Hugging Face's logo

mlc-ai
/
Qwen1.5-0.5B-Chat-q4f16_1-MLC

MLC-LLM
web-llm
Model card Files Community
Qwen1.5-0.5B-Chat-q4f16_1-MLC / logs.txt
riczhou's picture
riczhou
Initial commit
4dd9b49 verified
raw
history blame contribute delete
82.9 kB
/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Qwen1.5-0.5B-Chat --quantization q4f16_1 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f16_1-MLC
[2024-06-04 03:31:28] INFO auto_config.py:116: Found model configuration: /models/Qwen1.5-0.5B-Chat/config.json
[2024-06-04 03:31:28] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
[2024-06-04 03:31:28] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-04 03:31:28] INFO qwen2_model.py:66: prefill_chunk_size defaults to 2048
[2024-06-04 03:31:28] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-04 03:31:28] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 151643
[2024-06-04 03:31:28] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 151643
[2024-06-04 03:31:28] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [151645, 151643]
[2024-06-04 03:31:28] INFO gen_config.py:143: [generation_config.json] Setting repetition_penalty: 1.1
[2024-06-04 03:31:28] INFO gen_config.py:143: [generation_config.json] Setting top_p: 0.8
[2024-06-04 03:31:28] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen1.5-0.5B-Chat/tokenizer.model
[2024-06-04 03:31:28] INFO gen_config.py:155: Found tokenizer config: /models/Qwen1.5-0.5B-Chat/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f16_1-MLC/tokenizer.json
[2024-06-04 03:31:28] INFO gen_config.py:155: Found tokenizer config: /models/Qwen1.5-0.5B-Chat/vocab.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f16_1-MLC/vocab.json
[2024-06-04 03:31:28] INFO gen_config.py:155: Found tokenizer config: /models/Qwen1.5-0.5B-Chat/merges.txt. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f16_1-MLC/merges.txt
[2024-06-04 03:31:28] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen1.5-0.5B-Chat/added_tokens.json
[2024-06-04 03:31:28] INFO gen_config.py:155: Found tokenizer config: /models/Qwen1.5-0.5B-Chat/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f16_1-MLC/tokenizer_config.json
[2024-06-04 03:31:28] 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 03:31:28] INFO gen_config.py:32: [System default] Setting temperature: 1.0
[2024-06-04 03:31:28] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-04 03:31:28] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-04 03:31:28] INFO gen_config.py:32: [System default] Setting mean_gen_len: 128
[2024-06-04 03:31:28] INFO gen_config.py:32: [System default] Setting max_gen_len: 512
[2024-06-04 03:31:28] INFO gen_config.py:32: [System default] Setting shift_fill_factor: 0.3
[2024-06-04 03:31:28] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f16_1-MLC/mlc-chat-config.json
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Qwen1.5-0.5B-Chat --quantization q4f16_1 --output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f16_1-MLC
[2024-06-04 03:31:30] INFO auto_config.py:116: Found model configuration: /models/Qwen1.5-0.5B-Chat/config.json
[2024-06-04 03:31:31] INFO auto_device.py:79: Found device: cuda:0
[2024-06-04 03:31:33] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-04 03:31:34] INFO auto_device.py:88: Not found device: metal:0
[2024-06-04 03:31:36] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-04 03:31:36] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-04 03:31:36] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-04 03:31:36] INFO auto_device.py:79: Found device: vulkan:3
[2024-06-04 03:31:37] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-04 03:31:37] INFO auto_device.py:35: Using device: cuda:0
[2024-06-04 03:31:37] INFO auto_weight.py:71: Finding weights in: /models/Qwen1.5-0.5B-Chat
[2024-06-04 03:31:37] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-04 03:31:37] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /models/Qwen1.5-0.5B-Chat/model.safetensors.index.json
[2024-06-04 03:31:37] INFO auto_weight.py:107: Using source weight configuration: /models/Qwen1.5-0.5B-Chat/model.safetensors.index.json. Use `--source` to override.
[2024-06-04 03:31:37] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-04 03:31:37] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
[2024-06-04 03:31:37] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-04 03:31:37] INFO qwen2_model.py:66: prefill_chunk_size defaults to 2048
Weight conversion with arguments:
--config /models/Qwen1.5-0.5B-Chat/config.json
--quantization GroupQuantize(name='q4f16_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float16', 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/Qwen1.5-0.5B-Chat/model.safetensors.index.json
--source-format huggingface-safetensor
--output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f16_1-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f16_1-MLC
0%| | 0/171 [00:00<?, ?it/s] [2024-06-04 03:31:39] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Qwen1.5-0.5B-Chat/model.safetensors
0%| | 0/171 [00:00<?, ?it/s] [2024-06-04 03:31:43] INFO group_quantization.py:217: Compiling quantize function for key: ((151936, 1024), float16, cuda, axis=1, output_transpose=False)
0%| | 0/171 [00:03<?, ?it/s] [2024-06-04 03:31:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_weight", shape: (151936, 128), dtype: uint32
0%| | 0/171 [00:04<?, ?it/s] [2024-06-04 03:31:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_scale", shape: (151936, 32), dtype: float16
0%| | 0/171 [00:04<?, ?it/s] 1%| | 1/171 [00:04<13:53, 4.90s/it] [2024-06-04 03:31:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (151936, 128), dtype: uint32
1%| | 1/171 [00:05<13:53, 4.90s/it] [2024-06-04 03:31:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (151936, 32), dtype: float16
1%| | 1/171 [00:05<13:53, 4.90s/it] 1%| | 2/171 [00:05<06:57, 2.47s/it] [2024-06-04 03:31:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (1024,), dtype: float16
1%| | 2/171 [00:05<06:57, 2.47s/it] [2024-06-04 03:31:44] INFO group_quantization.py:217: Compiling quantize function for key: ((1024, 2816), float16, cuda, axis=1, output_transpose=False)
1%| | 2/171 [00:05<06:57, 2.47s/it] [2024-06-04 03:31:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
1%| | 2/171 [00:06<06:57, 2.47s/it] [2024-06-04 03:31:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
1%| | 2/171 [00:06<06:57, 2.47s/it] 2%|▏ | 4/171 [00:06<02:59, 1.07s/it] [2024-06-04 03:31:45] INFO group_quantization.py:217: Compiling quantize function for key: ((5632, 1024), float16, cuda, axis=1, output_transpose=False)
2%|▏ | 4/171 [00:06<02:59, 1.07s/it] [2024-06-04 03:31:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
2%|▏ | 4/171 [00:06<02:59, 1.07s/it] [2024-06-04 03:31:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
2%|▏ | 4/171 [00:06<02:59, 1.07s/it] 3%|▎ | 5/171 [00:06<02:28, 1.12it/s] [2024-06-04 03:31:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (1024,), dtype: float16
3%|▎ | 5/171 [00:06<02:28, 1.12it/s] [2024-06-04 03:31:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.c_attn.bias", shape: (3072,), dtype: float16
3%|▎ | 5/171 [00:06<02:28, 1.12it/s] [2024-06-04 03:31:45] INFO group_quantization.py:217: Compiling quantize function for key: ((3072, 1024), float16, cuda, axis=1, output_transpose=False)
3%|▎ | 5/171 [00:06<02:28, 1.12it/s] [2024-06-04 03:31:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
3%|▎ | 5/171 [00:07<02:28, 1.12it/s] [2024-06-04 03:31:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
3%|▎ | 5/171 [00:07<02:28, 1.12it/s] 5%|▍ | 8/171 [00:07<01:17, 2.11it/s] [2024-06-04 03:31:46] INFO group_quantization.py:217: Compiling quantize function for key: ((1024, 1024), float16, cuda, axis=1, output_transpose=False)
5%|▍ | 8/171 [00:07<01:17, 2.11it/s] [2024-06-04 03:31:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
5%|▍ | 8/171 [00:07<01:17, 2.11it/s] [2024-06-04 03:31:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
5%|▍ | 8/171 [00:07<01:17, 2.11it/s] 5%|▌ | 9/171 [00:07<01:16, 2.11it/s] [2024-06-04 03:31:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (1024,), dtype: float16
5%|▌ | 9/171 [00:07<01:16, 2.11it/s] [2024-06-04 03:31:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
5%|▌ | 9/171 [00:07<01:16, 2.11it/s] [2024-06-04 03:31:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
5%|▌ | 9/171 [00:07<01:16, 2.11it/s] [2024-06-04 03:31:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
5%|▌ | 9/171 [00:07<01:16, 2.11it/s] [2024-06-04 03:31:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
5%|▌ | 9/171 [00:07<01:16, 2.11it/s] [2024-06-04 03:31:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (1024,), dtype: float16
5%|▌ | 9/171 [00:07<01:16, 2.11it/s] [2024-06-04 03:31:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.c_attn.bias", shape: (3072,), dtype: float16
5%|▌ | 9/171 [00:07<01:16, 2.11it/s] [2024-06-04 03:31:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
5%|▌ | 9/171 [00:07<01:16, 2.11it/s] [2024-06-04 03:31:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
5%|▌ | 9/171 [00:07<01:16, 2.11it/s] [2024-06-04 03:31:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
5%|▌ | 9/171 [00:07<01:16, 2.11it/s] [2024-06-04 03:31:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
5%|▌ | 9/171 [00:07<01:16, 2.11it/s] 9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (1024,), dtype: float16
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (1024,), dtype: float16
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.c_attn.bias", shape: (3072,), dtype: float16
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (1024,), dtype: float16
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (1024,), dtype: float16
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.c_attn.bias", shape: (3072,), dtype: float16
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
9%|▉ | 16/171 [00:07<00:25, 6.11it/s] 17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (1024,), dtype: float16
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (1024,), dtype: float16
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.c_attn.bias", shape: (3072,), dtype: float16
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (1024,), dtype: float16
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (1024,), dtype: float16
17%|█▋ | 29/171 [00:07<00:09, 15.69it/s] 24%|██▍ | 41/171 [00:07<00:04, 26.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.c_attn.bias", shape: (3072,), dtype: float16
24%|██▍ | 41/171 [00:07<00:04, 26.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
24%|██▍ | 41/171 [00:07<00:04, 26.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
24%|██▍ | 41/171 [00:07<00:04, 26.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
24%|██▍ | 41/171 [00:07<00:04, 26.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
24%|██▍ | 41/171 [00:07<00:04, 26.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (1024,), dtype: float16
24%|██▍ | 41/171 [00:07<00:04, 26.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
24%|██▍ | 41/171 [00:07<00:04, 26.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
24%|██▍ | 41/171 [00:07<00:04, 26.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
24%|██▍ | 41/171 [00:07<00:04, 26.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
24%|██▍ | 41/171 [00:08<00:04, 26.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (1024,), dtype: float16
24%|██▍ | 41/171 [00:08<00:04, 26.11it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.c_attn.bias", shape: (3072,), dtype: float16
24%|██▍ | 41/171 [00:08<00:04, 26.11it/s] 29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (1024,), dtype: float16
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (1024,), dtype: float16
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.c_attn.bias", shape: (3072,), dtype: float16
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (1024,), dtype: float16
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
29%|██▊ | 49/171 [00:08<00:03, 32.06it/s] 36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (1024,), dtype: float16
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.c_attn.bias", shape: (3072,), dtype: float16
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (1024,), dtype: float16
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (1024,), dtype: float16
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.c_attn.bias", shape: (3072,), dtype: float16
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (1024,), dtype: float16
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
36%|███▌ | 61/171 [00:08<00:02, 43.84it/s] 44%|████▍ | 75/171 [00:08<00:01, 58.43it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (1024,), dtype: float16
44%|████▍ | 75/171 [00:08<00:01, 58.43it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.c_attn.bias", shape: (3072,), dtype: float16
44%|████▍ | 75/171 [00:08<00:01, 58.43it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
44%|████▍ | 75/171 [00:08<00:01, 58.43it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
44%|████▍ | 75/171 [00:08<00:01, 58.43it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
44%|████▍ | 75/171 [00:08<00:01, 58.43it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
44%|████▍ | 75/171 [00:08<00:01, 58.43it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (1024,), dtype: float16
44%|████▍ | 75/171 [00:08<00:01, 58.43it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
44%|████▍ | 75/171 [00:08<00:01, 58.43it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
44%|████▍ | 75/171 [00:08<00:01, 58.43it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
44%|████▍ | 75/171 [00:08<00:01, 58.43it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
44%|████▍ | 75/171 [00:08<00:01, 58.43it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (1024,), dtype: float16
44%|████▍ | 75/171 [00:08<00:01, 58.43it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.c_attn.bias", shape: (3072,), dtype: float16
44%|████▍ | 75/171 [00:08<00:01, 58.43it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
44%|████▍ | 75/171 [00:08<00:01, 58.43it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
44%|████▍ | 75/171 [00:08<00:01, 58.43it/s] 50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (1024,), dtype: float16
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (1024,), dtype: float16
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.c_attn.bias", shape: (3072,), dtype: float16
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (1024,), dtype: float16
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
50%|████▉ | 85/171 [00:08<00:01, 61.64it/s] 56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (1024,), dtype: float16
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.c_attn.bias", shape: (3072,), dtype: float16
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (1024,), dtype: float16
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (1024,), dtype: float16
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.c_attn.bias", shape: (3072,), dtype: float16
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (1024,), dtype: float16
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
56%|█████▌ | 96/171 [00:08<00:01, 71.32it/s] 64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (1024,), dtype: float16
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.c_attn.bias", shape: (3072,), dtype: float16
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (1024,), dtype: float16
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (1024,), dtype: float16
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.c_attn.bias", shape: (3072,), dtype: float16
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (1024,), dtype: float16
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
64%|██████▍ | 110/171 [00:08<00:00, 73.99it/s] 73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (1024,), dtype: float16
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.c_attn.bias", shape: (3072,), dtype: float16
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (1024,), dtype: float16
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (1024,), dtype: float16
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.c_attn.bias", shape: (3072,), dtype: float16
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (1024,), dtype: float16
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
73%|███████▎ | 124/171 [00:08<00:00, 85.07it/s] 81%|████████ | 138/171 [00:08<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (1024,), dtype: float16
81%|████████ | 138/171 [00:08<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.c_attn.bias", shape: (3072,), dtype: float16
81%|████████ | 138/171 [00:08<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
81%|████████ | 138/171 [00:08<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
81%|████████ | 138/171 [00:09<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
81%|████████ | 138/171 [00:09<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
81%|████████ | 138/171 [00:09<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (1024,), dtype: float16
81%|████████ | 138/171 [00:09<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
81%|████████ | 138/171 [00:09<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
81%|████████ | 138/171 [00:09<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
81%|████████ | 138/171 [00:09<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
81%|████████ | 138/171 [00:09<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (1024,), dtype: float16
81%|████████ | 138/171 [00:09<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.c_attn.bias", shape: (3072,), dtype: float16
81%|████████ | 138/171 [00:09<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
81%|████████ | 138/171 [00:09<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
81%|████████ | 138/171 [00:09<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
81%|████████ | 138/171 [00:09<00:00, 94.74it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
81%|████████ | 138/171 [00:09<00:00, 94.74it/s] 87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (1024,), dtype: float16
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (1024,), dtype: float16
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.c_attn.bias", shape: (3072,), dtype: float16
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (1024,), dtype: float16
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (1024,), dtype: float16
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.c_attn.bias", shape: (3072,), dtype: float16
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
87%|████████▋ | 149/171 [00:09<00:00, 90.11it/s] 95%|█████████▍| 162/171 [00:09<00:00, 97.51it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
95%|█████████▍| 162/171 [00:09<00:00, 97.51it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
95%|█████████▍| 162/171 [00:09<00:00, 97.51it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (1024,), dtype: float16
95%|█████████▍| 162/171 [00:09<00:00, 97.51it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (1024, 352), dtype: uint32
95%|█████████▍| 162/171 [00:09<00:00, 97.51it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (1024, 88), dtype: float16
95%|█████████▍| 162/171 [00:09<00:00, 97.51it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (5632, 128), dtype: uint32
95%|█████████▍| 162/171 [00:09<00:00, 97.51it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (5632, 32), dtype: float16
95%|█████████▍| 162/171 [00:09<00:00, 97.51it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (1024,), dtype: float16
95%|█████████▍| 162/171 [00:09<00:00, 97.51it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.c_attn.bias", shape: (3072,), dtype: float16
95%|█████████▍| 162/171 [00:09<00:00, 97.51it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.c_attn.q_weight", shape: (3072, 128), dtype: uint32
95%|█████████▍| 162/171 [00:09<00:00, 97.51it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.c_attn.q_scale", shape: (3072, 32), dtype: float16
95%|█████████▍| 162/171 [00:09<00:00, 97.51it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (1024, 128), dtype: uint32
95%|█████████▍| 162/171 [00:09<00:00, 97.51it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (1024, 32), dtype: float16
95%|█████████▍| 162/171 [00:09<00:00, 97.51it/s] [2024-06-04 03:31:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (1024,), dtype: float16
95%|█████████▍| 162/171 [00:09<00:00, 97.51it/s] 100%|██████████| 171/171 [00:09<00:00, 18.50it/s]
[2024-06-04 03:31:48] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Qwen1.5-0.5B-Chat/model.safetensors
[2024-06-04 03:31:48] INFO stats.py:77: Time usage: HF loading: 3.360 sec; Pre-quantization mapping: 2.166 sec; Quantization: 2.748 sec
[2024-06-04 03:31:48] INFO stats.py:91: RAM usage: Peak RAM: 2.308 GB. Total bytes loaded from disk: 2.308 GB
[2024-06-04 03:31:48] INFO convert_weight.py:155: Parameter size after quantization: 0.325 GB
[2024-06-04 03:31:48] INFO convert_weight.py:160: Total parameters: 619,570,176
[2024-06-04 03:31:48] INFO convert_weight.py:161: Bits per parameter: 4.502
[2024-06-04 03:31:48] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f16_1-MLC
All finished, 8 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-0.5B-Chat-q4f16_1-MLC/ndarray-cache.json