Hugging Face's logo

mlc-ai
/
Qwen1.5-1.8B-Chat-q4f16_1-MLC

MLC-LLM
web-llm
Model card Files Community
Qwen1.5-1.8B-Chat-q4f16_1-MLC / logs.txt
riczhou's picture
riczhou
Initial commit
423c362 verified
raw
history blame contribute delete
85.2 kB
/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Qwen1.5-1.8B-Chat --quantization q4f16_1 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC
[2024-06-04 03:33:26] INFO auto_config.py:116: Found model configuration: /models/Qwen1.5-1.8B-Chat/config.json
[2024-06-04 03:33:26] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
[2024-06-04 03:33:26] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-04 03:33:26] INFO qwen2_model.py:66: prefill_chunk_size defaults to 2048
[2024-06-04 03:33:26] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-04 03:33:26] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 151643
[2024-06-04 03:33:26] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 151643
[2024-06-04 03:33:26] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [151645, 151643]
[2024-06-04 03:33:26] INFO gen_config.py:143: [generation_config.json] Setting repetition_penalty: 1.1
[2024-06-04 03:33:26] INFO gen_config.py:143: [generation_config.json] Setting top_p: 0.8
[2024-06-04 03:33:26] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen1.5-1.8B-Chat/tokenizer.model
[2024-06-04 03:33:26] 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-q4f16_1-MLC/tokenizer.json
[2024-06-04 03:33:26] 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-q4f16_1-MLC/vocab.json
[2024-06-04 03:33:26] 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-q4f16_1-MLC/merges.txt
[2024-06-04 03:33:26] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen1.5-1.8B-Chat/added_tokens.json
[2024-06-04 03:33:26] 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-q4f16_1-MLC/tokenizer_config.json
[2024-06-04 03:33:26] 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 03:33:26] INFO gen_config.py:32: [System default] Setting temperature: 1.0
[2024-06-04 03:33:26] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-04 03:33:26] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-04 03:33:26] INFO gen_config.py:32: [System default] Setting mean_gen_len: 128
[2024-06-04 03:33:26] INFO gen_config.py:32: [System default] Setting max_gen_len: 512
[2024-06-04 03:33:26] INFO gen_config.py:32: [System default] Setting shift_fill_factor: 0.3
[2024-06-04 03:33:26] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC/mlc-chat-config.json
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Qwen1.5-1.8B-Chat --quantization q4f16_1 --output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC
[2024-06-04 03:33:28] INFO auto_config.py:116: Found model configuration: /models/Qwen1.5-1.8B-Chat/config.json
[2024-06-04 03:33:29] INFO auto_device.py:79: Found device: cuda:0
[2024-06-04 03:33:30] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-04 03:33:32] INFO auto_device.py:88: Not found device: metal:0
[2024-06-04 03:33:34] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-04 03:33:34] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-04 03:33:34] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-04 03:33:34] INFO auto_device.py:79: Found device: vulkan:3
[2024-06-04 03:33:35] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-04 03:33:35] INFO auto_device.py:35: Using device: cuda:0
[2024-06-04 03:33:35] INFO auto_weight.py:71: Finding weights in: /models/Qwen1.5-1.8B-Chat
[2024-06-04 03:33:35] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-04 03:33:35] 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 03:33:35] 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 03:33:35] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-04 03:33:35] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
[2024-06-04 03:33:35] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-04 03:33:35] 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='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/Qwen1.5-1.8B-Chat/model.safetensors.index.json
--source-format huggingface-safetensor
--output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC
0%| | 0/171 [00:00<?, ?it/s] [2024-06-04 03:33:37] 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 03:33:42] INFO group_quantization.py:217: Compiling quantize function for key: ((151936, 2048), float16, cuda, axis=1, output_transpose=False)
0%| | 0/171 [00:05<?, ?it/s] [2024-06-04 03:33:43] 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 03:33:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_scale", shape: (151936, 64), dtype: float16
0%| | 0/171 [00:06<?, ?it/s] 1%| | 1/171 [00:06<18:30, 6.53s/it] [2024-06-04 03:33:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (151936, 256), dtype: uint32
1%| | 1/171 [00:08<18:30, 6.53s/it] [2024-06-04 03:33:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (151936, 64), dtype: float16
1%| | 1/171 [00:08<18:30, 6.53s/it] 1%| | 2/171 [00:08<10:46, 3.83s/it] [2024-06-04 03:33:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (2048,), dtype: float16
1%| | 2/171 [00:08<10:46, 3.83s/it] [2024-06-04 03:33:45] INFO group_quantization.py:217: Compiling quantize function for key: ((2048, 5504), float16, cuda, axis=1, output_transpose=False)
1%| | 2/171 [00:08<10:46, 3.83s/it] [2024-06-04 03:33:45] 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<10:46, 3.83s/it] [2024-06-04 03:33:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
1%| | 2/171 [00:08<10:46, 3.83s/it] 2%|▏ | 4/171 [00:08<04:25, 1.59s/it] [2024-06-04 03:33:46] INFO group_quantization.py:217: Compiling quantize function for key: ((11008, 2048), float16, cuda, axis=1, output_transpose=False)
2%|▏ | 4/171 [00:09<04:25, 1.59s/it] [2024-06-04 03:33:46] 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<04:25, 1.59s/it] [2024-06-04 03:33:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
2%|▏ | 4/171 [00:09<04:25, 1.59s/it] 3%|▎ | 5/171 [00:09<03:33, 1.28s/it] [2024-06-04 03:33:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (2048,), dtype: float16
3%|▎ | 5/171 [00:09<03:33, 1.28s/it] [2024-06-04 03:33:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.c_attn.bias", shape: (6144,), dtype: float16
3%|▎ | 5/171 [00:09<03:33, 1.28s/it] [2024-06-04 03:33:46] INFO group_quantization.py:217: Compiling quantize function for key: ((6144, 2048), float16, cuda, axis=1, output_transpose=False)
3%|▎ | 5/171 [00:09<03:33, 1.28s/it] [2024-06-04 03:33:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
3%|▎ | 5/171 [00:10<03:33, 1.28s/it] [2024-06-04 03:33:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
3%|▎ | 5/171 [00:10<03:33, 1.28s/it] 5%|▍ | 8/171 [00:10<01:46, 1.54it/s] [2024-06-04 03:33:47] INFO group_quantization.py:217: Compiling quantize function for key: ((2048, 2048), float16, cuda, axis=1, output_transpose=False)
5%|▍ | 8/171 [00:10<01:46, 1.54it/s] [2024-06-04 03:33:47] 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<01:46, 1.54it/s] [2024-06-04 03:33:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
5%|▍ | 8/171 [00:10<01:46, 1.54it/s] 5%|▌ | 9/171 [00:10<01:39, 1.63it/s] [2024-06-04 03:33:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (2048,), dtype: float16
5%|▌ | 9/171 [00:10<01:39, 1.63it/s] [2024-06-04 03:33:47] 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<01:39, 1.63it/s] [2024-06-04 03:33:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
5%|▌ | 9/171 [00:10<01:39, 1.63it/s] [2024-06-04 03:33:47] 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<01:39, 1.63it/s] [2024-06-04 03:33:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
5%|▌ | 9/171 [00:10<01:39, 1.63it/s] 7%|▋ | 12/171 [00:10<00:55, 2.85it/s] [2024-06-04 03:33:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (2048,), dtype: float16
7%|▋ | 12/171 [00:10<00:55, 2.85it/s] [2024-06-04 03:33:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.c_attn.bias", shape: (6144,), dtype: float16
7%|▋ | 12/171 [00:10<00:55, 2.85it/s] [2024-06-04 03:33:47] 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<00:55, 2.85it/s] [2024-06-04 03:33:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
7%|▋ | 12/171 [00:10<00:55, 2.85it/s] [2024-06-04 03:33:47] 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<00:55, 2.85it/s] [2024-06-04 03:33:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
7%|▋ | 12/171 [00:10<00:55, 2.85it/s] [2024-06-04 03:33:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (2048,), dtype: float16
7%|▋ | 12/171 [00:10<00:55, 2.85it/s] [2024-06-04 03:33:47] 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<00:55, 2.85it/s] [2024-06-04 03:33:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
7%|▋ | 12/171 [00:10<00:55, 2.85it/s] 11%|█ | 18/171 [00:10<00:24, 6.26it/s] [2024-06-04 03:33:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
11%|█ | 18/171 [00:10<00:24, 6.26it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
11%|█ | 18/171 [00:11<00:24, 6.26it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (2048,), dtype: float16
11%|█ | 18/171 [00:11<00:24, 6.26it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.c_attn.bias", shape: (6144,), dtype: float16
11%|█ | 18/171 [00:11<00:24, 6.26it/s] 12%|█▏ | 21/171 [00:11<00:19, 7.84it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
12%|█▏ | 21/171 [00:11<00:19, 7.84it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
12%|█▏ | 21/171 [00:11<00:19, 7.84it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
12%|█▏ | 21/171 [00:11<00:19, 7.84it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
12%|█▏ | 21/171 [00:11<00:19, 7.84it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (2048,), dtype: float16
12%|█▏ | 21/171 [00:11<00:19, 7.84it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
12%|█▏ | 21/171 [00:11<00:19, 7.84it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
12%|█▏ | 21/171 [00:11<00:19, 7.84it/s] 15%|█▍ | 25/171 [00:11<00:13, 10.86it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
15%|█▍ | 25/171 [00:11<00:13, 10.86it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
15%|█▍ | 25/171 [00:11<00:13, 10.86it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (2048,), dtype: float16
15%|█▍ | 25/171 [00:11<00:13, 10.86it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.c_attn.bias", shape: (6144,), dtype: float16
15%|█▍ | 25/171 [00:11<00:13, 10.86it/s] 16%|█▋ | 28/171 [00:11<00:11, 12.43it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
16%|█▋ | 28/171 [00:11<00:11, 12.43it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
16%|█▋ | 28/171 [00:11<00:11, 12.43it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
16%|█▋ | 28/171 [00:11<00:11, 12.43it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
16%|█▋ | 28/171 [00:11<00:11, 12.43it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (2048,), dtype: float16
16%|█▋ | 28/171 [00:11<00:11, 12.43it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
16%|█▋ | 28/171 [00:11<00:11, 12.43it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
16%|█▋ | 28/171 [00:11<00:11, 12.43it/s] 19%|█▊ | 32/171 [00:11<00:08, 16.03it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
19%|█▊ | 32/171 [00:11<00:08, 16.03it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
19%|█▊ | 32/171 [00:11<00:08, 16.03it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (2048,), dtype: float16
19%|█▊ | 32/171 [00:11<00:08, 16.03it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.c_attn.bias", shape: (6144,), dtype: float16
19%|█▊ | 32/171 [00:11<00:08, 16.03it/s] 20%|██ | 35/171 [00:11<00:08, 16.95it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
20%|██ | 35/171 [00:11<00:08, 16.95it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
20%|██ | 35/171 [00:11<00:08, 16.95it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
20%|██ | 35/171 [00:11<00:08, 16.95it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
20%|██ | 35/171 [00:11<00:08, 16.95it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (2048,), dtype: float16
20%|██ | 35/171 [00:11<00:08, 16.95it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
20%|██ | 35/171 [00:11<00:08, 16.95it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
20%|██ | 35/171 [00:11<00:08, 16.95it/s] 23%|██▎ | 39/171 [00:11<00:06, 20.62it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
23%|██▎ | 39/171 [00:11<00:06, 20.62it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
23%|██▎ | 39/171 [00:11<00:06, 20.62it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (2048,), dtype: float16
23%|██▎ | 39/171 [00:11<00:06, 20.62it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.c_attn.bias", shape: (6144,), dtype: float16
23%|██▎ | 39/171 [00:11<00:06, 20.62it/s] 25%|██▍ | 42/171 [00:11<00:06, 20.46it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
25%|██▍ | 42/171 [00:11<00:06, 20.46it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
25%|██▍ | 42/171 [00:11<00:06, 20.46it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
25%|██▍ | 42/171 [00:11<00:06, 20.46it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
25%|██▍ | 42/171 [00:11<00:06, 20.46it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (2048,), dtype: float16
25%|██▍ | 42/171 [00:11<00:06, 20.46it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
25%|██▍ | 42/171 [00:11<00:06, 20.46it/s] [2024-06-04 03:33:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
25%|██▍ | 42/171 [00:11<00:06, 20.46it/s] 27%|██▋ | 46/171 [00:11<00:05, 23.87it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
27%|██▋ | 46/171 [00:12<00:05, 23.87it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
27%|██▋ | 46/171 [00:12<00:05, 23.87it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (2048,), dtype: float16
27%|██▋ | 46/171 [00:12<00:05, 23.87it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.c_attn.bias", shape: (6144,), dtype: float16
27%|██▋ | 46/171 [00:12<00:05, 23.87it/s] 29%|██▊ | 49/171 [00:12<00:05, 22.71it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
29%|██▊ | 49/171 [00:12<00:05, 22.71it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
29%|██▊ | 49/171 [00:12<00:05, 22.71it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
29%|██▊ | 49/171 [00:12<00:05, 22.71it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
29%|██▊ | 49/171 [00:12<00:05, 22.71it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (2048,), dtype: float16
29%|██▊ | 49/171 [00:12<00:05, 22.71it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
29%|██▊ | 49/171 [00:12<00:05, 22.71it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
29%|██▊ | 49/171 [00:12<00:05, 22.71it/s] 31%|███ | 53/171 [00:12<00:04, 25.82it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
31%|███ | 53/171 [00:12<00:04, 25.82it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
31%|███ | 53/171 [00:12<00:04, 25.82it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (2048,), dtype: float16
31%|███ | 53/171 [00:12<00:04, 25.82it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.c_attn.bias", shape: (6144,), dtype: float16
31%|███ | 53/171 [00:12<00:04, 25.82it/s] 33%|███▎ | 56/171 [00:12<00:04, 23.63it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
33%|███▎ | 56/171 [00:12<00:04, 23.63it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
33%|███▎ | 56/171 [00:12<00:04, 23.63it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
33%|███▎ | 56/171 [00:12<00:04, 23.63it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
33%|███▎ | 56/171 [00:12<00:04, 23.63it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (2048,), dtype: float16
33%|███▎ | 56/171 [00:12<00:04, 23.63it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
33%|███▎ | 56/171 [00:12<00:04, 23.63it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
33%|███▎ | 56/171 [00:12<00:04, 23.63it/s] 35%|███▌ | 60/171 [00:12<00:04, 26.61it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
35%|███▌ | 60/171 [00:12<00:04, 26.61it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
35%|███▌ | 60/171 [00:12<00:04, 26.61it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (2048,), dtype: float16
35%|███▌ | 60/171 [00:12<00:04, 26.61it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.c_attn.bias", shape: (6144,), dtype: float16
35%|███▌ | 60/171 [00:12<00:04, 26.61it/s] 37%|███▋ | 63/171 [00:12<00:05, 20.36it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
37%|███▋ | 63/171 [00:12<00:05, 20.36it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
37%|███▋ | 63/171 [00:12<00:05, 20.36it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
37%|███▋ | 63/171 [00:12<00:05, 20.36it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
37%|███▋ | 63/171 [00:12<00:05, 20.36it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (2048,), dtype: float16
37%|███▋ | 63/171 [00:12<00:05, 20.36it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
37%|███▋ | 63/171 [00:12<00:05, 20.36it/s] [2024-06-04 03:33:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
37%|███▋ | 63/171 [00:12<00:05, 20.36it/s] 39%|███▉ | 67/171 [00:12<00:04, 23.76it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
39%|███▉ | 67/171 [00:13<00:04, 23.76it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
39%|███▉ | 67/171 [00:13<00:04, 23.76it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (2048,), dtype: float16
39%|███▉ | 67/171 [00:13<00:04, 23.76it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.c_attn.bias", shape: (6144,), dtype: float16
39%|███▉ | 67/171 [00:13<00:04, 23.76it/s] 41%|████ | 70/171 [00:13<00:05, 19.28it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
41%|████ | 70/171 [00:13<00:05, 19.28it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
41%|████ | 70/171 [00:13<00:05, 19.28it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
41%|████ | 70/171 [00:13<00:05, 19.28it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
41%|████ | 70/171 [00:13<00:05, 19.28it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (2048,), dtype: float16
41%|████ | 70/171 [00:13<00:05, 19.28it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
41%|████ | 70/171 [00:13<00:05, 19.28it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
41%|████ | 70/171 [00:13<00:05, 19.28it/s] 43%|████▎ | 74/171 [00:13<00:04, 22.77it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
43%|████▎ | 74/171 [00:13<00:04, 22.77it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
43%|████▎ | 74/171 [00:13<00:04, 22.77it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (2048,), dtype: float16
43%|████▎ | 74/171 [00:13<00:04, 22.77it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.c_attn.bias", shape: (6144,), dtype: float16
43%|████▎ | 74/171 [00:13<00:04, 22.77it/s] 45%|████▌ | 77/171 [00:13<00:05, 17.28it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
45%|████▌ | 77/171 [00:13<00:05, 17.28it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
45%|████▌ | 77/171 [00:13<00:05, 17.28it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
45%|████▌ | 77/171 [00:13<00:05, 17.28it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
45%|████▌ | 77/171 [00:13<00:05, 17.28it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (2048,), dtype: float16
45%|████▌ | 77/171 [00:13<00:05, 17.28it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
45%|████▌ | 77/171 [00:13<00:05, 17.28it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
45%|████▌ | 77/171 [00:13<00:05, 17.28it/s] 47%|████▋ | 81/171 [00:13<00:04, 20.87it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
47%|████▋ | 81/171 [00:13<00:04, 20.87it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
47%|████▋ | 81/171 [00:13<00:04, 20.87it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (2048,), dtype: float16
47%|████▋ | 81/171 [00:13<00:04, 20.87it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.c_attn.bias", shape: (6144,), dtype: float16
47%|████▋ | 81/171 [00:13<00:04, 20.87it/s] 49%|████▉ | 84/171 [00:13<00:04, 19.15it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
49%|████▉ | 84/171 [00:13<00:04, 19.15it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
49%|████▉ | 84/171 [00:13<00:04, 19.15it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
49%|████▉ | 84/171 [00:13<00:04, 19.15it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
49%|████▉ | 84/171 [00:13<00:04, 19.15it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (2048,), dtype: float16
49%|████▉ | 84/171 [00:13<00:04, 19.15it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
49%|████▉ | 84/171 [00:13<00:04, 19.15it/s] [2024-06-04 03:33:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
49%|████▉ | 84/171 [00:13<00:04, 19.15it/s] 51%|█████▏ | 88/171 [00:13<00:03, 22.66it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
51%|█████▏ | 88/171 [00:14<00:03, 22.66it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
51%|█████▏ | 88/171 [00:14<00:03, 22.66it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (2048,), dtype: float16
51%|█████▏ | 88/171 [00:14<00:03, 22.66it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.c_attn.bias", shape: (6144,), dtype: float16
51%|█████▏ | 88/171 [00:14<00:03, 22.66it/s] 53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (2048,), dtype: float16
53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
53%|█████▎ | 91/171 [00:14<00:04, 18.32it/s] 56%|█████▌ | 95/171 [00:14<00:03, 21.87it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
56%|█████▌ | 95/171 [00:14<00:03, 21.87it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
56%|█████▌ | 95/171 [00:14<00:03, 21.87it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (2048,), dtype: float16
56%|█████▌ | 95/171 [00:14<00:03, 21.87it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.c_attn.bias", shape: (6144,), dtype: float16
56%|█████▌ | 95/171 [00:14<00:03, 21.87it/s] 57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (2048,), dtype: float16
57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
57%|█████▋ | 98/171 [00:14<00:03, 18.27it/s] 60%|█████▉ | 102/171 [00:14<00:03, 21.81it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
60%|█████▉ | 102/171 [00:14<00:03, 21.81it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
60%|█████▉ | 102/171 [00:14<00:03, 21.81it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (2048,), dtype: float16
60%|█████▉ | 102/171 [00:14<00:03, 21.81it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.c_attn.bias", shape: (6144,), dtype: float16
60%|█████▉ | 102/171 [00:14<00:03, 21.81it/s] 61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (2048,), dtype: float16
61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s] [2024-06-04 03:33:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
61%|██████▏ | 105/171 [00:14<00:03, 18.04it/s] 64%|██████▎ | 109/171 [00:14<00:02, 21.40it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
64%|██████▎ | 109/171 [00:15<00:02, 21.40it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
64%|██████▎ | 109/171 [00:15<00:02, 21.40it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (2048,), dtype: float16
64%|██████▎ | 109/171 [00:15<00:02, 21.40it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.c_attn.bias", shape: (6144,), dtype: float16
64%|██████▎ | 109/171 [00:15<00:02, 21.40it/s] 65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (2048,), dtype: float16
65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
65%|██████▌ | 112/171 [00:15<00:04, 14.47it/s] 68%|██████▊ | 116/171 [00:15<00:03, 17.96it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
68%|██████▊ | 116/171 [00:15<00:03, 17.96it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
68%|██████▊ | 116/171 [00:15<00:03, 17.96it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (2048,), dtype: float16
68%|██████▊ | 116/171 [00:15<00:03, 17.96it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.c_attn.bias", shape: (6144,), dtype: float16
68%|██████▊ | 116/171 [00:15<00:03, 17.96it/s] 70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (2048,), dtype: float16
70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s] [2024-06-04 03:33:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
70%|██████▉ | 119/171 [00:15<00:03, 15.75it/s] 72%|███████▏ | 123/171 [00:15<00:02, 19.27it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
72%|███████▏ | 123/171 [00:16<00:02, 19.27it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
72%|███████▏ | 123/171 [00:16<00:02, 19.27it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (2048,), dtype: float16
72%|███████▏ | 123/171 [00:16<00:02, 19.27it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.c_attn.bias", shape: (6144,), dtype: float16
72%|███████▏ | 123/171 [00:16<00:02, 19.27it/s] 74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (2048,), dtype: float16
74%|███████▎ | 126/171 [00:16<00:02, 15.81it/s] 75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (2048,), dtype: float16
75%|███████▌ | 129/171 [00:16<00:02, 16.67it/s] 77%|███████▋ | 132/171 [00:16<00:02, 13.41it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.c_attn.bias", shape: (6144,), dtype: float16
77%|███████▋ | 132/171 [00:16<00:02, 13.41it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
77%|███████▋ | 132/171 [00:16<00:02, 13.41it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
77%|███████▋ | 132/171 [00:16<00:02, 13.41it/s] 78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (2048,), dtype: float16
78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s] [2024-06-04 03:33:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
78%|███████▊ | 134/171 [00:16<00:02, 14.24it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
78%|███████▊ | 134/171 [00:17<00:02, 14.24it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
78%|███████▊ | 134/171 [00:17<00:02, 14.24it/s] 81%|████████ | 138/171 [00:17<00:02, 13.00it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (2048,), dtype: float16
81%|████████ | 138/171 [00:17<00:02, 13.00it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.c_attn.bias", shape: (6144,), dtype: float16
81%|████████ | 138/171 [00:17<00:02, 13.00it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
81%|████████ | 138/171 [00:17<00:02, 13.00it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
81%|████████ | 138/171 [00:17<00:02, 13.00it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
81%|████████ | 138/171 [00:17<00:02, 13.00it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
81%|████████ | 138/171 [00:17<00:02, 13.00it/s] 83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (2048,), dtype: float16
83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
83%|████████▎ | 142/171 [00:17<00:01, 16.92it/s] 85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (2048,), dtype: float16
85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.c_attn.bias", shape: (6144,), dtype: float16
85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (2048,), dtype: float16
85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
85%|████████▍ | 145/171 [00:17<00:01, 14.18it/s] 88%|████████▊ | 151/171 [00:17<00:00, 20.66it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
88%|████████▊ | 151/171 [00:17<00:00, 20.66it/s] [2024-06-04 03:33:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
88%|████████▊ | 151/171 [00:17<00:00, 20.66it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (2048,), dtype: float16
88%|████████▊ | 151/171 [00:17<00:00, 20.66it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.c_attn.bias", shape: (6144,), dtype: float16
88%|████████▊ | 151/171 [00:17<00:00, 20.66it/s] 90%|█████████ | 154/171 [00:17<00:01, 14.89it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
90%|█████████ | 154/171 [00:18<00:01, 14.89it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
90%|█████████ | 154/171 [00:18<00:01, 14.89it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
90%|█████████ | 154/171 [00:18<00:01, 14.89it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
90%|█████████ | 154/171 [00:18<00:01, 14.89it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (2048,), dtype: float16
90%|█████████ | 154/171 [00:18<00:01, 14.89it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
90%|█████████ | 154/171 [00:18<00:01, 14.89it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
90%|█████████ | 154/171 [00:18<00:01, 14.89it/s] 92%|█████████▏| 158/171 [00:18<00:00, 17.48it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
92%|█████████▏| 158/171 [00:18<00:00, 17.48it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
92%|█████████▏| 158/171 [00:18<00:00, 17.48it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (2048,), dtype: float16
92%|█████████▏| 158/171 [00:18<00:00, 17.48it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.c_attn.bias", shape: (6144,), dtype: float16
92%|█████████▏| 158/171 [00:18<00:00, 17.48it/s] 94%|█████████▍| 161/171 [00:18<00:00, 14.41it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
94%|█████████▍| 161/171 [00:18<00:00, 14.41it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
94%|█████████▍| 161/171 [00:18<00:00, 14.41it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
94%|█████████▍| 161/171 [00:18<00:00, 14.41it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
94%|█████████▍| 161/171 [00:18<00:00, 14.41it/s] 95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (2048,), dtype: float16
95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (2048, 688), dtype: uint32
95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (2048, 172), dtype: float16
95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (11008, 256), dtype: uint32
95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (11008, 64), dtype: float16
95%|█████████▌| 163/171 [00:18<00:00, 14.22it/s] 97%|█████████▋| 166/171 [00:18<00:00, 11.94it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (2048,), dtype: float16
97%|█████████▋| 166/171 [00:18<00:00, 11.94it/s] [2024-06-04 03:33:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.c_attn.bias", shape: (6144,), dtype: float16
97%|█████████▋| 166/171 [00:18<00:00, 11.94it/s] [2024-06-04 03:33:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.c_attn.q_weight", shape: (6144, 256), dtype: uint32
97%|█████████▋| 166/171 [00:19<00:00, 11.94it/s] [2024-06-04 03:33:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.c_attn.q_scale", shape: (6144, 64), dtype: float16
97%|█████████▋| 166/171 [00:19<00:00, 11.94it/s] 99%|█████████▉| 169/171 [00:19<00:00, 13.89it/s] [2024-06-04 03:33:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32
99%|█████████▉| 169/171 [00:19<00:00, 13.89it/s] [2024-06-04 03:33:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float16
99%|█████████▉| 169/171 [00:19<00:00, 13.89it/s] [2024-06-04 03:33:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (2048,), dtype: float16
99%|█████████▉| 169/171 [00:19<00:00, 13.89it/s] 100%|██████████| 171/171 [00:19<00:00, 8.96it/s]
[2024-06-04 03:33:56] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Qwen1.5-1.8B-Chat/model.safetensors
[2024-06-04 03:33:56] INFO stats.py:77: Time usage: HF loading: 4.272 sec; Pre-quantization mapping: 9.413 sec; Quantization: 2.770 sec
[2024-06-04 03:33:56] INFO stats.py:91: RAM usage: Peak RAM: 6.843 GB. Total bytes loaded from disk: 6.843 GB
[2024-06-04 03:33:56] INFO convert_weight.py:155: Parameter size after quantization: 0.963 GB
[2024-06-04 03:33:56] INFO convert_weight.py:160: Total parameters: 1,836,828,672
[2024-06-04 03:33:56] INFO convert_weight.py:161: Bits per parameter: 4.502
[2024-06-04 03:33:56] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC
All finished, 28 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f16_1-MLC/ndarray-cache.json