|
/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Meta-Llama-3-8B-Instruct --quantization q4f32_1 --conv-template llama-3 --output /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC |
|
[2024-06-04 03:10:23] INFO auto_config.py:116: [92mFound[0m model configuration: /models/Meta-Llama-3-8B-Instruct/config.json |
|
[2024-06-04 03:10:23] INFO auto_config.py:154: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override. |
|
[2024-06-04 03:10:23] INFO llama_model.py:52: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (8192) |
|
[2024-06-04 03:10:23] INFO llama_model.py:72: [1mprefill_chunk_size[0m defaults to 2048 |
|
[2024-06-04 03:10:23] INFO config.py:107: Overriding [1mmax_batch_size[0m from 1 to 80 |
|
[2024-06-04 03:10:23] INFO gen_config.py:143: [generation_config.json] Setting [1mbos_token_id[0m: 128000 |
|
[2024-06-04 03:10:23] INFO gen_config.py:143: [generation_config.json] Setting [1meos_token_id[0m: [128001, 128009] |
|
[2024-06-04 03:10:23] INFO gen_config.py:143: [generation_config.json] Setting [1mtemperature[0m: 0.6 |
|
[2024-06-04 03:10:23] INFO gen_config.py:143: [generation_config.json] Setting [1mtop_p[0m: 0.9 |
|
[2024-06-04 03:10:23] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Meta-Llama-3-8B-Instruct/tokenizer.model |
|
[2024-06-04 03:10:23] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Meta-Llama-3-8B-Instruct/tokenizer.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC/tokenizer.json[0m |
|
[2024-06-04 03:10:23] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Meta-Llama-3-8B-Instruct/vocab.json |
|
[2024-06-04 03:10:23] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Meta-Llama-3-8B-Instruct/merges.txt |
|
[2024-06-04 03:10:23] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Meta-Llama-3-8B-Instruct/added_tokens.json |
|
[2024-06-04 03:10:23] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Meta-Llama-3-8B-Instruct/tokenizer_config.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC/tokenizer_config.json[0m |
|
[2024-06-04 03:10:23] 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 03:10:23] INFO gen_config.py:32: [System default] Setting [1mpad_token_id[0m: 0 |
|
[2024-06-04 03:10:23] INFO gen_config.py:32: [System default] Setting [1mpresence_penalty[0m: 0.0 |
|
[2024-06-04 03:10:23] INFO gen_config.py:32: [System default] Setting [1mfrequency_penalty[0m: 0.0 |
|
[2024-06-04 03:10:23] INFO gen_config.py:32: [System default] Setting [1mrepetition_penalty[0m: 1.0 |
|
[2024-06-04 03:10:23] INFO gen_config.py:32: [System default] Setting [1mmean_gen_len[0m: 128 |
|
[2024-06-04 03:10:23] INFO gen_config.py:32: [System default] Setting [1mmax_gen_len[0m: 512 |
|
[2024-06-04 03:10:23] INFO gen_config.py:32: [System default] Setting [1mshift_fill_factor[0m: 0.3 |
|
[2024-06-04 03:10:23] INFO gen_config.py:223: Dumping configuration file to: [1m/models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC/mlc-chat-config.json[0m |
|
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Meta-Llama-3-8B-Instruct --quantization q4f32_1 --output /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC |
|
[2024-06-04 03:10:24] INFO auto_config.py:116: [92mFound[0m model configuration: /models/Meta-Llama-3-8B-Instruct/config.json |
|
[2024-06-04 03:10:26] INFO auto_device.py:79: [92mFound[0m device: cuda:0 |
|
[2024-06-04 03:10:27] INFO auto_device.py:88: [91mNot found[0m device: rocm:0 |
|
[2024-06-04 03:10:29] INFO auto_device.py:88: [91mNot found[0m device: metal:0 |
|
[2024-06-04 03:10:30] INFO auto_device.py:79: [92mFound[0m device: vulkan:0 |
|
[2024-06-04 03:10:30] INFO auto_device.py:79: [92mFound[0m device: vulkan:1 |
|
[2024-06-04 03:10:30] INFO auto_device.py:79: [92mFound[0m device: vulkan:2 |
|
[2024-06-04 03:10:30] INFO auto_device.py:79: [92mFound[0m device: vulkan:3 |
|
[2024-06-04 03:10:32] INFO auto_device.py:88: [91mNot found[0m device: opencl:0 |
|
[2024-06-04 03:10:32] INFO auto_device.py:35: Using device: [1mcuda:0[0m |
|
[2024-06-04 03:10:32] INFO auto_weight.py:71: Finding weights in: /models/Meta-Llama-3-8B-Instruct |
|
[2024-06-04 03:10:32] INFO auto_weight.py:137: [91mNot found[0m Huggingface PyTorch |
|
[2024-06-04 03:10:32] INFO auto_weight.py:144: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: /models/Meta-Llama-3-8B-Instruct/model.safetensors.index.json |
|
[2024-06-04 03:10:32] INFO auto_weight.py:107: Using source weight configuration: [1m/models/Meta-Llama-3-8B-Instruct/model.safetensors.index.json[0m. Use `--source` to override. |
|
[2024-06-04 03:10:32] INFO auto_weight.py:111: Using source weight format: [1mhuggingface-safetensor[0m. Use `--source-format` to override. |
|
[2024-06-04 03:10:32] INFO auto_config.py:154: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override. |
|
[2024-06-04 03:10:32] INFO llama_model.py:52: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (8192) |
|
[2024-06-04 03:10:32] INFO llama_model.py:72: [1mprefill_chunk_size[0m defaults to 2048 |
|
[1mWeight conversion with arguments:[0m |
|
[1m--config[0m /models/Meta-Llama-3-8B-Instruct/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 llama |
|
[1m--device[0m cuda:0 |
|
[1m--source[0m /models/Meta-Llama-3-8B-Instruct/model.safetensors.index.json |
|
[1m--source-format[0m huggingface-safetensor |
|
[1m--output[0m /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC |
|
Start storing to cache /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC |
|
0%| | 0/195 [00:00<?, ?it/s]
[2024-06-04 03:10:36] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Meta-Llama-3-8B-Instruct/model-00004-of-00004.safetensors |
|
0%| | 0/195 [00:00<?, ?it/s]
[2024-06-04 03:10:39] INFO group_quantization.py:217: Compiling quantize function for key: ((128256, 4096), float32, cuda, axis=1, output_transpose=False) |
|
0%| | 0/195 [00:02<?, ?it/s]
[2024-06-04 03:10:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mlm_head.q_weight[0m", shape: (128256, 512), dtype: uint32 |
|
0%| | 0/195 [00:03<?, ?it/s]
[2024-06-04 03:10:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mlm_head.q_scale[0m", shape: (128256, 128), dtype: float32 |
|
0%| | 0/195 [00:04<?, ?it/s]
1%| | 1/195 [00:04<15:45, 4.87s/it]
[2024-06-04 03:10:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.31.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
1%| | 1/195 [00:04<15:45, 4.87s/it]
[2024-06-04 03:10:41] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 14336), float32, cuda, axis=1, output_transpose=False) |
|
1%| | 1/195 [00:04<15:45, 4.87s/it]
[2024-06-04 03:10:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.31.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
1%| | 1/195 [00:05<15:45, 4.87s/it]
[2024-06-04 03:10:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.31.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
1%| | 1/195 [00:05<15:45, 4.87s/it]
2%|β | 3/195 [00:05<04:49, 1.51s/it]
[2024-06-04 03:10:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.31.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
2%|β | 3/195 [00:05<04:49, 1.51s/it]
[2024-06-04 03:10:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.norm.weight[0m", shape: (4096,), dtype: float32 |
|
2%|β | 3/195 [00:05<04:49, 1.51s/it]
[2024-06-04 03:10:41] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Meta-Llama-3-8B-Instruct/model-00004-of-00004.safetensors |
|
2%|β | 3/195 [00:05<04:49, 1.51s/it]
[2024-06-04 03:10:41] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Meta-Llama-3-8B-Instruct/model-00001-of-00004.safetensors |
|
2%|β | 3/195 [00:05<04:49, 1.51s/it]
[2024-06-04 03:10:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.embed_tokens.q_weight[0m", shape: (128256, 512), dtype: uint32 |
|
2%|β | 3/195 [00:10<04:49, 1.51s/it]
[2024-06-04 03:10:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.embed_tokens.q_scale[0m", shape: (128256, 128), dtype: float32 |
|
2%|β | 3/195 [00:11<04:49, 1.51s/it]
3%|β | 6/195 [00:11<05:41, 1.81s/it]
[2024-06-04 03:10:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
3%|β | 6/195 [00:11<05:41, 1.81s/it]
[2024-06-04 03:10:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
3%|β | 6/195 [00:11<05:41, 1.81s/it]
[2024-06-04 03:10:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
3%|β | 6/195 [00:11<05:41, 1.81s/it]
4%|β | 8/195 [00:11<03:38, 1.17s/it]
[2024-06-04 03:10:48] INFO group_quantization.py:217: Compiling quantize function for key: ((28672, 4096), float32, cuda, axis=1, output_transpose=False) |
|
4%|β | 8/195 [00:11<03:38, 1.17s/it]
[2024-06-04 03:10:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
4%|β | 8/195 [00:12<03:38, 1.17s/it]
[2024-06-04 03:10:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
4%|β | 8/195 [00:12<03:38, 1.17s/it]
5%|β | 9/195 [00:12<03:21, 1.08s/it]
[2024-06-04 03:10:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
5%|β | 9/195 [00:12<03:21, 1.08s/it]
[2024-06-04 03:10:48] INFO group_quantization.py:217: Compiling quantize function for key: ((6144, 4096), float32, cuda, axis=1, output_transpose=False) |
|
5%|β | 9/195 [00:12<03:21, 1.08s/it]
[2024-06-04 03:10:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
5%|β | 9/195 [00:12<03:21, 1.08s/it]
[2024-06-04 03:10:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
5%|β | 9/195 [00:12<03:21, 1.08s/it]
6%|β | 11/195 [00:12<02:20, 1.31it/s]
[2024-06-04 03:10:49] INFO group_quantization.py:217: Compiling quantize function for key: ((4096, 4096), float32, cuda, axis=1, output_transpose=False) |
|
6%|β | 11/195 [00:12<02:20, 1.31it/s]
[2024-06-04 03:10:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
6%|β | 11/195 [00:13<02:20, 1.31it/s]
[2024-06-04 03:10:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
6%|β | 11/195 [00:13<02:20, 1.31it/s]
6%|β | 12/195 [00:13<02:08, 1.43it/s]
[2024-06-04 03:10:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
6%|β | 12/195 [00:13<02:08, 1.43it/s]
[2024-06-04 03:10:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
6%|β | 12/195 [00:13<02:08, 1.43it/s]
[2024-06-04 03:10:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
6%|β | 12/195 [00:13<02:08, 1.43it/s]
7%|β | 14/195 [00:13<01:23, 2.16it/s]
[2024-06-04 03:10:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
7%|β | 14/195 [00:13<01:23, 2.16it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
7%|β | 14/195 [00:13<01:23, 2.16it/s]
8%|β | 15/195 [00:13<01:17, 2.31it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
8%|β | 15/195 [00:13<01:17, 2.31it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
8%|β | 15/195 [00:13<01:17, 2.31it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
8%|β | 15/195 [00:13<01:17, 2.31it/s]
9%|β | 17/195 [00:13<00:51, 3.45it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
9%|β | 17/195 [00:13<00:51, 3.45it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
9%|β | 17/195 [00:13<00:51, 3.45it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
9%|β | 17/195 [00:13<00:51, 3.45it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
9%|β | 17/195 [00:13<00:51, 3.45it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
9%|β | 17/195 [00:14<00:51, 3.45it/s]
10%|β | 20/195 [00:14<00:31, 5.49it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
10%|β | 20/195 [00:14<00:31, 5.49it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
10%|β | 20/195 [00:14<00:31, 5.49it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
10%|β | 20/195 [00:14<00:31, 5.49it/s]
11%|ββ | 22/195 [00:14<00:30, 5.75it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
11%|ββ | 22/195 [00:14<00:30, 5.75it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
11%|ββ | 22/195 [00:14<00:30, 5.75it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
11%|ββ | 22/195 [00:14<00:30, 5.75it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
11%|ββ | 22/195 [00:14<00:30, 5.75it/s]
12%|ββ | 24/195 [00:14<00:23, 7.26it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
12%|ββ | 24/195 [00:14<00:23, 7.26it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
12%|ββ | 24/195 [00:14<00:23, 7.26it/s]
[2024-06-04 03:10:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
12%|ββ | 24/195 [00:14<00:23, 7.26it/s]
13%|ββ | 26/195 [00:14<00:19, 8.66it/s]
[2024-06-04 03:10:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
13%|ββ | 26/195 [00:15<00:19, 8.66it/s]
[2024-06-04 03:10:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
13%|ββ | 26/195 [00:15<00:19, 8.66it/s]
[2024-06-04 03:10:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
13%|ββ | 26/195 [00:15<00:19, 8.66it/s]
14%|ββ | 28/195 [00:15<00:30, 5.49it/s]
[2024-06-04 03:10:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
14%|ββ | 28/195 [00:15<00:30, 5.49it/s]
[2024-06-04 03:10:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
14%|ββ | 28/195 [00:15<00:30, 5.49it/s]
[2024-06-04 03:10:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
14%|ββ | 28/195 [00:15<00:30, 5.49it/s]
[2024-06-04 03:10:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
14%|ββ | 28/195 [00:15<00:30, 5.49it/s]
[2024-06-04 03:10:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
14%|ββ | 28/195 [00:15<00:30, 5.49it/s]
[2024-06-04 03:10:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
14%|ββ | 28/195 [00:15<00:30, 5.49it/s]
[2024-06-04 03:10:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
14%|ββ | 28/195 [00:15<00:30, 5.49it/s]
16%|ββ | 32/195 [00:15<00:20, 7.88it/s]
[2024-06-04 03:10:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
16%|ββ | 32/195 [00:15<00:20, 7.88it/s]
[2024-06-04 03:10:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
16%|ββ | 32/195 [00:16<00:20, 7.88it/s]
[2024-06-04 03:10:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
16%|ββ | 32/195 [00:16<00:20, 7.88it/s]
17%|ββ | 34/195 [00:16<00:27, 5.81it/s]
[2024-06-04 03:10:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
17%|ββ | 34/195 [00:16<00:27, 5.81it/s]
[2024-06-04 03:10:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
17%|ββ | 34/195 [00:16<00:27, 5.81it/s]
[2024-06-04 03:10:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
17%|ββ | 34/195 [00:16<00:27, 5.81it/s]
[2024-06-04 03:10:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
17%|ββ | 34/195 [00:16<00:27, 5.81it/s]
18%|ββ | 36/195 [00:16<00:22, 7.04it/s]
[2024-06-04 03:10:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
18%|ββ | 36/195 [00:16<00:22, 7.04it/s]
[2024-06-04 03:10:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
18%|ββ | 36/195 [00:16<00:22, 7.04it/s]
[2024-06-04 03:10:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
18%|ββ | 36/195 [00:16<00:22, 7.04it/s]
19%|ββ | 38/195 [00:16<00:18, 8.32it/s]
[2024-06-04 03:10:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
19%|ββ | 38/195 [00:17<00:18, 8.32it/s]
[2024-06-04 03:10:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
19%|ββ | 38/195 [00:17<00:18, 8.32it/s]
[2024-06-04 03:10:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
19%|ββ | 38/195 [00:17<00:18, 8.32it/s]
21%|ββ | 40/195 [00:17<00:30, 5.07it/s]
[2024-06-04 03:10:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
21%|ββ | 40/195 [00:17<00:30, 5.07it/s]
[2024-06-04 03:10:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
21%|ββ | 40/195 [00:17<00:30, 5.07it/s]
[2024-06-04 03:10:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
21%|ββ | 40/195 [00:17<00:30, 5.07it/s]
[2024-06-04 03:10:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
21%|ββ | 40/195 [00:17<00:30, 5.07it/s]
22%|βββ | 42/195 [00:17<00:24, 6.28it/s]
[2024-06-04 03:10:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
22%|βββ | 42/195 [00:17<00:24, 6.28it/s]
[2024-06-04 03:10:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
22%|βββ | 42/195 [00:17<00:24, 6.28it/s]
[2024-06-04 03:10:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
22%|βββ | 42/195 [00:17<00:24, 6.28it/s]
23%|βββ | 44/195 [00:17<00:19, 7.66it/s]
[2024-06-04 03:10:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
23%|βββ | 44/195 [00:17<00:19, 7.66it/s]
[2024-06-04 03:10:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
23%|βββ | 44/195 [00:18<00:19, 7.66it/s]
[2024-06-04 03:10:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
23%|βββ | 44/195 [00:18<00:19, 7.66it/s]
24%|βββ | 46/195 [00:18<00:28, 5.14it/s]
[2024-06-04 03:10:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
24%|βββ | 46/195 [00:18<00:28, 5.14it/s]
[2024-06-04 03:10:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
24%|βββ | 46/195 [00:18<00:28, 5.14it/s]
[2024-06-04 03:10:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
24%|βββ | 46/195 [00:18<00:28, 5.14it/s]
[2024-06-04 03:10:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
24%|βββ | 46/195 [00:18<00:28, 5.14it/s]
25%|βββ | 48/195 [00:18<00:22, 6.54it/s]
[2024-06-04 03:10:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
25%|βββ | 48/195 [00:18<00:22, 6.54it/s]
[2024-06-04 03:10:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
25%|βββ | 48/195 [00:18<00:22, 6.54it/s]
[2024-06-04 03:10:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
25%|βββ | 48/195 [00:18<00:22, 6.54it/s]
26%|βββ | 50/195 [00:18<00:18, 7.86it/s]
[2024-06-04 03:10:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
26%|βββ | 50/195 [00:19<00:18, 7.86it/s]
[2024-06-04 03:10:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
26%|βββ | 50/195 [00:19<00:18, 7.86it/s]
[2024-06-04 03:10:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
26%|βββ | 50/195 [00:19<00:18, 7.86it/s]
27%|βββ | 52/195 [00:19<00:32, 4.40it/s]
[2024-06-04 03:10:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
27%|βββ | 52/195 [00:19<00:32, 4.40it/s]
[2024-06-04 03:10:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
27%|βββ | 52/195 [00:19<00:32, 4.40it/s]
[2024-06-04 03:10:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
27%|βββ | 52/195 [00:19<00:32, 4.40it/s]
[2024-06-04 03:10:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
27%|βββ | 52/195 [00:19<00:32, 4.40it/s]
[2024-06-04 03:10:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
27%|βββ | 52/195 [00:19<00:32, 4.40it/s]
[2024-06-04 03:10:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
27%|βββ | 52/195 [00:19<00:32, 4.40it/s]
[2024-06-04 03:10:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
27%|βββ | 52/195 [00:19<00:32, 4.40it/s]
29%|βββ | 56/195 [00:19<00:21, 6.57it/s]
[2024-06-04 03:10:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
29%|βββ | 56/195 [00:20<00:21, 6.57it/s]
[2024-06-04 03:10:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
29%|βββ | 56/195 [00:20<00:21, 6.57it/s]
[2024-06-04 03:10:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
29%|βββ | 56/195 [00:20<00:21, 6.57it/s]
30%|βββ | 58/195 [00:20<00:30, 4.43it/s]
[2024-06-04 03:10:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
30%|βββ | 58/195 [00:20<00:30, 4.43it/s]
[2024-06-04 03:10:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
30%|βββ | 58/195 [00:20<00:30, 4.43it/s]
[2024-06-04 03:10:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
30%|βββ | 58/195 [00:20<00:30, 4.43it/s]
[2024-06-04 03:10:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
30%|βββ | 58/195 [00:20<00:30, 4.43it/s]
31%|βββ | 60/195 [00:20<00:24, 5.47it/s]
[2024-06-04 03:10:56] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Meta-Llama-3-8B-Instruct/model-00001-of-00004.safetensors |
|
31%|βββ | 60/195 [00:20<00:24, 5.47it/s]
[2024-06-04 03:10:57] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Meta-Llama-3-8B-Instruct/model-00002-of-00004.safetensors |
|
31%|βββ | 60/195 [00:21<00:24, 5.47it/s]
[2024-06-04 03:11:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
31%|βββ | 60/195 [00:25<00:24, 5.47it/s]
[2024-06-04 03:11:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
31%|βββ | 60/195 [00:25<00:24, 5.47it/s]
[2024-06-04 03:11:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
31%|βββ | 60/195 [00:25<00:24, 5.47it/s]
32%|ββββ | 62/195 [00:25<01:40, 1.32it/s]
[2024-06-04 03:11:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
32%|ββββ | 62/195 [00:26<01:40, 1.32it/s]
[2024-06-04 03:11:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
32%|ββββ | 62/195 [00:26<01:40, 1.32it/s]
32%|ββββ | 63/195 [00:26<01:54, 1.15it/s]
[2024-06-04 03:11:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
32%|ββββ | 63/195 [00:26<01:54, 1.15it/s]
[2024-06-04 03:11:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
32%|ββββ | 63/195 [00:26<01:54, 1.15it/s]
[2024-06-04 03:11:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
32%|ββββ | 63/195 [00:26<01:54, 1.15it/s]
33%|ββββ | 65/195 [00:26<01:19, 1.63it/s]
[2024-06-04 03:11:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
33%|ββββ | 65/195 [00:26<01:19, 1.63it/s]
[2024-06-04 03:11:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
33%|ββββ | 65/195 [00:26<01:19, 1.63it/s]
[2024-06-04 03:11:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
33%|ββββ | 65/195 [00:26<01:19, 1.63it/s]
[2024-06-04 03:11:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
33%|ββββ | 65/195 [00:26<01:19, 1.63it/s]
[2024-06-04 03:11:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
33%|ββββ | 65/195 [00:26<01:19, 1.63it/s]
35%|ββββ | 68/195 [00:26<00:50, 2.50it/s]
[2024-06-04 03:11:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
35%|ββββ | 68/195 [00:28<00:50, 2.50it/s]
[2024-06-04 03:11:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
35%|ββββ | 68/195 [00:28<00:50, 2.50it/s]
[2024-06-04 03:11:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
35%|ββββ | 68/195 [00:28<00:50, 2.50it/s]
36%|ββββ | 70/195 [00:28<00:58, 2.14it/s]
[2024-06-04 03:11:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
36%|ββββ | 70/195 [00:28<00:58, 2.14it/s]
[2024-06-04 03:11:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
36%|ββββ | 70/195 [00:28<00:58, 2.14it/s]
[2024-06-04 03:11:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
36%|ββββ | 70/195 [00:28<00:58, 2.14it/s]
[2024-06-04 03:11:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
36%|ββββ | 70/195 [00:28<00:58, 2.14it/s]
37%|ββββ | 72/195 [00:28<00:43, 2.85it/s]
[2024-06-04 03:11:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
37%|ββββ | 72/195 [00:28<00:43, 2.85it/s]
[2024-06-04 03:11:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
37%|ββββ | 72/195 [00:28<00:43, 2.85it/s]
[2024-06-04 03:11:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
37%|ββββ | 72/195 [00:28<00:43, 2.85it/s]
38%|ββββ | 74/195 [00:28<00:32, 3.69it/s]
[2024-06-04 03:11:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
38%|ββββ | 74/195 [00:29<00:32, 3.69it/s]
[2024-06-04 03:11:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
38%|ββββ | 74/195 [00:29<00:32, 3.69it/s]
[2024-06-04 03:11:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
38%|ββββ | 74/195 [00:29<00:32, 3.69it/s]
39%|ββββ | 76/195 [00:29<00:41, 2.89it/s]
[2024-06-04 03:11:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
39%|ββββ | 76/195 [00:29<00:41, 2.89it/s]
[2024-06-04 03:11:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
39%|ββββ | 76/195 [00:29<00:41, 2.89it/s]
[2024-06-04 03:11:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
39%|ββββ | 76/195 [00:29<00:41, 2.89it/s]
[2024-06-04 03:11:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
39%|ββββ | 76/195 [00:29<00:41, 2.89it/s]
[2024-06-04 03:11:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
39%|ββββ | 76/195 [00:29<00:41, 2.89it/s]
[2024-06-04 03:11:05] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
39%|ββββ | 76/195 [00:29<00:41, 2.89it/s]
[2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
39%|ββββ | 76/195 [00:29<00:41, 2.89it/s]
41%|ββββ | 80/195 [00:29<00:25, 4.54it/s]
[2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
41%|ββββ | 80/195 [00:30<00:25, 4.54it/s]
[2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
41%|ββββ | 80/195 [00:30<00:25, 4.54it/s]
[2024-06-04 03:11:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
41%|ββββ | 80/195 [00:30<00:25, 4.54it/s]
42%|βββββ | 82/195 [00:30<00:23, 4.72it/s]
[2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
42%|βββββ | 82/195 [00:30<00:23, 4.72it/s]
[2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
42%|βββββ | 82/195 [00:30<00:23, 4.72it/s]
[2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
42%|βββββ | 82/195 [00:30<00:23, 4.72it/s]
[2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
42%|βββββ | 82/195 [00:30<00:23, 4.72it/s]
43%|βββββ | 84/195 [00:30<00:19, 5.79it/s]
[2024-06-04 03:11:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
43%|βββββ | 84/195 [00:30<00:19, 5.79it/s]
[2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
43%|βββββ | 84/195 [00:30<00:19, 5.79it/s]
[2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
43%|βββββ | 84/195 [00:30<00:19, 5.79it/s]
44%|βββββ | 86/195 [00:30<00:15, 6.91it/s]
[2024-06-04 03:11:06] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
44%|βββββ | 86/195 [00:30<00:15, 6.91it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
44%|βββββ | 86/195 [00:30<00:15, 6.91it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
44%|βββββ | 86/195 [00:30<00:15, 6.91it/s]
45%|βββββ | 88/195 [00:30<00:16, 6.49it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
45%|βββββ | 88/195 [00:30<00:16, 6.49it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
45%|βββββ | 88/195 [00:30<00:16, 6.49it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
45%|βββββ | 88/195 [00:30<00:16, 6.49it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
45%|βββββ | 88/195 [00:30<00:16, 6.49it/s]
46%|βββββ | 90/195 [00:30<00:13, 7.68it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
46%|βββββ | 90/195 [00:30<00:13, 7.68it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
46%|βββββ | 90/195 [00:31<00:13, 7.68it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
46%|βββββ | 90/195 [00:31<00:13, 7.68it/s]
47%|βββββ | 92/195 [00:31<00:11, 8.93it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
47%|βββββ | 92/195 [00:31<00:11, 8.93it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
47%|βββββ | 92/195 [00:31<00:11, 8.93it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
47%|βββββ | 92/195 [00:31<00:11, 8.93it/s]
48%|βββββ | 94/195 [00:31<00:13, 7.71it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
48%|βββββ | 94/195 [00:31<00:13, 7.71it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
48%|βββββ | 94/195 [00:31<00:13, 7.71it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
48%|βββββ | 94/195 [00:31<00:13, 7.71it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
48%|βββββ | 94/195 [00:31<00:13, 7.71it/s]
49%|βββββ | 96/195 [00:31<00:10, 9.25it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
49%|βββββ | 96/195 [00:31<00:10, 9.25it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
49%|βββββ | 96/195 [00:31<00:10, 9.25it/s]
[2024-06-04 03:11:07] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
49%|βββββ | 96/195 [00:31<00:10, 9.25it/s]
50%|βββββ | 98/195 [00:31<00:09, 10.19it/s]
[2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
50%|βββββ | 98/195 [00:31<00:09, 10.19it/s]
[2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
50%|βββββ | 98/195 [00:32<00:09, 10.19it/s]
[2024-06-04 03:11:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
50%|βββββ | 98/195 [00:32<00:09, 10.19it/s]
51%|ββββββ | 100/195 [00:32<00:12, 7.84it/s]
[2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
51%|ββββββ | 100/195 [00:32<00:12, 7.84it/s]
[2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
51%|ββββββ | 100/195 [00:32<00:12, 7.84it/s]
[2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
51%|ββββββ | 100/195 [00:32<00:12, 7.84it/s]
[2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
51%|ββββββ | 100/195 [00:32<00:12, 7.84it/s]
[2024-06-04 03:11:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
51%|ββββββ | 100/195 [00:32<00:12, 7.84it/s]
[2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
51%|ββββββ | 100/195 [00:32<00:12, 7.84it/s]
[2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
51%|ββββββ | 100/195 [00:32<00:12, 7.84it/s]
53%|ββββββ | 104/195 [00:32<00:09, 9.93it/s]
[2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
53%|ββββββ | 104/195 [00:32<00:09, 9.93it/s]
[2024-06-04 03:11:08] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
53%|ββββββ | 104/195 [00:32<00:09, 9.93it/s]
[2024-06-04 03:11:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
53%|ββββββ | 104/195 [00:32<00:09, 9.93it/s]
54%|ββββββ | 106/195 [00:32<00:10, 8.43it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
54%|ββββββ | 106/195 [00:32<00:10, 8.43it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
54%|ββββββ | 106/195 [00:32<00:10, 8.43it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
54%|ββββββ | 106/195 [00:32<00:10, 8.43it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
54%|ββββββ | 106/195 [00:32<00:10, 8.43it/s]
55%|ββββββ | 108/195 [00:32<00:09, 9.65it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
55%|ββββββ | 108/195 [00:32<00:09, 9.65it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
55%|ββββββ | 108/195 [00:32<00:09, 9.65it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
55%|ββββββ | 108/195 [00:32<00:09, 9.65it/s]
56%|ββββββ | 110/195 [00:33<00:07, 10.66it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
56%|ββββββ | 110/195 [00:33<00:07, 10.66it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
56%|ββββββ | 110/195 [00:33<00:07, 10.66it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
56%|ββββββ | 110/195 [00:33<00:07, 10.66it/s]
57%|ββββββ | 112/195 [00:33<00:09, 8.60it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
57%|ββββββ | 112/195 [00:33<00:09, 8.60it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
57%|ββββββ | 112/195 [00:33<00:09, 8.60it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
57%|ββββββ | 112/195 [00:33<00:09, 8.60it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
57%|ββββββ | 112/195 [00:33<00:09, 8.60it/s]
58%|ββββββ | 114/195 [00:33<00:08, 9.72it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
58%|ββββββ | 114/195 [00:33<00:08, 9.72it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
58%|ββββββ | 114/195 [00:33<00:08, 9.72it/s]
[2024-06-04 03:11:09] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
58%|ββββββ | 114/195 [00:33<00:08, 9.72it/s]
59%|ββββββ | 116/195 [00:33<00:07, 10.80it/s]
[2024-06-04 03:11:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
59%|ββββββ | 116/195 [00:33<00:07, 10.80it/s]
[2024-06-04 03:11:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
59%|ββββββ | 116/195 [00:33<00:07, 10.80it/s]
[2024-06-04 03:11:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
59%|ββββββ | 116/195 [00:33<00:07, 10.80it/s]
61%|ββββββ | 118/195 [00:33<00:08, 8.64it/s]
[2024-06-04 03:11:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
61%|ββββββ | 118/195 [00:34<00:08, 8.64it/s]
[2024-06-04 03:11:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
61%|ββββββ | 118/195 [00:34<00:08, 8.64it/s]
[2024-06-04 03:11:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
61%|ββββββ | 118/195 [00:34<00:08, 8.64it/s]
[2024-06-04 03:11:10] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
61%|ββββββ | 118/195 [00:34<00:08, 8.64it/s]
62%|βββββββ | 120/195 [00:34<00:07, 10.18it/s]
[2024-06-04 03:11:10] INFO huggingface_loader.py:185: Loading HF parameters from: /models/Meta-Llama-3-8B-Instruct/model-00003-of-00004.safetensors |
|
62%|βββββββ | 120/195 [00:34<00:07, 10.18it/s]
[2024-06-04 03:11:15] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
62%|βββββββ | 120/195 [00:39<00:07, 10.18it/s]
[2024-06-04 03:11:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
62%|βββββββ | 120/195 [00:39<00:07, 10.18it/s]
[2024-06-04 03:11:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
62%|βββββββ | 120/195 [00:40<00:07, 10.18it/s]
[2024-06-04 03:11:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
62%|βββββββ | 120/195 [00:40<00:07, 10.18it/s]
63%|βββββββ | 122/195 [00:40<01:10, 1.04it/s]
[2024-06-04 03:11:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
63%|βββββββ | 122/195 [00:40<01:10, 1.04it/s]
[2024-06-04 03:11:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
63%|βββββββ | 122/195 [00:40<01:10, 1.04it/s]
[2024-06-04 03:11:16] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
63%|βββββββ | 122/195 [00:40<01:10, 1.04it/s]
[2024-06-04 03:11:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
63%|βββββββ | 122/195 [00:40<01:10, 1.04it/s]
[2024-06-04 03:11:16] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
63%|βββββββ | 122/195 [00:40<01:10, 1.04it/s]
64%|βββββββ | 125/195 [00:40<00:44, 1.58it/s]
[2024-06-04 03:11:17] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
64%|βββββββ | 125/195 [00:41<00:44, 1.58it/s]
[2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
64%|βββββββ | 125/195 [00:41<00:44, 1.58it/s]
65%|βββββββ | 126/195 [00:41<00:52, 1.33it/s]
[2024-06-04 03:11:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
65%|βββββββ | 126/195 [00:41<00:52, 1.33it/s]
[2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
65%|βββββββ | 126/195 [00:41<00:52, 1.33it/s]
[2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
65%|βββββββ | 126/195 [00:41<00:52, 1.33it/s]
[2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
65%|βββββββ | 126/195 [00:41<00:52, 1.33it/s]
[2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
65%|βββββββ | 126/195 [00:41<00:52, 1.33it/s]
[2024-06-04 03:11:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
65%|βββββββ | 126/195 [00:41<00:52, 1.33it/s]
[2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
65%|βββββββ | 126/195 [00:41<00:52, 1.33it/s]
[2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
65%|βββββββ | 126/195 [00:42<00:52, 1.33it/s]
67%|βββββββ | 131/195 [00:42<00:24, 2.60it/s]
[2024-06-04 03:11:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
67%|βββββββ | 131/195 [00:42<00:24, 2.60it/s]
[2024-06-04 03:11:18] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
67%|βββββββ | 131/195 [00:42<00:24, 2.60it/s]
[2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
67%|βββββββ | 131/195 [00:42<00:24, 2.60it/s]
[2024-06-04 03:11:18] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
67%|βββββββ | 131/195 [00:42<00:24, 2.60it/s]
69%|βββββββ | 134/195 [00:42<00:17, 3.56it/s]
[2024-06-04 03:11:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
69%|βββββββ | 134/195 [00:43<00:17, 3.56it/s]
[2024-06-04 03:11:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
69%|βββββββ | 134/195 [00:43<00:17, 3.56it/s]
[2024-06-04 03:11:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
69%|βββββββ | 134/195 [00:43<00:17, 3.56it/s]
70%|βββββββ | 136/195 [00:43<00:19, 3.04it/s]
[2024-06-04 03:11:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
70%|βββββββ | 136/195 [00:43<00:19, 3.04it/s]
[2024-06-04 03:11:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
70%|βββββββ | 136/195 [00:43<00:19, 3.04it/s]
[2024-06-04 03:11:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
70%|βββββββ | 136/195 [00:43<00:19, 3.04it/s]
[2024-06-04 03:11:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
70%|βββββββ | 136/195 [00:43<00:19, 3.04it/s]
71%|βββββββ | 138/195 [00:43<00:14, 3.81it/s]
[2024-06-04 03:11:19] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
71%|βββββββ | 138/195 [00:43<00:14, 3.81it/s]
[2024-06-04 03:11:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.22.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
71%|βββββββ | 138/195 [00:43<00:14, 3.81it/s]
[2024-06-04 03:11:19] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.22.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
71%|βββββββ | 138/195 [00:43<00:14, 3.81it/s]
72%|ββββββββ | 140/195 [00:43<00:11, 4.72it/s]
[2024-06-04 03:11:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.22.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
72%|ββββββββ | 140/195 [00:44<00:11, 4.72it/s]
[2024-06-04 03:11:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.22.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
72%|ββββββββ | 140/195 [00:44<00:11, 4.72it/s]
[2024-06-04 03:11:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
72%|ββββββββ | 140/195 [00:44<00:11, 4.72it/s]
73%|ββββββββ | 142/195 [00:44<00:15, 3.51it/s]
[2024-06-04 03:11:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
73%|ββββββββ | 142/195 [00:44<00:15, 3.51it/s]
[2024-06-04 03:11:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
73%|ββββββββ | 142/195 [00:44<00:15, 3.51it/s]
73%|ββββββββ | 143/195 [00:44<00:13, 3.88it/s]
[2024-06-04 03:11:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
73%|ββββββββ | 143/195 [00:44<00:13, 3.88it/s]
[2024-06-04 03:11:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
73%|ββββββββ | 143/195 [00:44<00:13, 3.88it/s]
[2024-06-04 03:11:20] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
73%|ββββββββ | 143/195 [00:44<00:13, 3.88it/s]
[2024-06-04 03:11:20] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.23.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
73%|ββββββββ | 143/195 [00:44<00:13, 3.88it/s]
[2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.23.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
73%|ββββββββ | 143/195 [00:44<00:13, 3.88it/s]
75%|ββββββββ | 146/195 [00:44<00:08, 5.71it/s]
[2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.23.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
75%|ββββββββ | 146/195 [00:45<00:08, 5.71it/s]
[2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.23.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
75%|ββββββββ | 146/195 [00:45<00:08, 5.71it/s]
[2024-06-04 03:11:21] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
75%|ββββββββ | 146/195 [00:45<00:08, 5.71it/s]
76%|ββββββββ | 148/195 [00:45<00:09, 4.83it/s]
[2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
76%|ββββββββ | 148/195 [00:45<00:09, 4.83it/s]
[2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
76%|ββββββββ | 148/195 [00:45<00:09, 4.83it/s]
[2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
76%|ββββββββ | 148/195 [00:45<00:09, 4.83it/s]
[2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
76%|ββββββββ | 148/195 [00:45<00:09, 4.83it/s]
77%|ββββββββ | 150/195 [00:45<00:07, 6.07it/s]
[2024-06-04 03:11:21] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
77%|ββββββββ | 150/195 [00:45<00:07, 6.07it/s]
[2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.24.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
77%|ββββββββ | 150/195 [00:45<00:07, 6.07it/s]
[2024-06-04 03:11:21] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.24.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
77%|ββββββββ | 150/195 [00:45<00:07, 6.07it/s]
78%|ββββββββ | 152/195 [00:45<00:05, 7.25it/s]
[2024-06-04 03:11:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.24.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
78%|ββββββββ | 152/195 [00:46<00:05, 7.25it/s]
[2024-06-04 03:11:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.24.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
78%|ββββββββ | 152/195 [00:46<00:05, 7.25it/s]
[2024-06-04 03:11:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
78%|ββββββββ | 152/195 [00:46<00:05, 7.25it/s]
79%|ββββββββ | 154/195 [00:46<00:07, 5.27it/s]
[2024-06-04 03:11:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.24.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
79%|ββββββββ | 154/195 [00:46<00:07, 5.27it/s]
[2024-06-04 03:11:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.24.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
79%|ββββββββ | 154/195 [00:46<00:07, 5.27it/s]
[2024-06-04 03:11:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.24.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
79%|ββββββββ | 154/195 [00:46<00:07, 5.27it/s]
[2024-06-04 03:11:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.24.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
79%|ββββββββ | 154/195 [00:46<00:07, 5.27it/s]
[2024-06-04 03:11:22] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
79%|ββββββββ | 154/195 [00:46<00:07, 5.27it/s]
[2024-06-04 03:11:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.25.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
79%|ββββββββ | 154/195 [00:46<00:07, 5.27it/s]
[2024-06-04 03:11:22] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.25.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
79%|ββββββββ | 154/195 [00:46<00:07, 5.27it/s]
81%|ββββββββ | 158/195 [00:46<00:05, 7.38it/s]
[2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.25.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
81%|ββββββββ | 158/195 [00:46<00:05, 7.38it/s]
[2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.25.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
81%|ββββββββ | 158/195 [00:47<00:05, 7.38it/s]
[2024-06-04 03:11:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
81%|ββββββββ | 158/195 [00:47<00:05, 7.38it/s]
82%|βββββββββ | 160/195 [00:47<00:06, 5.51it/s]
[2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.25.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
82%|βββββββββ | 160/195 [00:47<00:06, 5.51it/s]
[2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.25.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
82%|βββββββββ | 160/195 [00:47<00:06, 5.51it/s]
[2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.25.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
82%|βββββββββ | 160/195 [00:47<00:06, 5.51it/s]
[2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.25.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
82%|βββββββββ | 160/195 [00:47<00:06, 5.51it/s]
83%|βββββββββ | 162/195 [00:47<00:04, 6.65it/s]
[2024-06-04 03:11:23] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
83%|βββββββββ | 162/195 [00:47<00:04, 6.65it/s]
[2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.26.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
83%|βββββββββ | 162/195 [00:47<00:04, 6.65it/s]
[2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.26.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
83%|βββββββββ | 162/195 [00:47<00:04, 6.65it/s]
84%|βββββββββ | 164/195 [00:47<00:03, 7.83it/s]
[2024-06-04 03:11:23] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.26.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
84%|βββββββββ | 164/195 [00:47<00:03, 7.83it/s]
[2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.26.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
84%|βββββββββ | 164/195 [00:47<00:03, 7.83it/s]
[2024-06-04 03:11:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
84%|βββββββββ | 164/195 [00:47<00:03, 7.83it/s]
85%|βββββββββ | 166/195 [00:47<00:04, 6.25it/s]
[2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.26.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
85%|βββββββββ | 166/195 [00:47<00:04, 6.25it/s]
[2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.26.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
85%|βββββββββ | 166/195 [00:47<00:04, 6.25it/s]
86%|βββββββββ | 167/195 [00:48<00:04, 6.55it/s]
[2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.26.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
86%|βββββββββ | 167/195 [00:48<00:04, 6.55it/s]
[2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.26.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
86%|βββββββββ | 167/195 [00:48<00:04, 6.55it/s]
[2024-06-04 03:11:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
86%|βββββββββ | 167/195 [00:48<00:04, 6.55it/s]
[2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.27.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
86%|βββββββββ | 167/195 [00:48<00:04, 6.55it/s]
[2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.27.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
86%|βββββββββ | 167/195 [00:48<00:04, 6.55it/s]
87%|βββββββββ | 170/195 [00:48<00:02, 8.93it/s]
[2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.27.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
87%|βββββββββ | 170/195 [00:48<00:02, 8.93it/s]
[2024-06-04 03:11:24] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.27.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
87%|βββββββββ | 170/195 [00:48<00:02, 8.93it/s]
[2024-06-04 03:11:24] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
87%|βββββββββ | 170/195 [00:48<00:02, 8.93it/s]
88%|βββββββββ | 172/195 [00:48<00:03, 6.43it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.27.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
88%|βββββββββ | 172/195 [00:48<00:03, 6.43it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.27.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
88%|βββββββββ | 172/195 [00:48<00:03, 6.43it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.27.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
88%|βββββββββ | 172/195 [00:48<00:03, 6.43it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.27.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
88%|βββββββββ | 172/195 [00:48<00:03, 6.43it/s]
89%|βββββββββ | 174/195 [00:48<00:02, 7.88it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.28.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
89%|βββββββββ | 174/195 [00:48<00:02, 7.88it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.28.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
89%|βββββββββ | 174/195 [00:48<00:02, 7.88it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.28.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
89%|βββββββββ | 174/195 [00:48<00:02, 7.88it/s]
90%|βββββββββ | 176/195 [00:48<00:02, 8.98it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.28.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
90%|βββββββββ | 176/195 [00:49<00:02, 8.98it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.28.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
90%|βββββββββ | 176/195 [00:49<00:02, 8.98it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.28.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
90%|βββββββββ | 176/195 [00:49<00:02, 8.98it/s]
91%|ββββββββββ| 178/195 [00:49<00:02, 6.64it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.28.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
91%|ββββββββββ| 178/195 [00:49<00:02, 6.64it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.28.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
91%|ββββββββββ| 178/195 [00:49<00:02, 6.64it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.28.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
91%|ββββββββββ| 178/195 [00:49<00:02, 6.64it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.28.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
91%|ββββββββββ| 178/195 [00:49<00:02, 6.64it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.29.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
91%|ββββββββββ| 178/195 [00:49<00:02, 6.64it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.29.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
91%|ββββββββββ| 178/195 [00:49<00:02, 6.64it/s]
[2024-06-04 03:11:25] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.29.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
91%|ββββββββββ| 178/195 [00:49<00:02, 6.64it/s]
93%|ββββββββββ| 182/195 [00:49<00:01, 8.75it/s]
[2024-06-04 03:11:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.29.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
93%|ββββββββββ| 182/195 [00:50<00:01, 8.75it/s]
[2024-06-04 03:11:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.29.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
93%|ββββββββββ| 182/195 [00:50<00:01, 8.75it/s]
[2024-06-04 03:11:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.29.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
93%|ββββββββββ| 182/195 [00:50<00:01, 8.75it/s]
94%|ββββββββββ| 184/195 [00:50<00:01, 6.68it/s]
[2024-06-04 03:11:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.29.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
94%|ββββββββββ| 184/195 [00:50<00:01, 6.68it/s]
[2024-06-04 03:11:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.29.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
94%|ββββββββββ| 184/195 [00:50<00:01, 6.68it/s]
[2024-06-04 03:11:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.29.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
94%|ββββββββββ| 184/195 [00:50<00:01, 6.68it/s]
[2024-06-04 03:11:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.29.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
94%|ββββββββββ| 184/195 [00:50<00:01, 6.68it/s]
95%|ββββββββββ| 186/195 [00:50<00:01, 7.90it/s]
[2024-06-04 03:11:26] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.30.input_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
95%|ββββββββββ| 186/195 [00:50<00:01, 7.90it/s]
[2024-06-04 03:11:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.30.mlp.down_proj.q_weight[0m", shape: (4096, 1792), dtype: uint32 |
|
95%|ββββββββββ| 186/195 [00:50<00:01, 7.90it/s]
[2024-06-04 03:11:26] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.30.mlp.down_proj.q_scale[0m", shape: (4096, 448), dtype: float32 |
|
95%|ββββββββββ| 186/195 [00:50<00:01, 7.90it/s]
96%|ββββββββββ| 188/195 [00:50<00:00, 9.03it/s]
[2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.30.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
96%|ββββββββββ| 188/195 [00:50<00:00, 9.03it/s]
[2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.30.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
96%|ββββββββββ| 188/195 [00:50<00:00, 9.03it/s]
[2024-06-04 03:11:27] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.30.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32 |
|
96%|ββββββββββ| 188/195 [00:50<00:00, 9.03it/s]
97%|ββββββββββ| 190/195 [00:50<00:00, 7.15it/s]
[2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.30.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
97%|ββββββββββ| 190/195 [00:51<00:00, 7.15it/s]
[2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.30.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
97%|ββββββββββ| 190/195 [00:51<00:00, 7.15it/s]
98%|ββββββββββ| 191/195 [00:51<00:00, 7.35it/s]
[2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.30.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
98%|ββββββββββ| 191/195 [00:51<00:00, 7.35it/s]
[2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.30.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
98%|ββββββββββ| 191/195 [00:51<00:00, 7.35it/s]
[2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.31.mlp.gate_up_proj.q_weight[0m", shape: (28672, 512), dtype: uint32 |
|
98%|ββββββββββ| 191/195 [00:51<00:00, 7.35it/s]
[2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.31.mlp.gate_up_proj.q_scale[0m", shape: (28672, 128), dtype: float32 |
|
98%|ββββββββββ| 191/195 [00:51<00:00, 7.35it/s]
99%|ββββββββββ| 193/195 [00:51<00:00, 6.55it/s]
[2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.31.self_attn.qkv_proj.q_weight[0m", shape: (6144, 512), dtype: uint32 |
|
99%|ββββββββββ| 193/195 [00:51<00:00, 6.55it/s]
[2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.31.self_attn.qkv_proj.q_scale[0m", shape: (6144, 128), dtype: float32 |
|
99%|ββββββββββ| 193/195 [00:51<00:00, 6.55it/s]
[2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.31.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32 |
|
99%|ββββββββββ| 193/195 [00:51<00:00, 6.55it/s]
[2024-06-04 03:11:27] INFO huggingface_loader.py:167: [Quantized] Parameter: "[1mmodel.layers.31.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32 |
|
99%|ββββββββββ| 193/195 [00:51<00:00, 6.55it/s]
100%|ββββββββββ| 195/195 [00:51<00:00, 7.88it/s]
100%|ββββββββββ| 195/195 [00:51<00:00, 3.78it/s] |
|
[2024-06-04 03:11:27] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Meta-Llama-3-8B-Instruct/model-00002-of-00004.safetensors |
|
[2024-06-04 03:11:28] INFO huggingface_loader.py:197: Unloading HF weight file: /models/Meta-Llama-3-8B-Instruct/model-00003-of-00004.safetensors |
|
[2024-06-04 03:11:28] INFO stats.py:77: [92mTime usage[0m: HF loading: 15.651 sec; Pre-quantization mapping: 17.726 sec; Quantization: 3.229 sec |
|
[2024-06-04 03:11:28] INFO stats.py:91: [92mRAM usage[0m: Peak RAM: 18.469 GB. Total bytes loaded from disk: 29.915 GB |
|
[2024-06-04 03:11:28] INFO convert_weight.py:155: [92mParameter size[0m after quantization: 4.675 GB |
|
[2024-06-04 03:11:28] INFO convert_weight.py:160: [92mTotal parameters[0m: 8,030,261,248 |
|
[2024-06-04 03:11:28] INFO convert_weight.py:161: [92mBits per parameter[0m: 5.001 |
|
[2024-06-04 03:11:28] INFO convert_weight.py:166: Saved to directory: [1m/models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC[0m |
|
|
|
All finished, 108 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC/ndarray-cache.json |
|
Also saved a bf16 record to /models/mlc-delivery/hf/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC/ndarray-cache-b16.json |
|
|