 [00:54<01:28, 1.29it/s] [2024-06-06 23:15:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (4096,), dtype: float32
42%|████▏ | 81/195 [00:54<01:28, 1.29it/s] [2024-06-06 23:15:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
42%|████▏ | 81/195 [00:54<01:28, 1.29it/s] [2024-06-06 23:15:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
42%|████▏ | 81/195 [00:54<01:28, 1.29it/s] 43%|████▎ | 83/195 [00:54<01:02, 1.79it/s] [2024-06-06 23:15:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
43%|████▎ | 83/195 [00:55<01:02, 1.79it/s] [2024-06-06 23:15:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
43%|████▎ | 83/195 [00:55<01:02, 1.79it/s] 43%|████▎ | 84/195 [00:55<00:54, 2.04it/s] [2024-06-06 23:15:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (4096,), dtype: float32
43%|████▎ | 84/195 [00:55<00:54, 2.04it/s] [2024-06-06 23:15:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
43%|████▎ | 84/195 [00:55<00:54, 2.04it/s] [2024-06-06 23:15:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
43%|████▎ | 84/195 [00:55<00:54, 2.04it/s] 44%|████▍ | 86/195 [00:55<00:42, 2.59it/s] [2024-06-06 23:15:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
44%|████▍ | 86/195 [00:57<00:42, 2.59it/s] [2024-06-06 23:15:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
44%|████▍ | 86/195 [00:57<00:42, 2.59it/s] 45%|████▍ | 87/195 [00:57<01:16, 1.41it/s] [2024-06-06 23:15:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (4096,), dtype: float32
45%|████▍ | 87/195 [00:57<01:16, 1.41it/s] [2024-06-06 23:15:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
45%|████▍ | 87/195 [00:57<01:16, 1.41it/s] [2024-06-06 23:15:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
45%|████▍ | 87/195 [00:57<01:16, 1.41it/s] 46%|████▌ | 89/195 [00:57<00:54, 1.95it/s] [2024-06-06 23:15:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
46%|████▌ | 89/195 [00:57<00:54, 1.95it/s] [2024-06-06 23:15:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
46%|████▌ | 89/195 [00:57<00:54, 1.95it/s] [2024-06-06 23:15:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (4096,), dtype: float32
46%|████▌ | 89/195 [00:57<00:54, 1.95it/s] [2024-06-06 23:15:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
46%|████▌ | 89/195 [00:58<00:54, 1.95it/s] [2024-06-06 23:15:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
46%|████▌ | 89/195 [00:58<00:54, 1.95it/s] 47%|████▋ | 92/195 [00:58<00:36, 2.81it/s] [2024-06-06 23:15:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
47%|████▋ | 92/195 [00:59<00:36, 2.81it/s] [2024-06-06 23:15:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
47%|████▋ | 92/195 [01:00<00:36, 2.81it/s] 48%|████▊ | 93/195 [01:00<01:02, 1.62it/s] [2024-06-06 23:15:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (4096,), dtype: float32
48%|████▊ | 93/195 [01:00<01:02, 1.62it/s] [2024-06-06 23:15:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
48%|████▊ | 93/195 [01:00<01:02, 1.62it/s] [2024-06-06 23:15:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
48%|████▊ | 93/195 [01:00<01:02, 1.62it/s] 49%|████▊ | 95/195 [01:00<00:45, 2.18it/s] [2024-06-06 23:15:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
49%|████▊ | 95/195 [01:00<00:45, 2.18it/s] [2024-06-06 23:15:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
49%|████▊ | 95/195 [01:00<00:45, 2.18it/s] [2024-06-06 23:15:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (4096,), dtype: float32
49%|████▊ | 95/195 [01:00<00:45, 2.18it/s] [2024-06-06 23:15:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
49%|████▊ | 95/195 [01:00<00:45, 2.18it/s] [2024-06-06 23:15:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
49%|████▊ | 95/195 [01:00<00:45, 2.18it/s] 50%|█████ | 98/195 [01:00<00:32, 2.99it/s] [2024-06-06 23:15:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
50%|█████ | 98/195 [01:02<00:32, 2.99it/s] [2024-06-06 23:15:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
50%|█████ | 98/195 [01:02<00:32, 2.99it/s] 51%|█████ | 99/195 [01:03<00:59, 1.60it/s] [2024-06-06 23:15:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (4096,), dtype: float32
51%|█████ | 99/195 [01:03<00:59, 1.60it/s] [2024-06-06 23:15:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
51%|█████ | 99/195 [01:03<00:59, 1.60it/s] [2024-06-06 23:15:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
51%|█████ | 99/195 [01:03<00:59, 1.60it/s] 52%|█████▏ | 101/195 [01:03<00:42, 2.20it/s] [2024-06-06 23:15:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
52%|█████▏ | 101/195 [01:03<00:42, 2.20it/s] [2024-06-06 23:15:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
52%|█████▏ | 101/195 [01:03<00:42, 2.20it/s] [2024-06-06 23:15:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (4096,), dtype: float32
52%|█████▏ | 101/195 [01:03<00:42, 2.20it/s] [2024-06-06 23:15:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
52%|█████▏ | 101/195 [01:03<00:42, 2.20it/s] [2024-06-06 23:15:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
52%|█████▏ | 101/195 [01:03<00:42, 2.20it/s] 53%|█████▎ | 104/195 [01:03<00:31, 2.85it/s] [2024-06-06 23:15:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
53%|█████▎ | 104/195 [01:05<00:31, 2.85it/s] [2024-06-06 23:15:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
53%|█████▎ | 104/195 [01:05<00:31, 2.85it/s] 54%|█████▍ | 105/195 [01:05<00:54, 1.64it/s] [2024-06-06 23:15:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (4096,), dtype: float32
54%|█████▍ | 105/195 [01:05<00:54, 1.64it/s] [2024-06-06 23:15:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
54%|█████▍ | 105/195 [01:05<00:54, 1.64it/s] [2024-06-06 23:15:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
54%|█████▍ | 105/195 [01:05<00:54, 1.64it/s] 55%|█████▍ | 107/195 [01:05<00:39, 2.24it/s] [2024-06-06 23:15:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
55%|█████▍ | 107/195 [01:06<00:39, 2.24it/s] [2024-06-06 23:15:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
55%|█████▍ | 107/195 [01:06<00:39, 2.24it/s] 55%|█████▌ | 108/195 [01:06<00:34, 2.51it/s] [2024-06-06 23:15:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (4096,), dtype: float32
55%|█████▌ | 108/195 [01:06<00:34, 2.51it/s] [2024-06-06 23:15:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
55%|█████▌ | 108/195 [01:06<00:34, 2.51it/s] [2024-06-06 23:15:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
55%|█████▌ | 108/195 [01:06<00:34, 2.51it/s] 56%|█████▋ | 110/195 [01:06<00:27, 3.04it/s] [2024-06-06 23:15:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
56%|█████▋ | 110/195 [01:08<00:27, 3.04it/s] [2024-06-06 23:15:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
56%|█████▋ | 110/195 [01:08<00:27, 3.04it/s] 57%|█████▋ | 111/195 [01:08<00:54, 1.54it/s] [2024-06-06 23:15:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (4096,), dtype: float32
57%|█████▋ | 111/195 [01:08<00:54, 1.54it/s] [2024-06-06 23:15:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
57%|█████▋ | 111/195 [01:08<00:54, 1.54it/s] [2024-06-06 23:15:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
57%|█████▋ | 111/195 [01:08<00:54, 1.54it/s] 58%|█████▊ | 113/195 [01:08<00:38, 2.11it/s] [2024-06-06 23:15:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
58%|█████▊ | 113/195 [01:08<00:38, 2.11it/s] [2024-06-06 23:15:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
58%|█████▊ | 113/195 [01:08<00:38, 2.11it/s] [2024-06-06 23:15:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (4096,), dtype: float32
58%|█████▊ | 113/195 [01:08<00:38, 2.11it/s] [2024-06-06 23:15:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
58%|█████▊ | 113/195 [01:09<00:38, 2.11it/s] [2024-06-06 23:15:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
58%|█████▊ | 113/195 [01:09<00:38, 2.11it/s] 59%|█████▉ | 116/195 [01:09<00:26, 2.97it/s] [2024-06-06 23:15:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
59%|█████▉ | 116/195 [01:11<00:26, 2.97it/s] [2024-06-06 23:15:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
59%|█████▉ | 116/195 [01:11<00:26, 2.97it/s] 60%|██████ | 117/195 [01:11<00:49, 1.58it/s] [2024-06-06 23:15:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (4096,), dtype: float32
60%|██████ | 117/195 [01:11<00:49, 1.58it/s] [2024-06-06 23:15:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
60%|██████ | 117/195 [01:11<00:49, 1.58it/s] [2024-06-06 23:15:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
60%|██████ | 117/195 [01:11<00:49, 1.58it/s] 61%|██████ | 119/195 [01:11<00:35, 2.12it/s] [2024-06-06 23:15:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
61%|██████ | 119/195 [01:11<00:35, 2.12it/s] [2024-06-06 23:15:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
61%|██████ | 119/195 [01:11<00:35, 2.12it/s] [2024-06-06 23:15:48] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Hermes-2-Pro-Llama-3-8B/model-00003-of-00004.safetensors
61%|██████ | 119/195 [01:11<00:35, 2.12it/s] [2024-06-06 23:15:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
61%|██████ | 119/195 [01:13<00:35, 2.12it/s] [2024-06-06 23:15:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
61%|██████ | 119/195 [01:14<00:35, 2.12it/s] 62%|██████▏ | 121/195 [01:14<00:54, 1.37it/s] [2024-06-06 23:15:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
62%|██████▏ | 121/195 [01:14<00:54, 1.37it/s] [2024-06-06 23:15:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
62%|██████▏ | 121/195 [01:14<00:54, 1.37it/s] 63%|██████▎ | 122/195 [01:14<00:47, 1.53it/s] [2024-06-06 23:15:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
63%|██████▎ | 122/195 [01:14<00:47, 1.53it/s] [2024-06-06 23:15:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
63%|██████▎ | 122/195 [01:14<00:47, 1.53it/s] [2024-06-06 23:15:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (4096,), dtype: float32
63%|██████▎ | 122/195 [01:14<00:47, 1.53it/s] [2024-06-06 23:15:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
63%|██████▎ | 122/195 [01:14<00:47, 1.53it/s] [2024-06-06 23:15:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
63%|██████▎ | 122/195 [01:15<00:47, 1.53it/s] 64%|██████▍ | 125/195 [01:15<00:30, 2.26it/s] [2024-06-06 23:15:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
64%|██████▍ | 125/195 [01:17<00:30, 2.26it/s] [2024-06-06 23:15:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
64%|██████▍ | 125/195 [01:17<00:30, 2.26it/s] 65%|██████▍ | 126/195 [01:17<00:57, 1.21it/s] [2024-06-06 23:15:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (4096,), dtype: float32
65%|██████▍ | 126/195 [01:17<00:57, 1.21it/s] [2024-06-06 23:15:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
65%|██████▍ | 126/195 [01:17<00:57, 1.21it/s] [2024-06-06 23:15:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
65%|██████▍ | 126/195 [01:17<00:57, 1.21it/s] 66%|██████▌ | 128/195 [01:17<00:39, 1.72it/s] [2024-06-06 23:15:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
66%|██████▌ | 128/195 [01:17<00:39, 1.72it/s] [2024-06-06 23:15:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
66%|██████▌ | 128/195 [01:17<00:39, 1.72it/s] [2024-06-06 23:15:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (4096,), dtype: float32
66%|██████▌ | 128/195 [01:17<00:39, 1.72it/s] [2024-06-06 23:15:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
66%|██████▌ | 128/195 [01:18<00:39, 1.72it/s] [2024-06-06 23:15:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
66%|██████▌ | 128/195 [01:18<00:39, 1.72it/s] 67%|██████▋ | 131/195 [01:18<00:28, 2.28it/s] [2024-06-06 23:15:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (4096,), dtype: float32
67%|██████▋ | 131/195 [01:18<00:28, 2.28it/s] [2024-06-06 23:15:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (4096,), dtype: float32
67%|██████▋ | 131/195 [01:18<00:28, 2.28it/s] [2024-06-06 23:15:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
67%|██████▋ | 131/195 [01:19<00:28, 2.28it/s] [2024-06-06 23:15:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
67%|██████▋ | 131/195 [01:19<00:28, 2.28it/s] 69%|██████▊ | 134/195 [01:19<00:21, 2.87it/s] [2024-06-06 23:15:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
69%|██████▊ | 134/195 [01:21<00:21, 2.87it/s] [2024-06-06 23:15:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
69%|██████▊ | 134/195 [01:21<00:21, 2.87it/s] 69%|██████▉ | 135/195 [01:21<00:41, 1.46it/s] [2024-06-06 23:15:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (4096,), dtype: float32
69%|██████▉ | 135/195 [01:21<00:41, 1.46it/s] [2024-06-06 23:15:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
69%|██████▉ | 135/195 [01:21<00:41, 1.46it/s] [2024-06-06 23:15:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
69%|██████▉ | 135/195 [01:21<00:41, 1.46it/s] 70%|███████ | 137/195 [01:21<00:29, 1.98it/s] [2024-06-06 23:15:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
70%|███████ | 137/195 [01:22<00:29, 1.98it/s] [2024-06-06 23:15:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
70%|███████ | 137/195 [01:22<00:29, 1.98it/s] 71%|███████ | 138/195 [01:22<00:25, 2.23it/s] [2024-06-06 23:15:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (4096,), dtype: float32
71%|███████ | 138/195 [01:22<00:25, 2.23it/s] [2024-06-06 23:15:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
71%|███████ | 138/195 [01:22<00:25, 2.23it/s] [2024-06-06 23:15:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
71%|███████ | 138/195 [01:22<00:25, 2.23it/s] 72%|███████▏ | 140/195 [01:22<00:21, 2.61it/s] [2024-06-06 23:16:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
72%|███████▏ | 140/195 [01:24<00:21, 2.61it/s] [2024-06-06 23:16:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
72%|███████▏ | 140/195 [01:25<00:21, 2.61it/s] 72%|███████▏ | 141/195 [01:25<00:42, 1.28it/s] [2024-06-06 23:16:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (4096,), dtype: float32
72%|███████▏ | 141/195 [01:25<00:42, 1.28it/s] [2024-06-06 23:16:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
72%|███████▏ | 141/195 [01:25<00:42, 1.28it/s] [2024-06-06 23:16:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
72%|███████▏ | 141/195 [01:25<00:42, 1.28it/s] 73%|███████▎ | 143/195 [01:25<00:29, 1.78it/s] [2024-06-06 23:16:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
73%|███████▎ | 143/195 [01:25<00:29, 1.78it/s] [2024-06-06 23:16:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
73%|███████▎ | 143/195 [01:25<00:29, 1.78it/s] [2024-06-06 23:16:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (4096,), dtype: float32
73%|███████▎ | 143/195 [01:25<00:29, 1.78it/s] [2024-06-06 23:16:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
73%|███████▎ | 143/195 [01:25<00:29, 1.78it/s] [2024-06-06 23:16:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
73%|███████▎ | 143/195 [01:25<00:29, 1.78it/s] 75%|███████▍ | 146/195 [01:25<00:19, 2.54it/s] [2024-06-06 23:16:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
75%|███████▍ | 146/195 [01:28<00:19, 2.54it/s] [2024-06-06 23:16:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
75%|███████▍ | 146/195 [01:28<00:19, 2.54it/s] 75%|███████▌ | 147/195 [01:28<00:35, 1.36it/s] [2024-06-06 23:16:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (4096,), dtype: float32
75%|███████▌ | 147/195 [01:28<00:35, 1.36it/s] [2024-06-06 23:16:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
75%|███████▌ | 147/195 [01:28<00:35, 1.36it/s] [2024-06-06 23:16:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
75%|███████▌ | 147/195 [01:28<00:35, 1.36it/s] 76%|███████▋ | 149/195 [01:28<00:24, 1.85it/s] [2024-06-06 23:16:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
76%|███████▋ | 149/195 [01:28<00:24, 1.85it/s] [2024-06-06 23:16:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
76%|███████▋ | 149/195 [01:28<00:24, 1.85it/s] [2024-06-06 23:16:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (4096,), dtype: float32
76%|███████▋ | 149/195 [01:28<00:24, 1.85it/s] [2024-06-06 23:16:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
76%|███████▋ | 149/195 [01:29<00:24, 1.85it/s] [2024-06-06 23:16:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
76%|███████▋ | 149/195 [01:29<00:24, 1.85it/s] 78%|███████▊ | 152/195 [01:29<00:16, 2.54it/s] [2024-06-06 23:16:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
78%|███████▊ | 152/195 [01:31<00:16, 2.54it/s] [2024-06-06 23:16:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
78%|███████▊ | 152/195 [01:31<00:16, 2.54it/s] 78%|███████▊ | 153/195 [01:31<00:30, 1.39it/s] [2024-06-06 23:16:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (4096,), dtype: float32
78%|███████▊ | 153/195 [01:31<00:30, 1.39it/s] [2024-06-06 23:16:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
78%|███████▊ | 153/195 [01:31<00:30, 1.39it/s] [2024-06-06 23:16:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
78%|███████▊ | 153/195 [01:31<00:30, 1.39it/s] 79%|███████▉ | 155/195 [01:31<00:20, 1.93it/s] [2024-06-06 23:16:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
79%|███████▉ | 155/195 [01:31<00:20, 1.93it/s] [2024-06-06 23:16:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
79%|███████▉ | 155/195 [01:31<00:20, 1.93it/s] [2024-06-06 23:16:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (4096,), dtype: float32
79%|███████▉ | 155/195 [01:31<00:20, 1.93it/s] [2024-06-06 23:16:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
79%|███████▉ | 155/195 [01:32<00:20, 1.93it/s] [2024-06-06 23:16:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
79%|███████▉ | 155/195 [01:32<00:20, 1.93it/s] 81%|████████ | 158/195 [01:32<00:14, 2.52it/s] [2024-06-06 23:16:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
81%|████████ | 158/195 [01:34<00:14, 2.52it/s] [2024-06-06 23:16:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
81%|████████ | 158/195 [01:34<00:14, 2.52it/s] 82%|████████▏ | 159/195 [01:34<00:26, 1.35it/s] [2024-06-06 23:16:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (4096,), dtype: float32
82%|████████▏ | 159/195 [01:34<00:26, 1.35it/s] [2024-06-06 23:16:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
82%|████████▏ | 159/195 [01:35<00:26, 1.35it/s] [2024-06-06 23:16:11] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
82%|████████▏ | 159/195 [01:35<00:26, 1.35it/s] 83%|████████▎ | 161/195 [01:35<00:18, 1.86it/s] [2024-06-06 23:16:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
83%|████████▎ | 161/195 [01:35<00:18, 1.86it/s] [2024-06-06 23:16:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
83%|████████▎ | 161/195 [01:35<00:18, 1.86it/s] 83%|████████▎ | 162/195 [01:35<00:15, 2.12it/s] [2024-06-06 23:16:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (4096,), dtype: float32
83%|████████▎ | 162/195 [01:35<00:15, 2.12it/s] [2024-06-06 23:16:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
83%|████████▎ | 162/195 [01:35<00:15, 2.12it/s] [2024-06-06 23:16:12] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
83%|████████▎ | 162/195 [01:35<00:15, 2.12it/s] 84%|████████▍ | 164/195 [01:35<00:12, 2.45it/s] [2024-06-06 23:16:14] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
84%|████████▍ | 164/195 [01:38<00:12, 2.45it/s] [2024-06-06 23:16:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
84%|████████▍ | 164/195 [01:38<00:12, 2.45it/s] 85%|████████▍ | 165/195 [01:38<00:25, 1.19it/s] [2024-06-06 23:16:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (4096,), dtype: float32
85%|████████▍ | 165/195 [01:38<00:25, 1.19it/s] [2024-06-06 23:16:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
85%|████████▍ | 165/195 [01:38<00:25, 1.19it/s] [2024-06-06 23:16:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
85%|████████▍ | 165/195 [01:38<00:25, 1.19it/s] 86%|████████▌ | 167/195 [01:38<00:16, 1.68it/s] [2024-06-06 23:16:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
86%|████████▌ | 167/195 [01:38<00:16, 1.68it/s] [2024-06-06 23:16:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
86%|████████▌ | 167/195 [01:38<00:16, 1.68it/s] [2024-06-06 23:16:15] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (4096,), dtype: float32
86%|████████▌ | 167/195 [01:38<00:16, 1.68it/s] [2024-06-06 23:16:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
86%|████████▌ | 167/195 [01:39<00:16, 1.68it/s] [2024-06-06 23:16:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
86%|████████▌ | 167/195 [01:39<00:16, 1.68it/s] 87%|████████▋ | 170/195 [01:39<00:10, 2.36it/s] [2024-06-06 23:16:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
87%|████████▋ | 170/195 [01:41<00:10, 2.36it/s] [2024-06-06 23:16:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
87%|████████▋ | 170/195 [01:41<00:10, 2.36it/s] 88%|████████▊ | 171/195 [01:41<00:18, 1.31it/s] [2024-06-06 23:16:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (4096,), dtype: float32
88%|████████▊ | 171/195 [01:41<00:18, 1.31it/s] [2024-06-06 23:16:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
88%|████████▊ | 171/195 [01:41<00:18, 1.31it/s] [2024-06-06 23:16:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
88%|████████▊ | 171/195 [01:42<00:18, 1.31it/s] 89%|████████▊ | 173/195 [01:42<00:12, 1.81it/s] [2024-06-06 23:16:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
89%|████████▊ | 173/195 [01:42<00:12, 1.81it/s] [2024-06-06 23:16:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
89%|████████▊ | 173/195 [01:42<00:12, 1.81it/s] [2024-06-06 23:16:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.input_layernorm.weight", shape: (4096,), dtype: float32
89%|████████▊ | 173/195 [01:42<00:12, 1.81it/s] [2024-06-06 23:16:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
89%|████████▊ | 173/195 [01:42<00:12, 1.81it/s] [2024-06-06 23:16:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
89%|████████▊ | 173/195 [01:42<00:12, 1.81it/s] 90%|█████████ | 176/195 [01:42<00:07, 2.57it/s] [2024-06-06 23:16:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
90%|█████████ | 176/195 [01:44<00:07, 2.57it/s] [2024-06-06 23:16:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
90%|█████████ | 176/195 [01:44<00:07, 2.57it/s] 91%|█████████ | 177/195 [01:44<00:12, 1.47it/s] [2024-06-06 23:16:21] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.28.post_attention_layernorm.weight", shape: (4096,), dtype: float32
91%|█████████ | 177/195 [01:44<00:12, 1.47it/s] [2024-06-06 23:16:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
91%|█████████ | 177/195 [01:44<00:12, 1.47it/s] [2024-06-06 23:16:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
91%|█████████ | 177/195 [01:44<00:12, 1.47it/s] 92%|█████████▏| 179/195 [01:44<00:07, 2.03it/s] [2024-06-06 23:16:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
92%|█████████▏| 179/195 [01:44<00:07, 2.03it/s] [2024-06-06 23:16:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
92%|█████████▏| 179/195 [01:44<00:07, 2.03it/s] [2024-06-06 23:16:21] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.input_layernorm.weight", shape: (4096,), dtype: float32
92%|█████████▏| 179/195 [01:44<00:07, 2.03it/s] [2024-06-06 23:16:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
92%|█████████▏| 179/195 [01:45<00:07, 2.03it/s] [2024-06-06 23:16:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
92%|█████████▏| 179/195 [01:45<00:07, 2.03it/s] 93%|█████████▎| 182/195 [01:45<00:04, 2.68it/s] [2024-06-06 23:16:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
93%|█████████▎| 182/195 [01:47<00:04, 2.68it/s] [2024-06-06 23:16:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
93%|█████████▎| 182/195 [01:47<00:04, 2.68it/s] 94%|█████████▍| 183/195 [01:47<00:08, 1.46it/s] [2024-06-06 23:16:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.29.post_attention_layernorm.weight", shape: (4096,), dtype: float32
94%|█████████▍| 183/195 [01:47<00:08, 1.46it/s] [2024-06-06 23:16:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
94%|█████████▍| 183/195 [01:47<00:08, 1.46it/s] [2024-06-06 23:16:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
94%|█████████▍| 183/195 [01:47<00:08, 1.46it/s] 95%|█████████▍| 185/195 [01:47<00:04, 2.01it/s] [2024-06-06 23:16:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
95%|█████████▍| 185/195 [01:47<00:04, 2.01it/s] [2024-06-06 23:16:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
95%|█████████▍| 185/195 [01:48<00:04, 2.01it/s] 95%|█████████▌| 186/195 [01:48<00:03, 2.27it/s] [2024-06-06 23:16:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.input_layernorm.weight", shape: (4096,), dtype: float32
95%|█████████▌| 186/195 [01:48<00:03, 2.27it/s] [2024-06-06 23:16:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_weight", shape: (4096, 1792), dtype: uint32
95%|█████████▌| 186/195 [01:48<00:03, 2.27it/s] [2024-06-06 23:16:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_scale", shape: (4096, 448), dtype: float32
95%|█████████▌| 186/195 [01:48<00:03, 2.27it/s] 96%|█████████▋| 188/195 [01:48<00:02, 2.83it/s] [2024-06-06 23:16:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
96%|█████████▋| 188/195 [01:50<00:02, 2.83it/s] [2024-06-06 23:16:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
96%|█████████▋| 188/195 [01:50<00:02, 2.83it/s] 97%|█████████▋| 189/195 [01:50<00:04, 1.40it/s] [2024-06-06 23:16:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.30.post_attention_layernorm.weight", shape: (4096,), dtype: float32
97%|█████████▋| 189/195 [01:50<00:04, 1.40it/s] [2024-06-06 23:16:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
97%|█████████▋| 189/195 [01:50<00:04, 1.40it/s] [2024-06-06 23:16:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
97%|█████████▋| 189/195 [01:50<00:04, 1.40it/s] 98%|█████████▊| 191/195 [01:50<00:02, 1.95it/s] [2024-06-06 23:16:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
98%|█████████▊| 191/195 [01:51<00:02, 1.95it/s] [2024-06-06 23:16:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
98%|█████████▊| 191/195 [01:51<00:02, 1.95it/s] [2024-06-06 23:16:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_weight", shape: (28672, 512), dtype: uint32
98%|█████████▊| 191/195 [01:53<00:02, 1.95it/s] [2024-06-06 23:16:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_scale", shape: (28672, 128), dtype: float32
98%|█████████▊| 191/195 [01:53<00:02, 1.95it/s] 99%|█████████▉| 193/195 [01:53<00:01, 1.33it/s] [2024-06-06 23:16:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_weight", shape: (6144, 512), dtype: uint32
99%|█████████▉| 193/195 [01:53<00:01, 1.33it/s] [2024-06-06 23:16:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_scale", shape: (6144, 128), dtype: float32
99%|█████████▉| 193/195 [01:53<00:01, 1.33it/s] 99%|█████████▉| 194/195 [01:53<00:00, 1.56it/s] [2024-06-06 23:16:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
99%|█████████▉| 194/195 [01:53<00:00, 1.56it/s] [2024-06-06 23:16:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float32
99%|█████████▉| 194/195 [01:53<00:00, 1.56it/s] 100%|██████████| 195/195 [01:53<00:00, 1.83it/s] 100%|██████████| 195/195 [01:53<00:00, 1.71it/s]
[2024-06-06 23:16:30] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00002-of-00004.safetensors
[2024-06-06 23:16:30] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Hermes-2-Pro-Llama-3-8B/model-00003-of-00004.safetensors
[2024-06-06 23:16:31] INFO stats.py:77: Time usage: HF loading: 1.576 sec; Pre-quantization mapping: 84.298 sec; Quantization: 3.067 sec
[2024-06-06 23:16:31] INFO stats.py:91: RAM usage: Peak RAM: 9.235 GB. Total bytes loaded from disk: 14.958 GB
[2024-06-06 23:16:31] INFO convert_weight.py:155: Parameter size after quantization: 4.675 GB
[2024-06-06 23:16:31] INFO convert_weight.py:160: Total parameters: 8,030,523,392
[2024-06-06 23:16:31] INFO convert_weight.py:161: Bits per parameter: 5.001
[2024-06-06 23:16:31] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC
All finished, 108 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC/ndarray-cache.json
Also saved a bf16 record to /models/mlc-delivery/hf/mlc-ai/Hermes-2-Pro-Llama-3-8B-q4f32_1-MLC/ndarray-cache-b16.json