Hugging Face's logo

mlc-ai
/
Qwen1.5-1.8B-Chat-q0f16-MLC

MLC-LLM
web-llm
Model card Files Community
Qwen1.5-1.8B-Chat-q0f16-MLC / logs.txt
riczhou's picture
riczhou
Initial commit
c832d6f verified
raw
history blame contribute delete
58.8 kB
/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Qwen1.5-1.8B-Chat --quantization q0f16 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q0f16-MLC
[2024-06-04 03:34:12] INFO auto_config.py:116: Found model configuration: /models/Qwen1.5-1.8B-Chat/config.json
[2024-06-04 03:34:12] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
[2024-06-04 03:34:12] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-04 03:34:12] INFO qwen2_model.py:66: prefill_chunk_size defaults to 2048
[2024-06-04 03:34:12] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-04 03:34:12] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 151643
[2024-06-04 03:34:12] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 151643
[2024-06-04 03:34:12] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [151645, 151643]
[2024-06-04 03:34:12] INFO gen_config.py:143: [generation_config.json] Setting repetition_penalty: 1.1
[2024-06-04 03:34:12] INFO gen_config.py:143: [generation_config.json] Setting top_p: 0.8
[2024-06-04 03:34:12] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen1.5-1.8B-Chat/tokenizer.model
[2024-06-04 03:34:12] 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-q0f16-MLC/tokenizer.json
[2024-06-04 03:34:12] 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-q0f16-MLC/vocab.json
[2024-06-04 03:34:12] 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-q0f16-MLC/merges.txt
[2024-06-04 03:34:12] INFO gen_config.py:157: Not found tokenizer config: /models/Qwen1.5-1.8B-Chat/added_tokens.json
[2024-06-04 03:34:12] 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-q0f16-MLC/tokenizer_config.json
[2024-06-04 03:34:12] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_level', 'prepend_space_in_encode': False, 'strip_space_in_decode': False}
[2024-06-04 03:34:12] INFO gen_config.py:32: [System default] Setting temperature: 1.0
[2024-06-04 03:34:12] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-04 03:34:12] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-04 03:34:12] INFO gen_config.py:32: [System default] Setting mean_gen_len: 128
[2024-06-04 03:34:12] INFO gen_config.py:32: [System default] Setting max_gen_len: 512
[2024-06-04 03:34:12] INFO gen_config.py:32: [System default] Setting shift_fill_factor: 0.3
[2024-06-04 03:34:12] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q0f16-MLC/mlc-chat-config.json
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Qwen1.5-1.8B-Chat --quantization q0f16 --output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q0f16-MLC
[2024-06-04 03:34:14] INFO auto_config.py:116: Found model configuration: /models/Qwen1.5-1.8B-Chat/config.json
[2024-06-04 03:34:15] INFO auto_device.py:79: Found device: cuda:0
[2024-06-04 03:34:17] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-04 03:34:18] INFO auto_device.py:88: Not found device: metal:0
[2024-06-04 03:34:20] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-04 03:34:20] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-04 03:34:20] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-04 03:34:20] INFO auto_device.py:79: Found device: vulkan:3
[2024-06-04 03:34:21] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-04 03:34:21] INFO auto_device.py:35: Using device: cuda:0
[2024-06-04 03:34:21] INFO auto_weight.py:71: Finding weights in: /models/Qwen1.5-1.8B-Chat
[2024-06-04 03:34:21] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-04 03:34:21] 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 03:34:21] 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 03:34:21] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-04 03:34:21] INFO auto_config.py:154: Found model type: qwen2. Use `--model-type` to override.
[2024-06-04 03:34:21] INFO qwen2_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (32768)
[2024-06-04 03:34:21] 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 NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16')
--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-q0f16-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q0f16-MLC
0%| | 0/171 [00:00<?, ?it/s] [2024-06-04 03:34:22] 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 03:34:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "lm_head.weight", shape: (151936, 2048), dtype: float16
0%| | 0/171 [00:05<?, ?it/s] 1%| | 1/171 [00:07<20:15, 7.15s/it] [2024-06-04 03:34:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.embed_tokens.weight", shape: (151936, 2048), dtype: float16
1%| | 1/171 [00:09<20:15, 7.15s/it] 1%| | 2/171 [00:10<14:39, 5.20s/it] [2024-06-04 03:34:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (2048,), dtype: float16
1%| | 2/171 [00:10<14:39, 5.20s/it] [2024-06-04 03:34:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
1%| | 2/171 [00:11<14:39, 5.20s/it] 2%|▏ | 4/171 [00:11<05:29, 1.98s/it] [2024-06-04 03:34:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
2%|▏ | 4/171 [00:11<05:29, 1.98s/it] 3%|▎ | 5/171 [00:11<03:57, 1.43s/it] [2024-06-04 03:34:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (2048,), dtype: float16
3%|▎ | 5/171 [00:11<03:57, 1.43s/it] [2024-06-04 03:34:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.c_attn.bias", shape: (6144,), dtype: float16
3%|▎ | 5/171 [00:11<03:57, 1.43s/it] [2024-06-04 03:34:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
3%|▎ | 5/171 [00:11<03:57, 1.43s/it] 5%|▍ | 8/171 [00:11<01:44, 1.56it/s] [2024-06-04 03:34:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
5%|▍ | 8/171 [00:11<01:44, 1.56it/s] [2024-06-04 03:34:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (2048,), dtype: float16
5%|▍ | 8/171 [00:11<01:44, 1.56it/s] [2024-06-04 03:34:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
5%|▍ | 8/171 [00:11<01:44, 1.56it/s] 6%|▋ | 11/171 [00:11<00:58, 2.71it/s] [2024-06-04 03:34:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
6%|▋ | 11/171 [00:11<00:58, 2.71it/s] [2024-06-04 03:34:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (2048,), dtype: float16
6%|▋ | 11/171 [00:11<00:58, 2.71it/s] 8%|▊ | 13/171 [00:11<00:45, 3.44it/s] [2024-06-04 03:34:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.c_attn.bias", shape: (6144,), dtype: float16
8%|▊ | 13/171 [00:11<00:45, 3.44it/s] [2024-06-04 03:34:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
8%|▊ | 13/171 [00:11<00:45, 3.44it/s] 9%|▉ | 15/171 [00:11<00:34, 4.54it/s] [2024-06-04 03:34:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
9%|▉ | 15/171 [00:11<00:34, 4.54it/s] [2024-06-04 03:34:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (2048,), dtype: float16
9%|▉ | 15/171 [00:11<00:34, 4.54it/s] [2024-06-04 03:34:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
9%|▉ | 15/171 [00:11<00:34, 4.54it/s] 11%|█ | 18/171 [00:12<00:23, 6.57it/s] [2024-06-04 03:34:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
11%|█ | 18/171 [00:12<00:23, 6.57it/s] [2024-06-04 03:34:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (2048,), dtype: float16
11%|█ | 18/171 [00:12<00:23, 6.57it/s] 12%|█▏ | 20/171 [00:12<00:21, 7.11it/s] [2024-06-04 03:34:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.c_attn.bias", shape: (6144,), dtype: float16
12%|█▏ | 20/171 [00:12<00:21, 7.11it/s] [2024-06-04 03:34:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
12%|█▏ | 20/171 [00:12<00:21, 7.11it/s] 13%|█▎ | 22/171 [00:12<00:17, 8.63it/s] [2024-06-04 03:34:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
13%|█▎ | 22/171 [00:12<00:17, 8.63it/s] [2024-06-04 03:34:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (2048,), dtype: float16
13%|█▎ | 22/171 [00:12<00:17, 8.63it/s] [2024-06-04 03:34:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
13%|█▎ | 22/171 [00:12<00:17, 8.63it/s] 15%|█▍ | 25/171 [00:12<00:13, 11.19it/s] [2024-06-04 03:34:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
15%|█▍ | 25/171 [00:12<00:13, 11.19it/s] [2024-06-04 03:34:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (2048,), dtype: float16
15%|█▍ | 25/171 [00:12<00:13, 11.19it/s] 16%|█▌ | 27/171 [00:12<00:13, 10.56it/s] [2024-06-04 03:34:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.c_attn.bias", shape: (6144,), dtype: float16
16%|█▌ | 27/171 [00:12<00:13, 10.56it/s] [2024-06-04 03:34:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
16%|█▌ | 27/171 [00:12<00:13, 10.56it/s] 17%|█▋ | 29/171 [00:12<00:11, 12.06it/s] [2024-06-04 03:34:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
17%|█▋ | 29/171 [00:12<00:11, 12.06it/s] [2024-06-04 03:34:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (2048,), dtype: float16
17%|█▋ | 29/171 [00:12<00:11, 12.06it/s] [2024-06-04 03:34:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
17%|█▋ | 29/171 [00:12<00:11, 12.06it/s] 19%|█▊ | 32/171 [00:12<00:09, 14.52it/s] [2024-06-04 03:34:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
19%|█▊ | 32/171 [00:13<00:09, 14.52it/s] [2024-06-04 03:34:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (2048,), dtype: float16
19%|█▊ | 32/171 [00:13<00:09, 14.52it/s] 20%|█▉ | 34/171 [00:13<00:10, 12.58it/s] [2024-06-04 03:34:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.c_attn.bias", shape: (6144,), dtype: float16
20%|█▉ | 34/171 [00:13<00:10, 12.58it/s] [2024-06-04 03:34:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
20%|█▉ | 34/171 [00:13<00:10, 12.58it/s] 21%|██ | 36/171 [00:13<00:09, 13.89it/s] [2024-06-04 03:34:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
21%|██ | 36/171 [00:13<00:09, 13.89it/s] [2024-06-04 03:34:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (2048,), dtype: float16
21%|██ | 36/171 [00:13<00:09, 13.89it/s] [2024-06-04 03:34:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
21%|██ | 36/171 [00:13<00:09, 13.89it/s] 23%|██▎ | 39/171 [00:13<00:08, 16.13it/s] [2024-06-04 03:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
23%|██▎ | 39/171 [00:13<00:08, 16.13it/s] [2024-06-04 03:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (2048,), dtype: float16
23%|██▎ | 39/171 [00:13<00:08, 16.13it/s] 24%|██▍ | 41/171 [00:13<00:09, 13.54it/s] [2024-06-04 03:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.c_attn.bias", shape: (6144,), dtype: float16
24%|██▍ | 41/171 [00:13<00:09, 13.54it/s] [2024-06-04 03:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
24%|██▍ | 41/171 [00:13<00:09, 13.54it/s] 25%|██▌ | 43/171 [00:13<00:08, 14.73it/s] [2024-06-04 03:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
25%|██▌ | 43/171 [00:13<00:08, 14.73it/s] [2024-06-04 03:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (2048,), dtype: float16
25%|██▌ | 43/171 [00:13<00:08, 14.73it/s] [2024-06-04 03:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
25%|██▌ | 43/171 [00:13<00:08, 14.73it/s] 27%|██▋ | 46/171 [00:13<00:07, 16.83it/s] [2024-06-04 03:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
27%|██▋ | 46/171 [00:13<00:07, 16.83it/s] [2024-06-04 03:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (2048,), dtype: float16
27%|██▋ | 46/171 [00:14<00:07, 16.83it/s] 28%|██▊ | 48/171 [00:14<00:08, 14.08it/s] [2024-06-04 03:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.c_attn.bias", shape: (6144,), dtype: float16
28%|██▊ | 48/171 [00:14<00:08, 14.08it/s] [2024-06-04 03:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
28%|██▊ | 48/171 [00:14<00:08, 14.08it/s] 29%|██▉ | 50/171 [00:14<00:07, 15.24it/s] [2024-06-04 03:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
29%|██▉ | 50/171 [00:14<00:07, 15.24it/s] [2024-06-04 03:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (2048,), dtype: float16
29%|██▉ | 50/171 [00:14<00:07, 15.24it/s] [2024-06-04 03:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
29%|██▉ | 50/171 [00:14<00:07, 15.24it/s] 31%|███ | 53/171 [00:14<00:06, 17.29it/s] [2024-06-04 03:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
31%|███ | 53/171 [00:14<00:06, 17.29it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (2048,), dtype: float16
31%|███ | 53/171 [00:14<00:06, 17.29it/s] 32%|███▏ | 55/171 [00:14<00:08, 14.41it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.c_attn.bias", shape: (6144,), dtype: float16
32%|███▏ | 55/171 [00:14<00:08, 14.41it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
32%|███▏ | 55/171 [00:14<00:08, 14.41it/s] 33%|███▎ | 57/171 [00:14<00:07, 15.56it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
33%|███▎ | 57/171 [00:14<00:07, 15.56it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (2048,), dtype: float16
33%|███▎ | 57/171 [00:14<00:07, 15.56it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
33%|███▎ | 57/171 [00:14<00:07, 15.56it/s] 35%|███▌ | 60/171 [00:14<00:06, 17.64it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
35%|███▌ | 60/171 [00:14<00:06, 17.64it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (2048,), dtype: float16
35%|███▌ | 60/171 [00:14<00:06, 17.64it/s] 36%|███▋ | 62/171 [00:14<00:07, 14.59it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.c_attn.bias", shape: (6144,), dtype: float16
36%|███▋ | 62/171 [00:14<00:07, 14.59it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
36%|███▋ | 62/171 [00:14<00:07, 14.59it/s] 37%|███▋ | 64/171 [00:15<00:06, 15.72it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
37%|███▋ | 64/171 [00:15<00:06, 15.72it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (2048,), dtype: float16
37%|███▋ | 64/171 [00:15<00:06, 15.72it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
37%|███▋ | 64/171 [00:15<00:06, 15.72it/s] 39%|███▉ | 67/171 [00:15<00:05, 17.79it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
39%|███▉ | 67/171 [00:15<00:05, 17.79it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (2048,), dtype: float16
39%|███▉ | 67/171 [00:15<00:05, 17.79it/s] 40%|████ | 69/171 [00:15<00:06, 14.67it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.c_attn.bias", shape: (6144,), dtype: float16
40%|████ | 69/171 [00:15<00:06, 14.67it/s] [2024-06-04 03:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
40%|████ | 69/171 [00:15<00:06, 14.67it/s] 42%|████▏ | 71/171 [00:15<00:06, 15.80it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
42%|████▏ | 71/171 [00:15<00:06, 15.80it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (2048,), dtype: float16
42%|████▏ | 71/171 [00:15<00:06, 15.80it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
42%|████▏ | 71/171 [00:15<00:06, 15.80it/s] 43%|████▎ | 74/171 [00:15<00:05, 17.85it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
43%|████▎ | 74/171 [00:15<00:05, 17.85it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (2048,), dtype: float16
43%|████▎ | 74/171 [00:15<00:05, 17.85it/s] 44%|████▍ | 76/171 [00:15<00:06, 14.73it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.c_attn.bias", shape: (6144,), dtype: float16
44%|████▍ | 76/171 [00:15<00:06, 14.73it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
44%|████▍ | 76/171 [00:15<00:06, 14.73it/s] 46%|████▌ | 78/171 [00:15<00:05, 15.82it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
46%|████▌ | 78/171 [00:15<00:05, 15.82it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (2048,), dtype: float16
46%|████▌ | 78/171 [00:15<00:05, 15.82it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
46%|████▌ | 78/171 [00:16<00:05, 15.82it/s] 47%|████▋ | 81/171 [00:16<00:05, 17.86it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
47%|████▋ | 81/171 [00:16<00:05, 17.86it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (2048,), dtype: float16
47%|████▋ | 81/171 [00:16<00:05, 17.86it/s] 49%|████▊ | 83/171 [00:16<00:05, 14.72it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.c_attn.bias", shape: (6144,), dtype: float16
49%|████▊ | 83/171 [00:16<00:05, 14.72it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
49%|████▊ | 83/171 [00:16<00:05, 14.72it/s] 50%|████▉ | 85/171 [00:16<00:05, 15.83it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
50%|████▉ | 85/171 [00:16<00:05, 15.83it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (2048,), dtype: float16
50%|████▉ | 85/171 [00:16<00:05, 15.83it/s] [2024-06-04 03:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
50%|████▉ | 85/171 [00:16<00:05, 15.83it/s] 51%|█████▏ | 88/171 [00:16<00:04, 17.89it/s] [2024-06-04 03:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
51%|█████▏ | 88/171 [00:16<00:04, 17.89it/s] [2024-06-04 03:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (2048,), dtype: float16
51%|█████▏ | 88/171 [00:16<00:04, 17.89it/s] 53%|█████▎ | 90/171 [00:16<00:05, 14.73it/s] [2024-06-04 03:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.c_attn.bias", shape: (6144,), dtype: float16
53%|█████▎ | 90/171 [00:16<00:05, 14.73it/s] [2024-06-04 03:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
53%|█████▎ | 90/171 [00:16<00:05, 14.73it/s] 54%|█████▍ | 92/171 [00:16<00:05, 15.76it/s] [2024-06-04 03:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
54%|█████▍ | 92/171 [00:16<00:05, 15.76it/s] [2024-06-04 03:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (2048,), dtype: float16
54%|█████▍ | 92/171 [00:16<00:05, 15.76it/s] [2024-06-04 03:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
54%|█████▍ | 92/171 [00:16<00:05, 15.76it/s] 56%|█████▌ | 95/171 [00:16<00:04, 17.86it/s] [2024-06-04 03:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
56%|█████▌ | 95/171 [00:16<00:04, 17.86it/s] [2024-06-04 03:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (2048,), dtype: float16
56%|█████▌ | 95/171 [00:17<00:04, 17.86it/s] 57%|█████▋ | 97/171 [00:17<00:05, 14.78it/s] [2024-06-04 03:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.c_attn.bias", shape: (6144,), dtype: float16
57%|█████▋ | 97/171 [00:17<00:05, 14.78it/s] [2024-06-04 03:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
57%|█████▋ | 97/171 [00:17<00:05, 14.78it/s] 58%|█████▊ | 99/171 [00:17<00:04, 15.87it/s] [2024-06-04 03:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
58%|█████▊ | 99/171 [00:17<00:04, 15.87it/s] [2024-06-04 03:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (2048,), dtype: float16
58%|█████▊ | 99/171 [00:17<00:04, 15.87it/s] [2024-06-04 03:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
58%|█████▊ | 99/171 [00:17<00:04, 15.87it/s] 60%|█████▉ | 102/171 [00:17<00:03, 17.97it/s] [2024-06-04 03:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
60%|█████▉ | 102/171 [00:17<00:03, 17.97it/s] [2024-06-04 03:34:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (2048,), dtype: float16
60%|█████▉ | 102/171 [00:17<00:03, 17.97it/s] 61%|██████ | 104/171 [00:17<00:04, 14.77it/s] [2024-06-04 03:34:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.c_attn.bias", shape: (6144,), dtype: float16
61%|██████ | 104/171 [00:17<00:04, 14.77it/s] [2024-06-04 03:34:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
61%|██████ | 104/171 [00:17<00:04, 14.77it/s] 62%|██████▏ | 106/171 [00:17<00:04, 15.85it/s] [2024-06-04 03:34:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
62%|██████▏ | 106/171 [00:17<00:04, 15.85it/s] [2024-06-04 03:34:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (2048,), dtype: float16
62%|██████▏ | 106/171 [00:17<00:04, 15.85it/s] [2024-06-04 03:34:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
62%|██████▏ | 106/171 [00:17<00:04, 15.85it/s] 64%|██████▎ | 109/171 [00:17<00:03, 17.50it/s] [2024-06-04 03:34:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
64%|██████▎ | 109/171 [00:18<00:03, 17.50it/s] [2024-06-04 03:34:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (2048,), dtype: float16
64%|██████▎ | 109/171 [00:18<00:03, 17.50it/s] 65%|██████▍ | 111/171 [00:18<00:05, 11.52it/s] [2024-06-04 03:34:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.c_attn.bias", shape: (6144,), dtype: float16
65%|██████▍ | 111/171 [00:18<00:05, 11.52it/s] [2024-06-04 03:34:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
65%|██████▍ | 111/171 [00:18<00:05, 11.52it/s] 66%|██████▌ | 113/171 [00:18<00:04, 12.95it/s] [2024-06-04 03:34:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.22.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
66%|██████▌ | 113/171 [00:18<00:04, 12.95it/s] [2024-06-04 03:34:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (2048,), dtype: float16
66%|██████▌ | 113/171 [00:18<00:04, 12.95it/s] [2024-06-04 03:34:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
66%|██████▌ | 113/171 [00:18<00:04, 12.95it/s] 68%|██████▊ | 116/171 [00:18<00:03, 15.50it/s] [2024-06-04 03:34:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
68%|██████▊ | 116/171 [00:18<00:03, 15.50it/s] [2024-06-04 03:34:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (2048,), dtype: float16
68%|██████▊ | 116/171 [00:18<00:03, 15.50it/s] 69%|██████▉ | 118/171 [00:18<00:04, 11.18it/s] [2024-06-04 03:34:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.c_attn.bias", shape: (6144,), dtype: float16
69%|██████▉ | 118/171 [00:18<00:04, 11.18it/s] [2024-06-04 03:34:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
69%|██████▉ | 118/171 [00:18<00:04, 11.18it/s] 70%|███████ | 120/171 [00:18<00:04, 12.65it/s] [2024-06-04 03:34:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.23.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
70%|███████ | 120/171 [00:18<00:04, 12.65it/s] [2024-06-04 03:34:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (2048,), dtype: float16
70%|███████ | 120/171 [00:18<00:04, 12.65it/s] [2024-06-04 03:34:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
70%|███████ | 120/171 [00:18<00:04, 12.65it/s] 72%|███████▏ | 123/171 [00:18<00:03, 15.18it/s] [2024-06-04 03:34:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
72%|███████▏ | 123/171 [00:19<00:03, 15.18it/s] [2024-06-04 03:34:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (2048,), dtype: float16
72%|███████▏ | 123/171 [00:19<00:03, 15.18it/s] 73%|███████▎ | 125/171 [00:19<00:04, 11.25it/s] [2024-06-04 03:34:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.c_attn.bias", shape: (6144,), dtype: float16
73%|███████▎ | 125/171 [00:19<00:04, 11.25it/s] [2024-06-04 03:34:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
73%|███████▎ | 125/171 [00:19<00:04, 11.25it/s] 74%|███████▍ | 127/171 [00:19<00:03, 12.38it/s] [2024-06-04 03:34:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
74%|███████▍ | 127/171 [00:19<00:03, 12.38it/s] [2024-06-04 03:34:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (2048,), dtype: float16
74%|███████▍ | 127/171 [00:19<00:03, 12.38it/s] [2024-06-04 03:34:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
74%|███████▍ | 127/171 [00:19<00:03, 12.38it/s] 76%|███████▌ | 130/171 [00:19<00:02, 14.83it/s] [2024-06-04 03:34:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
76%|███████▌ | 130/171 [00:19<00:02, 14.83it/s] [2024-06-04 03:34:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (2048,), dtype: float16
76%|███████▌ | 130/171 [00:19<00:02, 14.83it/s] 77%|███████▋ | 132/171 [00:19<00:04, 9.01it/s] [2024-06-04 03:34:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.c_attn.bias", shape: (6144,), dtype: float16
77%|███████▋ | 132/171 [00:19<00:04, 9.01it/s] [2024-06-04 03:34:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
77%|███████▋ | 132/171 [00:19<00:04, 9.01it/s] 78%|███████▊ | 134/171 [00:20<00:03, 10.52it/s] [2024-06-04 03:34:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
78%|███████▊ | 134/171 [00:20<00:03, 10.52it/s] [2024-06-04 03:34:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (2048,), dtype: float16
78%|███████▊ | 134/171 [00:20<00:03, 10.52it/s] [2024-06-04 03:34:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
78%|███████▊ | 134/171 [00:20<00:03, 10.52it/s] 80%|████████ | 137/171 [00:20<00:02, 13.07it/s] [2024-06-04 03:34:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
80%|████████ | 137/171 [00:20<00:02, 13.07it/s] [2024-06-04 03:34:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (2048,), dtype: float16
80%|████████ | 137/171 [00:20<00:02, 13.07it/s] 81%|████████▏ | 139/171 [00:20<00:03, 10.27it/s] [2024-06-04 03:34:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.c_attn.bias", shape: (6144,), dtype: float16
81%|████████▏ | 139/171 [00:20<00:03, 10.27it/s] [2024-06-04 03:34:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
81%|████████▏ | 139/171 [00:20<00:03, 10.27it/s] 82%|████████▏ | 141/171 [00:20<00:02, 11.76it/s] [2024-06-04 03:34:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
82%|████████▏ | 141/171 [00:20<00:02, 11.76it/s] [2024-06-04 03:34:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (2048,), dtype: float16
82%|████████▏ | 141/171 [00:20<00:02, 11.76it/s] [2024-06-04 03:34:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
82%|████████▏ | 141/171 [00:20<00:02, 11.76it/s] 84%|████████▍ | 144/171 [00:20<00:01, 14.27it/s] [2024-06-04 03:34:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
84%|████████▍ | 144/171 [00:20<00:01, 14.27it/s] [2024-06-04 03:34:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (2048,), dtype: float16
84%|████████▍ | 144/171 [00:20<00:01, 14.27it/s] 85%|████████▌ | 146/171 [00:20<00:02, 11.77it/s] [2024-06-04 03:34:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.c_attn.bias", shape: (6144,), dtype: float16
85%|████████▌ | 146/171 [00:20<00:02, 11.77it/s] [2024-06-04 03:34:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
85%|████████▌ | 146/171 [00:21<00:02, 11.77it/s] 87%|████████▋ | 148/171 [00:21<00:01, 13.04it/s] [2024-06-04 03:34:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
87%|████████▋ | 148/171 [00:21<00:01, 13.04it/s] [2024-06-04 03:34:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (2048,), dtype: float16
87%|████████▋ | 148/171 [00:21<00:01, 13.04it/s] [2024-06-04 03:34:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
87%|████████▋ | 148/171 [00:21<00:01, 13.04it/s] 88%|████████▊ | 151/171 [00:21<00:01, 15.45it/s] [2024-06-04 03:34:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
88%|████████▊ | 151/171 [00:21<00:01, 15.45it/s] [2024-06-04 03:34:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (2048,), dtype: float16
88%|████████▊ | 151/171 [00:21<00:01, 15.45it/s] 89%|████████▉ | 153/171 [00:21<00:01, 11.67it/s] [2024-06-04 03:34:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.c_attn.bias", shape: (6144,), dtype: float16
89%|████████▉ | 153/171 [00:21<00:01, 11.67it/s] [2024-06-04 03:34:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
89%|████████▉ | 153/171 [00:21<00:01, 11.67it/s] 91%|█████████ | 155/171 [00:21<00:01, 13.12it/s] [2024-06-04 03:34:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
91%|█████████ | 155/171 [00:21<00:01, 13.12it/s] [2024-06-04 03:34:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (2048,), dtype: float16
91%|█████████ | 155/171 [00:21<00:01, 13.12it/s] [2024-06-04 03:34:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
91%|█████████ | 155/171 [00:21<00:01, 13.12it/s] 92%|█████████▏| 158/171 [00:21<00:00, 15.60it/s] [2024-06-04 03:34:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
92%|█████████▏| 158/171 [00:21<00:00, 15.60it/s] [2024-06-04 03:34:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (2048,), dtype: float16
92%|█████████▏| 158/171 [00:22<00:00, 15.60it/s] 94%|█████████▎| 160/171 [00:22<00:01, 10.41it/s] [2024-06-04 03:34:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.c_attn.bias", shape: (6144,), dtype: float16
94%|█████████▎| 160/171 [00:22<00:01, 10.41it/s] [2024-06-04 03:34:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
94%|█████████▎| 160/171 [00:22<00:01, 10.41it/s] 95%|█████████▍| 162/171 [00:22<00:00, 11.89it/s] [2024-06-04 03:34:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
95%|█████████▍| 162/171 [00:22<00:00, 11.89it/s] [2024-06-04 03:34:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (2048,), dtype: float16
95%|█████████▍| 162/171 [00:22<00:00, 11.89it/s] [2024-06-04 03:34:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.mlp.down_proj.weight", shape: (2048, 5504), dtype: float16
95%|█████████▍| 162/171 [00:22<00:00, 11.89it/s] 96%|█████████▋| 165/171 [00:22<00:00, 14.35it/s] [2024-06-04 03:34:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.mlp.gate_up_proj.weight", shape: (11008, 2048), dtype: float16
96%|█████████▋| 165/171 [00:22<00:00, 14.35it/s] [2024-06-04 03:34:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (2048,), dtype: float16
96%|█████████▋| 165/171 [00:22<00:00, 14.35it/s] 98%|█████████▊| 167/171 [00:22<00:00, 9.14it/s] [2024-06-04 03:34:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.c_attn.bias", shape: (6144,), dtype: float16
98%|█████████▊| 167/171 [00:22<00:00, 9.14it/s] [2024-06-04 03:34:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.c_attn.weight", shape: (6144, 2048), dtype: float16
98%|█████████▊| 167/171 [00:22<00:00, 9.14it/s] 99%|█████████▉| 169/171 [00:22<00:00, 10.65it/s] [2024-06-04 03:34:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.self_attn.o_proj.weight", shape: (2048, 2048), dtype: float16
99%|█████████▉| 169/171 [00:22<00:00, 10.65it/s] [2024-06-04 03:34:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (2048,), dtype: float16
99%|█████████▉| 169/171 [00:22<00:00, 10.65it/s] 100%|██████████| 171/171 [00:22<00:00, 7.44it/s]
[2024-06-04 03:34:45] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Qwen1.5-1.8B-Chat/model.safetensors
[2024-06-04 03:34:45] INFO stats.py:77: Time usage: HF loading: 4.456 sec; Pre-quantization mapping: 8.772 sec; Quantization: 0.000 sec
[2024-06-04 03:34:45] INFO stats.py:91: RAM usage: Peak RAM: 6.843 GB. Total bytes loaded from disk: 6.843 GB
[2024-06-04 03:34:45] INFO convert_weight.py:155: Parameter size after quantization: 3.421 GB
[2024-06-04 03:34:45] INFO convert_weight.py:160: Total parameters: 1,836,828,672
[2024-06-04 03:34:45] INFO convert_weight.py:161: Bits per parameter: 16.000
[2024-06-04 03:34:45] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q0f16-MLC
All finished, 75 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q0f16-MLC/ndarray-cache.json