|
/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Qwen1.5-1.8B-Chat --quantization q4f32_1 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC |
|
[2024-06-04 03:32:45] INFO auto_config.py:116: [92mFound[0m model configuration: /models/Qwen1.5-1.8B-Chat/config.json |
|
[2024-06-04 03:32:45] INFO auto_config.py:154: [92mFound[0m model type: [1mqwen2[0m. Use `--model-type` to override. |
|
[2024-06-04 03:32:45] INFO qwen2_model.py:49: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (32768) |
|
[2024-06-04 03:32:45] INFO qwen2_model.py:66: [1mprefill_chunk_size[0m defaults to 2048 |
|
[2024-06-04 03:32:45] INFO config.py:107: Overriding [1mmax_batch_size[0m from 1 to 80 |
|
[2024-06-04 03:32:45] INFO gen_config.py:143: [generation_config.json] Setting [1mbos_token_id[0m: 151643 |
|
[2024-06-04 03:32:45] INFO gen_config.py:143: [generation_config.json] Setting [1mpad_token_id[0m: 151643 |
|
[2024-06-04 03:32:45] INFO gen_config.py:143: [generation_config.json] Setting [1meos_token_id[0m: [151645, 151643] |
|
[2024-06-04 03:32:45] INFO gen_config.py:143: [generation_config.json] Setting [1mrepetition_penalty[0m: 1.1 |
|
[2024-06-04 03:32:45] INFO gen_config.py:143: [generation_config.json] Setting [1mtop_p[0m: 0.8 |
|
[2024-06-04 03:32:45] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Qwen1.5-1.8B-Chat/tokenizer.model |
|
[2024-06-04 03:32:45] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Qwen1.5-1.8B-Chat/tokenizer.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC/tokenizer.json[0m |
|
[2024-06-04 03:32:45] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Qwen1.5-1.8B-Chat/vocab.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC/vocab.json[0m |
|
[2024-06-04 03:32:45] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Qwen1.5-1.8B-Chat/merges.txt. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC/merges.txt[0m |
|
[2024-06-04 03:32:45] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Qwen1.5-1.8B-Chat/added_tokens.json |
|
[2024-06-04 03:32:45] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Qwen1.5-1.8B-Chat/tokenizer_config.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC/tokenizer_config.json[0m |
|
[2024-06-04 03:32:46] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_level', 'prepend_space_in_encode': False, 'strip_space_in_decode': False} |
|
[2024-06-04 03:32:46] INFO gen_config.py:32: [System default] Setting [1mtemperature[0m: 1.0 |
|
[2024-06-04 03:32:46] INFO gen_config.py:32: [System default] Setting [1mpresence_penalty[0m: 0.0 |
|
[2024-06-04 03:32:46] INFO gen_config.py:32: [System default] Setting [1mfrequency_penalty[0m: 0.0 |
|
[2024-06-04 03:32:46] INFO gen_config.py:32: [System default] Setting [1mmean_gen_len[0m: 128 |
|
[2024-06-04 03:32:46] INFO gen_config.py:32: [System default] Setting [1mmax_gen_len[0m: 512 |
|
[2024-06-04 03:32:46] INFO gen_config.py:32: [System default] Setting [1mshift_fill_factor[0m: 0.3 |
|
[2024-06-04 03:32:46] INFO gen_config.py:223: Dumping configuration file to: [1m/models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC/mlc-chat-config.json[0m |
|
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Qwen1.5-1.8B-Chat --quantization q4f32_1 --output /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC |
|
[2024-06-04 03:32:47] INFO auto_config.py:116: [92mFound[0m model configuration: /models/Qwen1.5-1.8B-Chat/config.json |
|
[2024-06-04 03:32:48] INFO auto_device.py:79: [92mFound[0m device: cuda:0 |
|
[2024-06-04 03:32:50] INFO auto_device.py:88: [91mNot found[0m device: rocm:0 |
|
[2024-06-04 03:32:51] INFO auto_device.py:88: [91mNot found[0m device: metal:0 |
|
[2024-06-04 03:32:53] INFO auto_device.py:79: [92mFound[0m device: vulkan:0 |
|
[2024-06-04 03:32:53] INFO auto_device.py:79: [92mFound[0m device: vulkan:1 |
|
[2024-06-04 03:32:53] INFO auto_device.py:79: [92mFound[0m device: vulkan:2 |
|
[2024-06-04 03:32:53] INFO auto_device.py:79: [92mFound[0m device: vulkan:3 |
|
[2024-06-04 03:32:54] INFO auto_device.py:88: [91mNot found[0m device: opencl:0 |
|
[2024-06-04 03:32:54] INFO auto_device.py:35: Using device: [1mcuda:0[0m |
|
[2024-06-04 03:32:54] INFO auto_weight.py:71: Finding weights in: /models/Qwen1.5-1.8B-Chat |
|
[2024-06-04 03:32:54] INFO auto_weight.py:137: [91mNot found[0m Huggingface PyTorch |
|
[2024-06-04 03:32:54] INFO auto_weight.py:144: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: /models/Qwen1.5-1.8B-Chat/model.safetensors.index.json |
|
[2024-06-04 03:32:54] INFO auto_weight.py:107: Using source weight configuration: [1m/models/Qwen1.5-1.8B-Chat/model.safetensors.index.json[0m. Use `--source` to override. |
|
[2024-06-04 03:32:54] INFO auto_weight.py:111: Using source weight format: [1mhuggingface-safetensor[0m. Use `--source-format` to override. |
|
[2024-06-04 03:32:54] INFO auto_config.py:154: [92mFound[0m model type: [1mqwen2[0m. Use `--model-type` to override. |
|
[2024-06-04 03:32:54] INFO qwen2_model.py:49: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (32768) |
|
[2024-06-04 03:32:54] INFO qwen2_model.py:66: [1mprefill_chunk_size[0m defaults to 2048 |
|
[1mWeight conversion with arguments:[0m |
|
[1m--config[0m /models/Qwen1.5-1.8B-Chat/config.json |
|
[1m--quantization[0m GroupQuantize(name='q4f32_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float32', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7) |
|
[1m--model-type[0m qwen2 |
|
[1m--device[0m cuda:0 |
|
[1m--source[0m /models/Qwen1.5-1.8B-Chat/model.safetensors.index.json |
|
[1m--source-format[0m huggingface-safetensor |
|
[1m--output[0m /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC |
|
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC |
|
0%| | 0/171 [00:00<?, ?it/s]
[2024-06-04 03:32:56] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Qwen1.5-1.8B-Chat/model.safetensors |
|
0%| | 0/171 [00:00<?, ?it/s]
[2024-06-04 03:33:02] INFO group_quantization.py:217: Compiling quantize function for key: ((151936, 2048), float32, cuda, axis=1, output_transpose=False) |
|
0%| | 0/171 [00:05<?, ?it/s]
[2024-06-04 03:33:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mlm_head.q_weight[0m", shape: (151936, 256), dtype: uint32 |
|
0%| | 0/171 [00:06<?, ?it/s]
[2024-06-04 03:33:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mlm_head.q_scale[0m", shape: (151936, 64), dtype: float32 |
|
0%| | 0/171 [00:06<?, ?it/s]
1%| | 1/171 [00:07<19:59, 7.06s/it]
[2024-06-04 03:33:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.embed_tokens.q_weight[0m", shape: (151936, 256), dtype: uint32 |
|
1%| | 1/171 [00:07<19:59, 7.06s/it]
[2024-06-04 03:33:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.embed_tokens.q_scale[0m", shape: (151936, 64), dtype: float32 |
|
1%| | 1/171 [00:08<19:59, 7.06s/it]
1%| | 2/171 [00:08<10:16, 3.65s/it]
[2024-06-04 03:33:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
1%| | 2/171 [00:08<10:16, 3.65s/it]
[2024-06-04 03:33:04] INFO group_quantization.py:217: Compiling quantize function for key: ((2048, 5504), float32, cuda, axis=1, output_transpose=False) |
|
1%| | 2/171 [00:08<10:16, 3.65s/it]
[2024-06-04 03:33:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
1%| | 2/171 [00:08<10:16, 3.65s/it]
[2024-06-04 03:33:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
1%| | 2/171 [00:08<10:16, 3.65s/it]
2%|β | 4/171 [00:08<04:11, 1.51s/it]
[2024-06-04 03:33:05] INFO group_quantization.py:217: Compiling quantize function for key: ((11008, 2048), float32, cuda, axis=1, output_transpose=False) |
|
2%|β | 4/171 [00:08<04:11, 1.51s/it]
[2024-06-04 03:33:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
2%|β | 4/171 [00:09<04:11, 1.51s/it]
[2024-06-04 03:33:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
2%|β | 4/171 [00:09<04:11, 1.51s/it]
3%|β | 5/171 [00:09<03:18, 1.20s/it]
[2024-06-04 03:33:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
3%|β | 5/171 [00:09<03:18, 1.20s/it]
[2024-06-04 03:33:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
3%|β | 5/171 [00:09<03:18, 1.20s/it]
[2024-06-04 03:33:05] INFO group_quantization.py:217: Compiling quantize function for key: ((6144, 2048), float32, cuda, axis=1, output_transpose=False) |
|
3%|β | 5/171 [00:09<03:18, 1.20s/it]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
3%|β | 5/171 [00:09<03:18, 1.20s/it]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
3%|β | 5/171 [00:09<03:18, 1.20s/it]
5%|β | 8/171 [00:09<01:37, 1.67it/s]
[2024-06-04 03:33:06] INFO group_quantization.py:217: Compiling quantize function for key: ((2048, 2048), float32, cuda, axis=1, output_transpose=False) |
|
5%|β | 8/171 [00:09<01:37, 1.67it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
5%|β | 8/171 [00:10<01:37, 1.67it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
5%|β | 8/171 [00:10<01:37, 1.67it/s]
5%|β | 9/171 [00:10<01:30, 1.79it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
5%|β | 9/171 [00:10<01:30, 1.79it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
5%|β | 9/171 [00:10<01:30, 1.79it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
5%|β | 9/171 [00:10<01:30, 1.79it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
5%|β | 9/171 [00:10<01:30, 1.79it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
5%|β | 9/171 [00:10<01:30, 1.79it/s]
7%|β | 12/171 [00:10<00:49, 3.22it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
7%|β | 12/171 [00:10<00:49, 3.22it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
7%|β | 12/171 [00:10<00:49, 3.22it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
7%|β | 12/171 [00:10<00:49, 3.22it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
7%|β | 12/171 [00:10<00:49, 3.22it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
7%|β | 12/171 [00:10<00:49, 3.22it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
7%|β | 12/171 [00:10<00:49, 3.22it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
7%|β | 12/171 [00:10<00:49, 3.22it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
7%|β | 12/171 [00:10<00:49, 3.22it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
7%|β | 12/171 [00:10<00:49, 3.22it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
7%|β | 12/171 [00:10<00:49, 3.22it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
7%|β | 12/171 [00:10<00:49, 3.22it/s]
11%|β | 19/171 [00:10<00:20, 7.56it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
11%|β | 19/171 [00:10<00:20, 7.56it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
11%|β | 19/171 [00:10<00:20, 7.56it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
11%|β | 19/171 [00:10<00:20, 7.56it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
11%|β | 19/171 [00:10<00:20, 7.56it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
11%|β | 19/171 [00:10<00:20, 7.56it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
11%|β | 19/171 [00:10<00:20, 7.56it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
11%|β | 19/171 [00:10<00:20, 7.56it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
11%|β | 19/171 [00:10<00:20, 7.56it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
11%|β | 19/171 [00:10<00:20, 7.56it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
11%|β | 19/171 [00:10<00:20, 7.56it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
11%|β | 19/171 [00:10<00:20, 7.56it/s]
15%|ββ | 26/171 [00:10<00:11, 12.51it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
15%|ββ | 26/171 [00:10<00:11, 12.51it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
15%|ββ | 26/171 [00:10<00:11, 12.51it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
15%|ββ | 26/171 [00:10<00:11, 12.51it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
15%|ββ | 26/171 [00:10<00:11, 12.51it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
15%|ββ | 26/171 [00:10<00:11, 12.51it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
15%|ββ | 26/171 [00:10<00:11, 12.51it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
15%|ββ | 26/171 [00:10<00:11, 12.51it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
15%|ββ | 26/171 [00:10<00:11, 12.51it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
15%|ββ | 26/171 [00:10<00:11, 12.51it/s]
[2024-06-04 03:33:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
15%|ββ | 26/171 [00:10<00:11, 12.51it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
15%|ββ | 26/171 [00:10<00:11, 12.51it/s]
19%|ββ | 33/171 [00:10<00:07, 17.91it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
19%|ββ | 33/171 [00:10<00:07, 17.91it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
19%|ββ | 33/171 [00:10<00:07, 17.91it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
19%|ββ | 33/171 [00:10<00:07, 17.91it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
19%|ββ | 33/171 [00:10<00:07, 17.91it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
19%|ββ | 33/171 [00:10<00:07, 17.91it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
19%|ββ | 33/171 [00:10<00:07, 17.91it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
19%|ββ | 33/171 [00:10<00:07, 17.91it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
19%|ββ | 33/171 [00:10<00:07, 17.91it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
19%|ββ | 33/171 [00:10<00:07, 17.91it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
19%|ββ | 33/171 [00:10<00:07, 17.91it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
19%|ββ | 33/171 [00:10<00:07, 17.91it/s]
23%|βββ | 40/171 [00:10<00:05, 23.38it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
23%|βββ | 40/171 [00:10<00:05, 23.38it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
23%|βββ | 40/171 [00:10<00:05, 23.38it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
23%|βββ | 40/171 [00:10<00:05, 23.38it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
23%|βββ | 40/171 [00:10<00:05, 23.38it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
23%|βββ | 40/171 [00:10<00:05, 23.38it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
23%|βββ | 40/171 [00:10<00:05, 23.38it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
23%|βββ | 40/171 [00:10<00:05, 23.38it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
23%|βββ | 40/171 [00:10<00:05, 23.38it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
23%|βββ | 40/171 [00:10<00:05, 23.38it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
23%|βββ | 40/171 [00:10<00:05, 23.38it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
23%|βββ | 40/171 [00:10<00:05, 23.38it/s]
27%|βββ | 47/171 [00:10<00:04, 28.69it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
27%|βββ | 47/171 [00:10<00:04, 28.69it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
27%|βββ | 47/171 [00:10<00:04, 28.69it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
27%|βββ | 47/171 [00:10<00:04, 28.69it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
27%|βββ | 47/171 [00:10<00:04, 28.69it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
27%|βββ | 47/171 [00:10<00:04, 28.69it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
27%|βββ | 47/171 [00:10<00:04, 28.69it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
27%|βββ | 47/171 [00:10<00:04, 28.69it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
27%|βββ | 47/171 [00:11<00:04, 28.69it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
27%|βββ | 47/171 [00:11<00:04, 28.69it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
27%|βββ | 47/171 [00:11<00:04, 28.69it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
27%|βββ | 47/171 [00:11<00:04, 28.69it/s]
32%|ββββ | 54/171 [00:11<00:03, 33.49it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
32%|ββββ | 54/171 [00:11<00:03, 33.49it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
32%|ββββ | 54/171 [00:11<00:03, 33.49it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
32%|ββββ | 54/171 [00:11<00:03, 33.49it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
32%|ββββ | 54/171 [00:11<00:03, 33.49it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
32%|ββββ | 54/171 [00:11<00:03, 33.49it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
32%|ββββ | 54/171 [00:11<00:03, 33.49it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
32%|ββββ | 54/171 [00:11<00:03, 33.49it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
32%|ββββ | 54/171 [00:11<00:03, 33.49it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
32%|ββββ | 54/171 [00:11<00:03, 33.49it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
32%|ββββ | 54/171 [00:11<00:03, 33.49it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
32%|ββββ | 54/171 [00:11<00:03, 33.49it/s]
36%|ββββ | 61/171 [00:11<00:02, 37.56it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
36%|ββββ | 61/171 [00:11<00:02, 37.56it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
36%|ββββ | 61/171 [00:11<00:02, 37.56it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
36%|ββββ | 61/171 [00:11<00:02, 37.56it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
36%|ββββ | 61/171 [00:11<00:02, 37.56it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
36%|ββββ | 61/171 [00:11<00:02, 37.56it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
36%|ββββ | 61/171 [00:11<00:02, 37.56it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
36%|ββββ | 61/171 [00:11<00:02, 37.56it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
36%|ββββ | 61/171 [00:11<00:02, 37.56it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
36%|ββββ | 61/171 [00:11<00:02, 37.56it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
36%|ββββ | 61/171 [00:11<00:02, 37.56it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
36%|ββββ | 61/171 [00:11<00:02, 37.56it/s]
40%|ββββ | 68/171 [00:11<00:02, 40.89it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
40%|ββββ | 68/171 [00:11<00:02, 40.89it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
40%|ββββ | 68/171 [00:11<00:02, 40.89it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
40%|ββββ | 68/171 [00:11<00:02, 40.89it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
40%|ββββ | 68/171 [00:11<00:02, 40.89it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
40%|ββββ | 68/171 [00:11<00:02, 40.89it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
40%|ββββ | 68/171 [00:11<00:02, 40.89it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
40%|ββββ | 68/171 [00:11<00:02, 40.89it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
40%|ββββ | 68/171 [00:11<00:02, 40.89it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
40%|ββββ | 68/171 [00:11<00:02, 40.89it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
40%|ββββ | 68/171 [00:11<00:02, 40.89it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
40%|ββββ | 68/171 [00:11<00:02, 40.89it/s]
44%|βββββ | 75/171 [00:11<00:02, 43.17it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
44%|βββββ | 75/171 [00:11<00:02, 43.17it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
44%|βββββ | 75/171 [00:11<00:02, 43.17it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
44%|βββββ | 75/171 [00:11<00:02, 43.17it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
44%|βββββ | 75/171 [00:11<00:02, 43.17it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
44%|βββββ | 75/171 [00:11<00:02, 43.17it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
44%|βββββ | 75/171 [00:11<00:02, 43.17it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
44%|βββββ | 75/171 [00:11<00:02, 43.17it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
44%|βββββ | 75/171 [00:11<00:02, 43.17it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
44%|βββββ | 75/171 [00:11<00:02, 43.17it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
44%|βββββ | 75/171 [00:11<00:02, 43.17it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
44%|βββββ | 75/171 [00:11<00:02, 43.17it/s]
48%|βββββ | 82/171 [00:11<00:01, 45.35it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
48%|βββββ | 82/171 [00:11<00:01, 45.35it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
48%|βββββ | 82/171 [00:11<00:01, 45.35it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
48%|βββββ | 82/171 [00:11<00:01, 45.35it/s]
[2024-06-04 03:33:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
48%|βββββ | 82/171 [00:11<00:01, 45.35it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
48%|βββββ | 82/171 [00:11<00:01, 45.35it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
48%|βββββ | 82/171 [00:11<00:01, 45.35it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
48%|βββββ | 82/171 [00:11<00:01, 45.35it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
48%|βββββ | 82/171 [00:11<00:01, 45.35it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
48%|βββββ | 82/171 [00:11<00:01, 45.35it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
48%|βββββ | 82/171 [00:11<00:01, 45.35it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
48%|βββββ | 82/171 [00:11<00:01, 45.35it/s]
52%|ββββββ | 89/171 [00:11<00:01, 46.85it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
52%|ββββββ | 89/171 [00:11<00:01, 46.85it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
52%|ββββββ | 89/171 [00:11<00:01, 46.85it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
52%|ββββββ | 89/171 [00:11<00:01, 46.85it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
52%|ββββββ | 89/171 [00:11<00:01, 46.85it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
52%|ββββββ | 89/171 [00:11<00:01, 46.85it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
52%|ββββββ | 89/171 [00:11<00:01, 46.85it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
52%|ββββββ | 89/171 [00:11<00:01, 46.85it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
52%|ββββββ | 89/171 [00:11<00:01, 46.85it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
52%|ββββββ | 89/171 [00:11<00:01, 46.85it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
52%|ββββββ | 89/171 [00:11<00:01, 46.85it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
52%|ββββββ | 89/171 [00:11<00:01, 46.85it/s]
56%|ββββββ | 96/171 [00:11<00:01, 47.87it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
56%|ββββββ | 96/171 [00:11<00:01, 47.87it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
56%|ββββββ | 96/171 [00:11<00:01, 47.87it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
56%|ββββββ | 96/171 [00:11<00:01, 47.87it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
56%|ββββββ | 96/171 [00:11<00:01, 47.87it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
56%|ββββββ | 96/171 [00:11<00:01, 47.87it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
56%|ββββββ | 96/171 [00:11<00:01, 47.87it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
56%|ββββββ | 96/171 [00:11<00:01, 47.87it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
56%|ββββββ | 96/171 [00:11<00:01, 47.87it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
56%|ββββββ | 96/171 [00:11<00:01, 47.87it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
56%|ββββββ | 96/171 [00:12<00:01, 47.87it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
56%|ββββββ | 96/171 [00:12<00:01, 47.87it/s]
60%|ββββββ | 103/171 [00:12<00:01, 48.60it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
60%|ββββββ | 103/171 [00:12<00:01, 48.60it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
60%|ββββββ | 103/171 [00:12<00:01, 48.60it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
60%|ββββββ | 103/171 [00:12<00:01, 48.60it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
60%|ββββββ | 103/171 [00:12<00:01, 48.60it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
60%|ββββββ | 103/171 [00:12<00:01, 48.60it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
60%|ββββββ | 103/171 [00:12<00:01, 48.60it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
60%|ββββββ | 103/171 [00:12<00:01, 48.60it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.22.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
60%|ββββββ | 103/171 [00:12<00:01, 48.60it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.22.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
60%|ββββββ | 103/171 [00:12<00:01, 48.60it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.22.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
60%|ββββββ | 103/171 [00:12<00:01, 48.60it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.22.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
60%|ββββββ | 103/171 [00:12<00:01, 48.60it/s]
64%|βββββββ | 110/171 [00:12<00:01, 49.33it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
64%|βββββββ | 110/171 [00:12<00:01, 49.33it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
64%|βββββββ | 110/171 [00:12<00:01, 49.33it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
64%|βββββββ | 110/171 [00:12<00:01, 49.33it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
64%|βββββββ | 110/171 [00:12<00:01, 49.33it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
64%|βββββββ | 110/171 [00:12<00:01, 49.33it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
64%|βββββββ | 110/171 [00:12<00:01, 49.33it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
64%|βββββββ | 110/171 [00:12<00:01, 49.33it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.23.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
64%|βββββββ | 110/171 [00:12<00:01, 49.33it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.23.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
64%|βββββββ | 110/171 [00:12<00:01, 49.33it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.23.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
64%|βββββββ | 110/171 [00:12<00:01, 49.33it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.23.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
64%|βββββββ | 110/171 [00:12<00:01, 49.33it/s]
68%|βββββββ | 117/171 [00:12<00:01, 49.43it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
68%|βββββββ | 117/171 [00:12<00:01, 49.43it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
68%|βββββββ | 117/171 [00:12<00:01, 49.43it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
68%|βββββββ | 117/171 [00:12<00:01, 49.43it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
68%|βββββββ | 117/171 [00:12<00:01, 49.43it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
68%|βββββββ | 117/171 [00:12<00:01, 49.43it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
68%|βββββββ | 117/171 [00:12<00:01, 49.43it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
68%|βββββββ | 117/171 [00:12<00:01, 49.43it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
68%|βββββββ | 117/171 [00:12<00:01, 49.43it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
68%|βββββββ | 117/171 [00:12<00:01, 49.43it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
68%|βββββββ | 117/171 [00:12<00:01, 49.43it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
68%|βββββββ | 117/171 [00:12<00:01, 49.43it/s]
73%|ββββββββ | 124/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
73%|ββββββββ | 124/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
73%|ββββββββ | 124/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
73%|ββββββββ | 124/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
73%|ββββββββ | 124/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
73%|ββββββββ | 124/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
73%|ββββββββ | 124/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
73%|ββββββββ | 124/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
73%|ββββββββ | 124/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
73%|ββββββββ | 124/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
73%|ββββββββ | 124/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
73%|ββββββββ | 124/171 [00:12<00:00, 49.83it/s]
77%|ββββββββ | 131/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
77%|ββββββββ | 131/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
77%|ββββββββ | 131/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
77%|ββββββββ | 131/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
77%|ββββββββ | 131/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
77%|ββββββββ | 131/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
77%|ββββββββ | 131/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
77%|ββββββββ | 131/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
77%|ββββββββ | 131/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
77%|ββββββββ | 131/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
77%|ββββββββ | 131/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
77%|ββββββββ | 131/171 [00:12<00:00, 50.20it/s]
81%|ββββββββ | 138/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
81%|ββββββββ | 138/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
81%|ββββββββ | 138/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
81%|ββββββββ | 138/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
81%|ββββββββ | 138/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
81%|ββββββββ | 138/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
81%|ββββββββ | 138/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
81%|ββββββββ | 138/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
81%|ββββββββ | 138/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
81%|ββββββββ | 138/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
81%|ββββββββ | 138/171 [00:12<00:00, 50.20it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
81%|ββββββββ | 138/171 [00:12<00:00, 50.20it/s]
85%|βββββββββ | 145/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
85%|βββββββββ | 145/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
85%|βββββββββ | 145/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
85%|βββββββββ | 145/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
85%|βββββββββ | 145/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
85%|βββββββββ | 145/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
85%|βββββββββ | 145/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
85%|βββββββββ | 145/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
85%|βββββββββ | 145/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
85%|βββββββββ | 145/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
85%|βββββββββ | 145/171 [00:12<00:00, 49.83it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
85%|βββββββββ | 145/171 [00:13<00:00, 49.83it/s]
89%|βββββββββ | 152/171 [00:13<00:00, 50.09it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
89%|βββββββββ | 152/171 [00:13<00:00, 50.09it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
89%|βββββββββ | 152/171 [00:13<00:00, 50.09it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
89%|βββββββββ | 152/171 [00:13<00:00, 50.09it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
89%|βββββββββ | 152/171 [00:13<00:00, 50.09it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
89%|βββββββββ | 152/171 [00:13<00:00, 50.09it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
89%|βββββββββ | 152/171 [00:13<00:00, 50.09it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
89%|βββββββββ | 152/171 [00:13<00:00, 50.09it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
89%|βββββββββ | 152/171 [00:13<00:00, 50.09it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
89%|βββββββββ | 152/171 [00:13<00:00, 50.09it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
89%|βββββββββ | 152/171 [00:13<00:00, 50.09it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
89%|βββββββββ | 152/171 [00:13<00:00, 50.09it/s]
93%|ββββββββββ| 159/171 [00:13<00:00, 50.22it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
93%|ββββββββββ| 159/171 [00:13<00:00, 50.22it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
93%|ββββββββββ| 159/171 [00:13<00:00, 50.22it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
93%|ββββββββββ| 159/171 [00:13<00:00, 50.22it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
93%|ββββββββββ| 159/171 [00:13<00:00, 50.22it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
93%|ββββββββββ| 159/171 [00:13<00:00, 50.22it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
93%|ββββββββββ| 159/171 [00:13<00:00, 50.22it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.input_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
93%|ββββββββββ| 159/171 [00:13<00:00, 50.22it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.q_weight[0m", shape: (2048, 688), dtype: uint32 |
|
93%|ββββββββββ| 159/171 [00:13<00:00, 50.22it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.q_scale[0m", shape: (2048, 172), dtype: float32 |
|
93%|ββββββββββ| 159/171 [00:13<00:00, 50.22it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.q_weight[0m", shape: (11008, 256), dtype: uint32 |
|
93%|ββββββββββ| 159/171 [00:13<00:00, 50.22it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.q_scale[0m", shape: (11008, 64), dtype: float32 |
|
93%|ββββββββββ| 159/171 [00:13<00:00, 50.22it/s]
97%|ββββββββββ| 166/171 [00:13<00:00, 49.82it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32 |
|
97%|ββββββββββ| 166/171 [00:13<00:00, 49.82it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.c_attn.bias[0m", shape: (6144,), dtype: float32 |
|
97%|ββββββββββ| 166/171 [00:13<00:00, 49.82it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.c_attn.q_weight[0m", shape: (6144, 256), dtype: uint32 |
|
97%|ββββββββββ| 166/171 [00:13<00:00, 49.82it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.c_attn.q_scale[0m", shape: (6144, 64), dtype: float32 |
|
97%|ββββββββββ| 166/171 [00:13<00:00, 49.82it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 |
|
97%|ββββββββββ| 166/171 [00:13<00:00, 49.82it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32 |
|
97%|ββββββββββ| 166/171 [00:13<00:00, 49.82it/s]
[2024-06-04 03:33:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.norm.weight[0m", shape: (2048,), dtype: float32 |
|
97%|ββββββββββ| 166/171 [00:13<00:00, 49.82it/s]
100%|ββββββββββ| 171/171 [00:13<00:00, 12.80it/s] |
|
[2024-06-04 03:33:09] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Qwen1.5-1.8B-Chat/model.safetensors |
|
[2024-06-04 03:33:09] INFO stats.py:77: [92mTime usage[0m: HF loading: 4.409 sec; Pre-quantization mapping: 3.044 sec; Quantization: 2.600 sec |
|
[2024-06-04 03:33:09] INFO stats.py:91: [92mRAM usage[0m: Peak RAM: 6.843 GB. Total bytes loaded from disk: 6.843 GB |
|
[2024-06-04 03:33:10] INFO convert_weight.py:155: [92mParameter size[0m after quantization: 1.070 GB |
|
[2024-06-04 03:33:10] INFO convert_weight.py:160: [92mTotal parameters[0m: 1,836,828,672 |
|
[2024-06-04 03:33:10] INFO convert_weight.py:161: [92mBits per parameter[0m: 5.004 |
|
[2024-06-04 03:33:10] INFO convert_weight.py:166: Saved to directory: [1m/models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC[0m |
|
|
|
All finished, 28 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC/ndarray-cache.json |
|
Also saved a bf16 record to /models/mlc-delivery/hf/mlc-ai/Qwen1.5-1.8B-Chat-q4f32_1-MLC/ndarray-cache-b16.json |
|
|