Hugging Face's logo

mlc-ai
/
Qwen1.5-1.8B-Chat-q4f32_1-MLC

MLC-LLM
web-llm
Model card Files Community
Qwen1.5-1.8B-Chat-q4f32_1-MLC / logs.txt
riczhou's picture
riczhou
Initial commit
9e022b3 verified
raw
history blame contribute delete
No virus
83.8 kB
/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Qwen1.5-1.8B-Chat --quantization q4f32_1 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC
[2024-06-04 03:32:45] INFO auto_config.py:116: Found model configuration: /models/Qwen1.5-1.8B-Chat/config.json
[2024-06-04 03:32:45] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
[2024-06-04 03:32:45] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-04 03:32:45] INFO qwen2_model.py:66: prefill_chunk_size defaults to 2048
[2024-06-04 03:32:45] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-04 03:32:45] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 151643
[2024-06-04 03:32:45] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 151643
[2024-06-04 03:32:45] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [151645, 151643]
[2024-06-04 03:32:45] INFO gen_config.py:143: [generation_config.json] Setting repetition_penalty: 1.1
[2024-06-04 03:32:45] INFO gen_config.py:143: [generation_config.json] Setting top_p: 0.8
[2024-06-04 03:32:45] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen1.5-1.8B-Chat/tokenizer.model
[2024-06-04 03:32:45] INFO gen_config.py:155: Found tokenizer config: /models/Qwen1.5-1.8B-Chat/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC/tokenizer.json
[2024-06-04 03:32:45] INFO gen_config.py:155: Found tokenizer config: /models/Qwen1.5-1.8B-Chat/vocab.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC/vocab.json
[2024-06-04 03:32:45] INFO gen_config.py:155: Found tokenizer config: /models/Qwen1.5-1.8B-Chat/merges.txt. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC/merges.txt
[2024-06-04 03:32:45] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen1.5-1.8B-Chat/added_tokens.json
[2024-06-04 03:32:45] INFO gen_config.py:155: Found tokenizer config: /models/Qwen1.5-1.8B-Chat/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC/tokenizer_config.json
[2024-06-04 03:32:46] 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 03:32:46] INFO gen_config.py:32: [System default] Setting temperature: 1.0
[2024-06-04 03:32:46] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-04 03:32:46] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-04 03:32:46] INFO gen_config.py:32: [System default] Setting mean_gen_len: 128
[2024-06-04 03:32:46] INFO gen_config.py:32: [System default] Setting max_gen_len: 512
[2024-06-04 03:32:46] INFO gen_config.py:32: [System default] Setting shift_fill_factor: 0.3
[2024-06-04 03:32:46] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC/mlc-chat-config.json
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Qwen1.5-1.8B-Chat --quantization q4f32_1 --output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC
[2024-06-04 03:32:47] INFO auto_config.py:116: Found model configuration: /models/Qwen1.5-1.8B-Chat/config.json
[2024-06-04 03:32:48] INFO auto_device.py:79: Found device: cuda:0
[2024-06-04 03:32:50] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-04 03:32:51] INFO auto_device.py:88: Not found device: metal:0
[2024-06-04 03:32:53] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-04 03:32:53] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-04 03:32:53] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-04 03:32:53] INFO auto_device.py:79: Found device: vulkan:3
[2024-06-04 03:32:54] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-04 03:32:54] INFO auto_device.py:35: Using device: cuda:0
[2024-06-04 03:32:54] INFO auto_weight.py:71: Finding weights in: /models/Qwen1.5-1.8B-Chat
[2024-06-04 03:32:54] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-04 03:32:54] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /models/Qwen1.5-1.8B-Chat/model.safetensors.index.json
[2024-06-04 03:32:54] INFO auto_weight.py:107: Using source weight configuration: /models/Qwen1.5-1.8B-Chat/model.safetensors.index.json. Use `--source` to override.
[2024-06-04 03:32:54] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-04 03:32:54] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
[2024-06-04 03:32:54] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-04 03:32:54] INFO qwen2_model.py:66: prefill_chunk_size defaults to 2048
Weight conversion with arguments:
--config /models/Qwen1.5-1.8B-Chat/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 qwen2
--device cuda:0
--source /models/Qwen1.5-1.8B-Chat/model.safetensors.index.json
--source-format huggingface-safetensor
--output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC
0%| | 0/171 [00:00<?, ?it/s] [2024-06-04 03:32:56] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Qwen1.5-1.8B-Chat/model.safetensors
0%| | 0/171 [00:00<?, ?it/s] [2024-06-04 03:33:02] INFO group_quantization.py:217: Compiling quantize function for key: ((151936, 2048), float32, cuda, axis=1, output_transpose=False)
0%| | 0/171 [00:05<?, ?it/s] [2024-06-04 03:33:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_weight", shape: (151936, 256), dtype: uint32
0%| | 0/171 [00:06<?, ?it/s] [2024-06-04 03:33:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_scale", shape: (151936, 64), dtype: float32
0%| | 0/171 [00:06<?, ?it/s] 1%| | 1/171 [00:07<19:59, 7.06s/it] [2024-06-04 03:33:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (151936, 256), dtype: uint32
1%| | 1/171 [00:07<19:59, 7.06s/it] [2024-06-04 03:33:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (151936, 64), dtype: float32
1%| | 1/171 [00:08<19:59, 7.06s/it] 1%| | 2/171 [00:08<10:16, 3.65s/it] [2024-06-04 03:33:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (2048,), dtype: float32
1%| | 2/171 [00:08<10:16, 3.65s/it] [2024-06-04 03:33:04] INFO group_quantization.py:217: Compiling quantize function for key: ((2048, 5504), float32, cuda, axis=1, output_transpose=False)
1%| | 2/171 [00:08<10:16, 3.65s/it] [2024-06-04 03:33:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
1%| | 2/171 [00:08<10:16, 3.65s/it] [2024-06-04 03:33:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
1%| | 2/171 [00:08<10:16, 3.65s/it] 2%|▏ | 4/171 [00:08<04:11, 1.51s/it] [2024-06-04 03:33:05] INFO group_quantization.py:217: Compiling quantize function for key: ((11008, 2048), float32, cuda, axis=1, output_transpose=False)
2%|▏ | 4/171 [00:08<04:11, 1.51s/it] [2024-06-04 03:33:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
2%|▏ | 4/171 [00:09<04:11, 1.51s/it] [2024-06-04 03:33:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
2%|▏ | 4/171 [00:09<04:11, 1.51s/it] 3%|▎ | 5/171 [00:09<03:18, 1.20s/it] [2024-06-04 03:33:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (2048,), dtype: float32
3%|▎ | 5/171 [00:09<03:18, 1.20s/it] [2024-06-04 03:33:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.c_attn.bias", shape: (6144,), dtype: float32
3%|▎ | 5/171 [00:09<03:18, 1.20s/it] [2024-06-04 03:33:05] INFO group_quantization.py:217: Compiling quantize function for key: ((6144, 2048), float32, cuda, axis=1, output_transpose=False)
3%|▎ | 5/171 [00:09<03:18, 1.20s/it] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
3%|▎ | 5/171 [00:09<03:18, 1.20s/it] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
3%|▎ | 5/171 [00:09<03:18, 1.20s/it] 5%|▍ | 8/171 [00:09<01:37, 1.67it/s] [2024-06-04 03:33:06] INFO group_quantization.py:217: Compiling quantize function for key: ((2048, 2048), float32, cuda, axis=1, output_transpose=False)
5%|▍ | 8/171 [00:09<01:37, 1.67it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
5%|▍ | 8/171 [00:10<01:37, 1.67it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
5%|▍ | 8/171 [00:10<01:37, 1.67it/s] 5%|▌ | 9/171 [00:10<01:30, 1.79it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (2048,), dtype: float32
5%|▌ | 9/171 [00:10<01:30, 1.79it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
5%|▌ | 9/171 [00:10<01:30, 1.79it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
5%|▌ | 9/171 [00:10<01:30, 1.79it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
5%|▌ | 9/171 [00:10<01:30, 1.79it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
5%|▌ | 9/171 [00:10<01:30, 1.79it/s] 7%|▋ | 12/171 [00:10<00:49, 3.22it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (2048,), dtype: float32
7%|▋ | 12/171 [00:10<00:49, 3.22it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.c_attn.bias", shape: (6144,), dtype: float32
7%|▋ | 12/171 [00:10<00:49, 3.22it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
7%|▋ | 12/171 [00:10<00:49, 3.22it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
7%|▋ | 12/171 [00:10<00:49, 3.22it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
7%|▋ | 12/171 [00:10<00:49, 3.22it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
7%|▋ | 12/171 [00:10<00:49, 3.22it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (2048,), dtype: float32
7%|▋ | 12/171 [00:10<00:49, 3.22it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
7%|▋ | 12/171 [00:10<00:49, 3.22it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
7%|▋ | 12/171 [00:10<00:49, 3.22it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
7%|▋ | 12/171 [00:10<00:49, 3.22it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
7%|▋ | 12/171 [00:10<00:49, 3.22it/s] 11%|█ | 19/171 [00:10<00:20, 7.56it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (2048,), dtype: float32
11%|█ | 19/171 [00:10<00:20, 7.56it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.c_attn.bias", shape: (6144,), dtype: float32
11%|█ | 19/171 [00:10<00:20, 7.56it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
11%|█ | 19/171 [00:10<00:20, 7.56it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
11%|█ | 19/171 [00:10<00:20, 7.56it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
11%|█ | 19/171 [00:10<00:20, 7.56it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
11%|█ | 19/171 [00:10<00:20, 7.56it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (2048,), dtype: float32
11%|█ | 19/171 [00:10<00:20, 7.56it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
11%|█ | 19/171 [00:10<00:20, 7.56it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
11%|█ | 19/171 [00:10<00:20, 7.56it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
11%|█ | 19/171 [00:10<00:20, 7.56it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
11%|█ | 19/171 [00:10<00:20, 7.56it/s] 15%|█▌ | 26/171 [00:10<00:11, 12.51it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (2048,), dtype: float32
15%|█▌ | 26/171 [00:10<00:11, 12.51it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.c_attn.bias", shape: (6144,), dtype: float32
15%|█▌ | 26/171 [00:10<00:11, 12.51it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
15%|█▌ | 26/171 [00:10<00:11, 12.51it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
15%|█▌ | 26/171 [00:10<00:11, 12.51it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
15%|█▌ | 26/171 [00:10<00:11, 12.51it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
15%|█▌ | 26/171 [00:10<00:11, 12.51it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (2048,), dtype: float32
15%|█▌ | 26/171 [00:10<00:11, 12.51it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
15%|█▌ | 26/171 [00:10<00:11, 12.51it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
15%|█▌ | 26/171 [00:10<00:11, 12.51it/s] [2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
15%|█▌ | 26/171 [00:10<00:11, 12.51it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
15%|█▌ | 26/171 [00:10<00:11, 12.51it/s] 19%|█▉ | 33/171 [00:10<00:07, 17.91it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (2048,), dtype: float32
19%|█▉ | 33/171 [00:10<00:07, 17.91it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.c_attn.bias", shape: (6144,), dtype: float32
19%|█▉ | 33/171 [00:10<00:07, 17.91it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
19%|█▉ | 33/171 [00:10<00:07, 17.91it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
19%|█▉ | 33/171 [00:10<00:07, 17.91it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
19%|█▉ | 33/171 [00:10<00:07, 17.91it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
19%|█▉ | 33/171 [00:10<00:07, 17.91it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (2048,), dtype: float32
19%|█▉ | 33/171 [00:10<00:07, 17.91it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
19%|█▉ | 33/171 [00:10<00:07, 17.91it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
19%|█▉ | 33/171 [00:10<00:07, 17.91it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
19%|█▉ | 33/171 [00:10<00:07, 17.91it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
19%|█▉ | 33/171 [00:10<00:07, 17.91it/s] 23%|██▎ | 40/171 [00:10<00:05, 23.38it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (2048,), dtype: float32
23%|██▎ | 40/171 [00:10<00:05, 23.38it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.c_attn.bias", shape: (6144,), dtype: float32
23%|██▎ | 40/171 [00:10<00:05, 23.38it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
23%|██▎ | 40/171 [00:10<00:05, 23.38it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
23%|██▎ | 40/171 [00:10<00:05, 23.38it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
23%|██▎ | 40/171 [00:10<00:05, 23.38it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
23%|██▎ | 40/171 [00:10<00:05, 23.38it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (2048,), dtype: float32
23%|██▎ | 40/171 [00:10<00:05, 23.38it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
23%|██▎ | 40/171 [00:10<00:05, 23.38it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
23%|██▎ | 40/171 [00:10<00:05, 23.38it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
23%|██▎ | 40/171 [00:10<00:05, 23.38it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
23%|██▎ | 40/171 [00:10<00:05, 23.38it/s] 27%|██▋ | 47/171 [00:10<00:04, 28.69it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (2048,), dtype: float32
27%|██▋ | 47/171 [00:10<00:04, 28.69it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.c_attn.bias", shape: (6144,), dtype: float32
27%|██▋ | 47/171 [00:10<00:04, 28.69it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
27%|██▋ | 47/171 [00:10<00:04, 28.69it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
27%|██▋ | 47/171 [00:10<00:04, 28.69it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
27%|██▋ | 47/171 [00:10<00:04, 28.69it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
27%|██▋ | 47/171 [00:10<00:04, 28.69it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (2048,), dtype: float32
27%|██▋ | 47/171 [00:10<00:04, 28.69it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
27%|██▋ | 47/171 [00:11<00:04, 28.69it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
27%|██▋ | 47/171 [00:11<00:04, 28.69it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
27%|██▋ | 47/171 [00:11<00:04, 28.69it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
27%|██▋ | 47/171 [00:11<00:04, 28.69it/s] 32%|███▏ | 54/171 [00:11<00:03, 33.49it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (2048,), dtype: float32
32%|███▏ | 54/171 [00:11<00:03, 33.49it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.c_attn.bias", shape: (6144,), dtype: float32
32%|███▏ | 54/171 [00:11<00:03, 33.49it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
32%|███▏ | 54/171 [00:11<00:03, 33.49it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
32%|███▏ | 54/171 [00:11<00:03, 33.49it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
32%|███▏ | 54/171 [00:11<00:03, 33.49it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
32%|███▏ | 54/171 [00:11<00:03, 33.49it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (2048,), dtype: float32
32%|███▏ | 54/171 [00:11<00:03, 33.49it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
32%|███▏ | 54/171 [00:11<00:03, 33.49it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
32%|███▏ | 54/171 [00:11<00:03, 33.49it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
32%|███▏ | 54/171 [00:11<00:03, 33.49it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
32%|███▏ | 54/171 [00:11<00:03, 33.49it/s] 36%|███▌ | 61/171 [00:11<00:02, 37.56it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (2048,), dtype: float32
36%|███▌ | 61/171 [00:11<00:02, 37.56it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.c_attn.bias", shape: (6144,), dtype: float32
36%|███▌ | 61/171 [00:11<00:02, 37.56it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
36%|███▌ | 61/171 [00:11<00:02, 37.56it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
36%|███▌ | 61/171 [00:11<00:02, 37.56it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
36%|███▌ | 61/171 [00:11<00:02, 37.56it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
36%|███▌ | 61/171 [00:11<00:02, 37.56it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (2048,), dtype: float32
36%|███▌ | 61/171 [00:11<00:02, 37.56it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
36%|███▌ | 61/171 [00:11<00:02, 37.56it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
36%|███▌ | 61/171 [00:11<00:02, 37.56it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
36%|███▌ | 61/171 [00:11<00:02, 37.56it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
36%|███▌ | 61/171 [00:11<00:02, 37.56it/s] 40%|███▉ | 68/171 [00:11<00:02, 40.89it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (2048,), dtype: float32
40%|███▉ | 68/171 [00:11<00:02, 40.89it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.c_attn.bias", shape: (6144,), dtype: float32
40%|███▉ | 68/171 [00:11<00:02, 40.89it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
40%|███▉ | 68/171 [00:11<00:02, 40.89it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
40%|███▉ | 68/171 [00:11<00:02, 40.89it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
40%|███▉ | 68/171 [00:11<00:02, 40.89it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
40%|███▉ | 68/171 [00:11<00:02, 40.89it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (2048,), dtype: float32
40%|███▉ | 68/171 [00:11<00:02, 40.89it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
40%|███▉ | 68/171 [00:11<00:02, 40.89it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
40%|███▉ | 68/171 [00:11<00:02, 40.89it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
40%|███▉ | 68/171 [00:11<00:02, 40.89it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
40%|███▉ | 68/171 [00:11<00:02, 40.89it/s] 44%|████▍ | 75/171 [00:11<00:02, 43.17it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (2048,), dtype: float32
44%|████▍ | 75/171 [00:11<00:02, 43.17it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.c_attn.bias", shape: (6144,), dtype: float32
44%|████▍ | 75/171 [00:11<00:02, 43.17it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
44%|████▍ | 75/171 [00:11<00:02, 43.17it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
44%|████▍ | 75/171 [00:11<00:02, 43.17it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
44%|████▍ | 75/171 [00:11<00:02, 43.17it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
44%|████▍ | 75/171 [00:11<00:02, 43.17it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (2048,), dtype: float32
44%|████▍ | 75/171 [00:11<00:02, 43.17it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
44%|████▍ | 75/171 [00:11<00:02, 43.17it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
44%|████▍ | 75/171 [00:11<00:02, 43.17it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
44%|████▍ | 75/171 [00:11<00:02, 43.17it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
44%|████▍ | 75/171 [00:11<00:02, 43.17it/s] 48%|████▊ | 82/171 [00:11<00:01, 45.35it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (2048,), dtype: float32
48%|████▊ | 82/171 [00:11<00:01, 45.35it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.c_attn.bias", shape: (6144,), dtype: float32
48%|████▊ | 82/171 [00:11<00:01, 45.35it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
48%|████▊ | 82/171 [00:11<00:01, 45.35it/s] [2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
48%|████▊ | 82/171 [00:11<00:01, 45.35it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
48%|████▊ | 82/171 [00:11<00:01, 45.35it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
48%|████▊ | 82/171 [00:11<00:01, 45.35it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (2048,), dtype: float32
48%|████▊ | 82/171 [00:11<00:01, 45.35it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
48%|████▊ | 82/171 [00:11<00:01, 45.35it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
48%|████▊ | 82/171 [00:11<00:01, 45.35it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
48%|████▊ | 82/171 [00:11<00:01, 45.35it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
48%|████▊ | 82/171 [00:11<00:01, 45.35it/s] 52%|█████▏ | 89/171 [00:11<00:01, 46.85it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (2048,), dtype: float32
52%|█████▏ | 89/171 [00:11<00:01, 46.85it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.c_attn.bias", shape: (6144,), dtype: float32
52%|█████▏ | 89/171 [00:11<00:01, 46.85it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
52%|█████▏ | 89/171 [00:11<00:01, 46.85it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
52%|█████▏ | 89/171 [00:11<00:01, 46.85it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
52%|█████▏ | 89/171 [00:11<00:01, 46.85it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
52%|█████▏ | 89/171 [00:11<00:01, 46.85it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (2048,), dtype: float32
52%|█████▏ | 89/171 [00:11<00:01, 46.85it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
52%|█████▏ | 89/171 [00:11<00:01, 46.85it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
52%|█████▏ | 89/171 [00:11<00:01, 46.85it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
52%|█████▏ | 89/171 [00:11<00:01, 46.85it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
52%|█████▏ | 89/171 [00:11<00:01, 46.85it/s] 56%|█████▌ | 96/171 [00:11<00:01, 47.87it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (2048,), dtype: float32
56%|█████▌ | 96/171 [00:11<00:01, 47.87it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.c_attn.bias", shape: (6144,), dtype: float32
56%|█████▌ | 96/171 [00:11<00:01, 47.87it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
56%|█████▌ | 96/171 [00:11<00:01, 47.87it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
56%|█████▌ | 96/171 [00:11<00:01, 47.87it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
56%|█████▌ | 96/171 [00:11<00:01, 47.87it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
56%|█████▌ | 96/171 [00:11<00:01, 47.87it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (2048,), dtype: float32
56%|█████▌ | 96/171 [00:11<00:01, 47.87it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
56%|█████▌ | 96/171 [00:11<00:01, 47.87it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
56%|█████▌ | 96/171 [00:11<00:01, 47.87it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
56%|█████▌ | 96/171 [00:12<00:01, 47.87it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
56%|█████▌ | 96/171 [00:12<00:01, 47.87it/s] 60%|██████ | 103/171 [00:12<00:01, 48.60it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (2048,), dtype: float32
60%|██████ | 103/171 [00:12<00:01, 48.60it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.c_attn.bias", shape: (6144,), dtype: float32
60%|██████ | 103/171 [00:12<00:01, 48.60it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
60%|██████ | 103/171 [00:12<00:01, 48.60it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
60%|██████ | 103/171 [00:12<00:01, 48.60it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
60%|██████ | 103/171 [00:12<00:01, 48.60it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
60%|██████ | 103/171 [00:12<00:01, 48.60it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (2048,), dtype: float32
60%|██████ | 103/171 [00:12<00:01, 48.60it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
60%|██████ | 103/171 [00:12<00:01, 48.60it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
60%|██████ | 103/171 [00:12<00:01, 48.60it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
60%|██████ | 103/171 [00:12<00:01, 48.60it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
60%|██████ | 103/171 [00:12<00:01, 48.60it/s] 64%|██████▍ | 110/171 [00:12<00:01, 49.33it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (2048,), dtype: float32
64%|██████▍ | 110/171 [00:12<00:01, 49.33it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.c_attn.bias", shape: (6144,), dtype: float32
64%|██████▍ | 110/171 [00:12<00:01, 49.33it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
64%|██████▍ | 110/171 [00:12<00:01, 49.33it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
64%|██████▍ | 110/171 [00:12<00:01, 49.33it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
64%|██████▍ | 110/171 [00:12<00:01, 49.33it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
64%|██████▍ | 110/171 [00:12<00:01, 49.33it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (2048,), dtype: float32
64%|██████▍ | 110/171 [00:12<00:01, 49.33it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
64%|██████▍ | 110/171 [00:12<00:01, 49.33it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
64%|██████▍ | 110/171 [00:12<00:01, 49.33it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
64%|██████▍ | 110/171 [00:12<00:01, 49.33it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
64%|██████▍ | 110/171 [00:12<00:01, 49.33it/s] 68%|██████▊ | 117/171 [00:12<00:01, 49.43it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (2048,), dtype: float32
68%|██████▊ | 117/171 [00:12<00:01, 49.43it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.c_attn.bias", shape: (6144,), dtype: float32
68%|██████▊ | 117/171 [00:12<00:01, 49.43it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
68%|██████▊ | 117/171 [00:12<00:01, 49.43it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
68%|██████▊ | 117/171 [00:12<00:01, 49.43it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
68%|██████▊ | 117/171 [00:12<00:01, 49.43it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
68%|██████▊ | 117/171 [00:12<00:01, 49.43it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (2048,), dtype: float32
68%|██████▊ | 117/171 [00:12<00:01, 49.43it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
68%|██████▊ | 117/171 [00:12<00:01, 49.43it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
68%|██████▊ | 117/171 [00:12<00:01, 49.43it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
68%|██████▊ | 117/171 [00:12<00:01, 49.43it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
68%|██████▊ | 117/171 [00:12<00:01, 49.43it/s] 73%|███████▎ | 124/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (2048,), dtype: float32
73%|███████▎ | 124/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.c_attn.bias", shape: (6144,), dtype: float32
73%|███████▎ | 124/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
73%|███████▎ | 124/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
73%|███████▎ | 124/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
73%|███████▎ | 124/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
73%|███████▎ | 124/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (2048,), dtype: float32
73%|███████▎ | 124/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
73%|███████▎ | 124/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
73%|███████▎ | 124/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
73%|███████▎ | 124/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
73%|███████▎ | 124/171 [00:12<00:00, 49.83it/s] 77%|███████▋ | 131/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (2048,), dtype: float32
77%|███████▋ | 131/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.c_attn.bias", shape: (6144,), dtype: float32
77%|███████▋ | 131/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
77%|███████▋ | 131/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
77%|███████▋ | 131/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
77%|███████▋ | 131/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
77%|███████▋ | 131/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (2048,), dtype: float32
77%|███████▋ | 131/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
77%|███████▋ | 131/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
77%|███████▋ | 131/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
77%|███████▋ | 131/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
77%|███████▋ | 131/171 [00:12<00:00, 50.20it/s] 81%|████████ | 138/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (2048,), dtype: float32
81%|████████ | 138/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.c_attn.bias", shape: (6144,), dtype: float32
81%|████████ | 138/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
81%|████████ | 138/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
81%|████████ | 138/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
81%|████████ | 138/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
81%|████████ | 138/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (2048,), dtype: float32
81%|████████ | 138/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
81%|████████ | 138/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
81%|████████ | 138/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
81%|████████ | 138/171 [00:12<00:00, 50.20it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
81%|████████ | 138/171 [00:12<00:00, 50.20it/s] 85%|████████▍ | 145/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (2048,), dtype: float32
85%|████████▍ | 145/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.c_attn.bias", shape: (6144,), dtype: float32
85%|████████▍ | 145/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
85%|████████▍ | 145/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
85%|████████▍ | 145/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
85%|████████▍ | 145/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
85%|████████▍ | 145/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (2048,), dtype: float32
85%|████████▍ | 145/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
85%|████████▍ | 145/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
85%|████████▍ | 145/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
85%|████████▍ | 145/171 [00:12<00:00, 49.83it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
85%|████████▍ | 145/171 [00:13<00:00, 49.83it/s] 89%|████████▉ | 152/171 [00:13<00:00, 50.09it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (2048,), dtype: float32
89%|████████▉ | 152/171 [00:13<00:00, 50.09it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.c_attn.bias", shape: (6144,), dtype: float32
89%|████████▉ | 152/171 [00:13<00:00, 50.09it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
89%|████████▉ | 152/171 [00:13<00:00, 50.09it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
89%|████████▉ | 152/171 [00:13<00:00, 50.09it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
89%|████████▉ | 152/171 [00:13<00:00, 50.09it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
89%|████████▉ | 152/171 [00:13<00:00, 50.09it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (2048,), dtype: float32
89%|████████▉ | 152/171 [00:13<00:00, 50.09it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
89%|████████▉ | 152/171 [00:13<00:00, 50.09it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
89%|████████▉ | 152/171 [00:13<00:00, 50.09it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
89%|████████▉ | 152/171 [00:13<00:00, 50.09it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
89%|████████▉ | 152/171 [00:13<00:00, 50.09it/s] 93%|█████████▎| 159/171 [00:13<00:00, 50.22it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (2048,), dtype: float32
93%|█████████▎| 159/171 [00:13<00:00, 50.22it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.c_attn.bias", shape: (6144,), dtype: float32
93%|█████████▎| 159/171 [00:13<00:00, 50.22it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
93%|█████████▎| 159/171 [00:13<00:00, 50.22it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
93%|█████████▎| 159/171 [00:13<00:00, 50.22it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
93%|█████████▎| 159/171 [00:13<00:00, 50.22it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
93%|█████████▎| 159/171 [00:13<00:00, 50.22it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (2048,), dtype: float32
93%|█████████▎| 159/171 [00:13<00:00, 50.22it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
93%|█████████▎| 159/171 [00:13<00:00, 50.22it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float32
93%|█████████▎| 159/171 [00:13<00:00, 50.22it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
93%|█████████▎| 159/171 [00:13<00:00, 50.22it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float32
93%|█████████▎| 159/171 [00:13<00:00, 50.22it/s] 97%|█████████▋| 166/171 [00:13<00:00, 49.82it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (2048,), dtype: float32
97%|█████████▋| 166/171 [00:13<00:00, 49.82it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.c_attn.bias", shape: (6144,), dtype: float32
97%|█████████▋| 166/171 [00:13<00:00, 49.82it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
97%|█████████▋| 166/171 [00:13<00:00, 49.82it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float32
97%|█████████▋| 166/171 [00:13<00:00, 49.82it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
97%|█████████▋| 166/171 [00:13<00:00, 49.82it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32
97%|█████████▋| 166/171 [00:13<00:00, 49.82it/s] [2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (2048,), dtype: float32
97%|█████████▋| 166/171 [00:13<00:00, 49.82it/s] 100%|██████████| 171/171 [00:13<00:00, 12.80it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Qwen1.5-1.8B-Chat/model.safetensors
[2024-06-04 03:33:09] INFO stats.py:77: Time usage: HF loading: 4.409 sec; Pre-quantization mapping: 3.044 sec; Quantization: 2.600 sec
[2024-06-04 03:33:09] INFO stats.py:91: RAM usage: Peak RAM: 6.843 GB. Total bytes loaded from disk: 6.843 GB
[2024-06-04 03:33:10] INFO convert_weight.py:155: Parameter size after quantization: 1.070 GB
[2024-06-04 03:33:10] INFO convert_weight.py:160: Total parameters: 1,836,828,672
[2024-06-04 03:33:10] INFO convert_weight.py:161: Bits per parameter: 5.004
[2024-06-04 03:33:10] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC
All finished, 28 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC/ndarray-cache.json
Also saved a bf16 record to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC/ndarray-cache-b16.json