| /Users/cfruan/miniconda3/envs/mlc-chat-venv/bin/python -m mlc_chat gen_config /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo --quantization q4f16_1 --conv-template codellama_instruct --output /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y --context-window-size 16384 |
| [2024-01-30 00:51:30] INFO auto_config.py:115: [92mFound[0m model configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/config.json |
| [2024-01-30 00:51:30] INFO auto_config.py:153: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override. |
| [2024-01-30 00:51:30] INFO llama_model.py:51: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (16384) |
| [2024-01-30 00:51:30] INFO llama_model.py:71: [1mprefill_chunk_size[0m defaults to [1mcontext_window_size[0m (16384) |
| [2024-01-30 00:51:30] INFO config.py:106: Overriding [1mcontext_window_size[0m from 16384 to 16384 |
| [2024-01-30 00:51:30] INFO config.py:106: Overriding [1mmax_batch_size[0m from 1 to 80 |
| [2024-01-30 00:51:30] INFO gen_config.py:116: [generation_config.json] Setting [1mbos_token_id[0m: 1 |
| [2024-01-30 00:51:30] INFO gen_config.py:116: [generation_config.json] Setting [1meos_token_id[0m: 2 |
| [2024-01-30 00:51:30] INFO gen_config.py:128: [92mFound[0m tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/tokenizer.model. Copying to [1m/var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y/tokenizer.model[0m |
| [2024-01-30 00:51:30] INFO gen_config.py:128: [92mFound[0m tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/tokenizer.json. Copying to [1m/var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y/tokenizer.json[0m |
| [2024-01-30 00:51:30] INFO gen_config.py:130: [91mNot found[0m tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/vocab.json |
| [2024-01-30 00:51:30] INFO gen_config.py:130: [91mNot found[0m tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/merges.txt |
| [2024-01-30 00:51:30] INFO gen_config.py:130: [91mNot found[0m tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/added_tokens.json |
| [2024-01-30 00:51:30] INFO gen_config.py:128: [92mFound[0m tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/tokenizer_config.json. Copying to [1m/var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y/tokenizer_config.json[0m |
| [2024-01-30 00:51:30] INFO gen_config.py:69: [System default] Setting [1mpad_token_id[0m: 0 |
| [2024-01-30 00:51:30] INFO gen_config.py:69: [System default] Setting [1mtemperature[0m: 0.7 |
| [2024-01-30 00:51:30] INFO gen_config.py:69: [System default] Setting [1mrepetition_penalty[0m: 1.0 |
| [2024-01-30 00:51:30] INFO gen_config.py:69: [System default] Setting [1mtop_p[0m: 0.95 |
| [2024-01-30 00:51:30] INFO gen_config.py:69: [System default] Setting [1mmean_gen_len[0m: 128 |
| [2024-01-30 00:51:30] INFO gen_config.py:69: [System default] Setting [1mmax_gen_len[0m: 512 |
| [2024-01-30 00:51:30] INFO gen_config.py:69: [System default] Setting [1mshift_fill_factor[0m: 0.3 |
| [2024-01-30 00:51:30] INFO gen_config.py:158: Dumping configuration file to: [1m/var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y/mlc-chat-config.json[0m |
| /Users/cfruan/miniconda3/envs/mlc-chat-venv/bin/python -m mlc_chat convert_weight /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo --quantization q4f16_1 --source-format auto --output /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y |
| [2024-01-30 00:51:30] INFO auto_config.py:115: [92mFound[0m model configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/config.json |
| [2024-01-30 00:51:31] INFO auto_device.py:85: [91mNot found[0m device: cuda:0 |
| [2024-01-30 00:51:31] INFO auto_device.py:85: [91mNot found[0m device: rocm:0 |
| [2024-01-30 00:51:31] INFO auto_device.py:76: [92mFound[0m device: metal:0 |
| [2024-01-30 00:51:32] INFO auto_device.py:85: [91mNot found[0m device: vulkan:0 |
| [2024-01-30 00:51:32] INFO auto_device.py:85: [91mNot found[0m device: opencl:0 |
| [2024-01-30 00:51:32] INFO auto_device.py:33: Using device: [1mmetal:0[0m |
| [2024-01-30 00:51:32] INFO auto_weight.py:70: Finding weights in: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo |
| [2024-01-30 00:51:32] INFO auto_weight.py:120: [92mFound[0m source weight format: huggingface-torch. Source configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model.bin.index.json |
| [2024-01-30 00:51:32] INFO auto_weight.py:143: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/model.safetensors.index.json |
| [2024-01-30 00:51:32] INFO auto_weight.py:106: Using source weight configuration: [1m/var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model.bin.index.json[0m. Use `--source` to override. |
| [2024-01-30 00:51:32] INFO auto_weight.py:110: Using source weight format: [1mhuggingface-torch[0m. Use `--source-format` to override. |
| [2024-01-30 00:51:32] INFO auto_config.py:153: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override. |
| [2024-01-30 00:51:32] INFO llama_model.py:51: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (16384) |
| [2024-01-30 00:51:32] INFO llama_model.py:71: [1mprefill_chunk_size[0m defaults to [1mcontext_window_size[0m (16384) |
| [1mWeight conversion with arguments:[0m |
| [1m--config[0m /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/config.json |
| [1m--quantization[0m GroupQuantize(name='q4f16_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float16', linear_weight_layout='NK', num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7) |
| [1m--model-type[0m llama |
| [1m--device[0m metal:0 |
| [1m--source[0m /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model.bin.index.json |
| [1m--source-format[0m huggingface-torch |
| [1m--output[0m /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y |
|
0%| | 0/243 [00:00<?, ?it/s]
[2024-01-30 00:51:37] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model-00003-of-00003.bin |
|
0%| | 0/243 [00:00<?, ?it/s]
[2024-01-30 00:51:41] INFO group_quantization.py:227: Compiling quantize function for key: ((32000, 5120), float16, metal, axis=1, output_transpose=False) |
|
0%| | 0/243 [00:04<?, ?it/s]
[2024-01-30 00:51:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mlm_head.q_weight[0m", shape: (32000, 640), dtype: uint32 |
|
0%| | 0/243 [00:04<?, ?it/s]
[2024-01-30 00:51:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mlm_head.q_scale[0m", shape: (32000, 160), dtype: float16 |
|
0%| | 0/243 [00:04<?, ?it/s]
0%|▍ | 1/243 [00:04<17:50, 4.43s/it]
[2024-01-30 00:51:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.30.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
0%|▍ | 1/243 [00:04<17:50, 4.43s/it]
[2024-01-30 00:51:41] INFO group_quantization.py:227: Compiling quantize function for key: ((5120, 13824), float16, metal, axis=1, output_transpose=False) |
|
0%|▍ | 1/243 [00:04<17:50, 4.43s/it]
[2024-01-30 00:51:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.30.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
0%|▍ | 1/243 [00:04<17:50, 4.43s/it]
[2024-01-30 00:51:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.30.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
0%|▍ | 1/243 [00:04<17:50, 4.43s/it]
1%|█▎ | 3/243 [00:04<04:57, 1.24s/it]
[2024-01-30 00:51:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.30.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
1%|█▎ | 3/243 [00:04<04:57, 1.24s/it]
[2024-01-30 00:51:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.31.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
1%|█▎ | 3/243 [00:04<04:57, 1.24s/it]
[2024-01-30 00:51:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.31.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
1%|█▎ | 3/243 [00:04<04:57, 1.24s/it]
[2024-01-30 00:51:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.31.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
1%|█▎ | 3/243 [00:04<04:57, 1.24s/it]
2%|██▋ | 6/243 [00:04<02:02, 1.93it/s]
[2024-01-30 00:51:42] INFO group_quantization.py:227: Compiling quantize function for key: ((27648, 5120), float16, metal, axis=1, output_transpose=False) |
|
2%|██▋ | 6/243 [00:05<02:02, 1.93it/s]
[2024-01-30 00:51:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.31.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
2%|██▋ | 6/243 [00:05<02:02, 1.93it/s]
[2024-01-30 00:51:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.31.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
2%|██▋ | 6/243 [00:05<02:02, 1.93it/s]
3%|███ | 7/243 [00:05<02:01, 1.94it/s]
[2024-01-30 00:51:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.31.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
3%|███ | 7/243 [00:05<02:01, 1.94it/s]
[2024-01-30 00:51:42] INFO group_quantization.py:227: Compiling quantize function for key: ((15360, 5120), float16, metal, axis=1, output_transpose=False) |
|
3%|███ | 7/243 [00:05<02:01, 1.94it/s]
[2024-01-30 00:51:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.31.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
3%|███ | 7/243 [00:05<02:01, 1.94it/s]
[2024-01-30 00:51:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.31.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
3%|███ | 7/243 [00:05<02:01, 1.94it/s]
4%|████ | 9/243 [00:05<01:27, 2.68it/s]
[2024-01-30 00:51:42] INFO group_quantization.py:227: Compiling quantize function for key: ((5120, 5120), float16, metal, axis=1, output_transpose=False) |
|
4%|████ | 9/243 [00:05<01:27, 2.68it/s]
[2024-01-30 00:51:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.31.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
4%|████ | 9/243 [00:05<01:27, 2.68it/s]
[2024-01-30 00:51:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.31.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
4%|████ | 9/243 [00:05<01:27, 2.68it/s]
4%|████▍ | 10/243 [00:05<01:14, 3.13it/s]
[2024-01-30 00:51:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.32.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
4%|████▍ | 10/243 [00:05<01:14, 3.13it/s]
[2024-01-30 00:51:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.32.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
4%|████▍ | 10/243 [00:05<01:14, 3.13it/s]
[2024-01-30 00:51:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.32.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
4%|████▍ | 10/243 [00:05<01:14, 3.13it/s]
5%|█████▎ | 12/243 [00:05<00:53, 4.29it/s]
[2024-01-30 00:51:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.32.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
5%|█████▎ | 12/243 [00:06<00:53, 4.29it/s]
[2024-01-30 00:51:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.32.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
5%|█████▎ | 12/243 [00:06<00:53, 4.29it/s]
5%|█████▋ | 13/243 [00:06<01:04, 3.58it/s]
[2024-01-30 00:51:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.32.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
5%|█████▋ | 13/243 [00:06<01:04, 3.58it/s]
[2024-01-30 00:51:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.32.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
5%|█████▋ | 13/243 [00:06<01:04, 3.58it/s]
[2024-01-30 00:51:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.32.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
5%|█████▋ | 13/243 [00:06<01:04, 3.58it/s]
6%|██████▌ | 15/243 [00:06<00:49, 4.56it/s]
[2024-01-30 00:51:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.32.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
6%|██████▌ | 15/243 [00:06<00:49, 4.56it/s]
[2024-01-30 00:51:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.32.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
6%|██████▌ | 15/243 [00:06<00:49, 4.56it/s]
[2024-01-30 00:51:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.33.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
6%|██████▌ | 15/243 [00:06<00:49, 4.56it/s]
[2024-01-30 00:51:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.33.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
6%|██████▌ | 15/243 [00:06<00:49, 4.56it/s]
[2024-01-30 00:51:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.33.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
6%|██████▌ | 15/243 [00:06<00:49, 4.56it/s]
7%|███████▉ | 18/243 [00:06<00:36, 6.23it/s]
[2024-01-30 00:51:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.33.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
7%|███████▉ | 18/243 [00:07<00:36, 6.23it/s]
[2024-01-30 00:51:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.33.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
7%|███████▉ | 18/243 [00:07<00:36, 6.23it/s]
8%|████████▎ | 19/243 [00:07<00:47, 4.72it/s]
[2024-01-30 00:51:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.33.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
8%|████████▎ | 19/243 [00:07<00:47, 4.72it/s]
[2024-01-30 00:51:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.33.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
8%|████████▎ | 19/243 [00:07<00:47, 4.72it/s]
[2024-01-30 00:51:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.33.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
8%|████████▎ | 19/243 [00:07<00:47, 4.72it/s]
9%|█████████▏ | 21/243 [00:07<00:40, 5.49it/s]
[2024-01-30 00:51:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.33.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
9%|█████████▏ | 21/243 [00:07<00:40, 5.49it/s]
[2024-01-30 00:51:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.33.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
9%|█████████▏ | 21/243 [00:07<00:40, 5.49it/s]
[2024-01-30 00:51:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.34.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
9%|█████████▏ | 21/243 [00:07<00:40, 5.49it/s]
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.34.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
9%|█████████▏ | 21/243 [00:07<00:40, 5.49it/s]
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.34.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
9%|█████████▏ | 21/243 [00:07<00:40, 5.49it/s]
10%|██████████▌ | 24/243 [00:07<00:31, 6.98it/s]
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.34.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
10%|██████████▌ | 24/243 [00:08<00:31, 6.98it/s]
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.34.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
10%|██████████▌ | 24/243 [00:08<00:31, 6.98it/s]
10%|███████████ | 25/243 [00:08<00:42, 5.13it/s]
[2024-01-30 00:51:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.34.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
10%|███████████ | 25/243 [00:08<00:42, 5.13it/s]
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.34.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
10%|███████████ | 25/243 [00:08<00:42, 5.13it/s]
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.34.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
10%|███████████ | 25/243 [00:08<00:42, 5.13it/s]
11%|███████████▉ | 27/243 [00:08<00:37, 5.82it/s]
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.34.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
11%|███████████▉ | 27/243 [00:08<00:37, 5.82it/s]
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.34.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
11%|███████████▉ | 27/243 [00:08<00:37, 5.82it/s]
[2024-01-30 00:51:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.35.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
11%|███████████▉ | 27/243 [00:08<00:37, 5.82it/s]
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.35.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
11%|███████████▉ | 27/243 [00:08<00:37, 5.82it/s]
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.35.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
11%|███████████▉ | 27/243 [00:08<00:37, 5.82it/s]
12%|█████████████▏ | 30/243 [00:08<00:29, 7.24it/s]
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.35.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
12%|█████████████▏ | 30/243 [00:09<00:29, 7.24it/s]
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.35.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
12%|█████████████▏ | 30/243 [00:09<00:29, 7.24it/s]
13%|█████████████▋ | 31/243 [00:09<00:40, 5.28it/s]
[2024-01-30 00:51:46] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.35.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
13%|█████████████▋ | 31/243 [00:09<00:40, 5.28it/s]
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.35.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
13%|█████████████▋ | 31/243 [00:09<00:40, 5.28it/s]
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.35.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
13%|█████████████▋ | 31/243 [00:09<00:40, 5.28it/s]
14%|██████████████▌ | 33/243 [00:09<00:35, 5.94it/s]
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.35.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
14%|██████████████▌ | 33/243 [00:09<00:35, 5.94it/s]
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.35.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
14%|██████████████▌ | 33/243 [00:09<00:35, 5.94it/s]
[2024-01-30 00:51:46] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.36.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
14%|██████████████▌ | 33/243 [00:09<00:35, 5.94it/s]
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.36.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
14%|██████████████▌ | 33/243 [00:09<00:35, 5.94it/s]
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.36.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
14%|██████████████▌ | 33/243 [00:09<00:35, 5.94it/s]
15%|███████████████▊ | 36/243 [00:09<00:28, 7.36it/s]
[2024-01-30 00:51:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.36.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
15%|███████████████▊ | 36/243 [00:10<00:28, 7.36it/s]
[2024-01-30 00:51:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.36.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
15%|███████████████▊ | 36/243 [00:10<00:28, 7.36it/s]
15%|████████████████▎ | 37/243 [00:10<00:38, 5.34it/s]
[2024-01-30 00:51:47] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.36.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
15%|████████████████▎ | 37/243 [00:10<00:38, 5.34it/s]
[2024-01-30 00:51:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.36.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
15%|████████████████▎ | 37/243 [00:10<00:38, 5.34it/s]
[2024-01-30 00:51:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.36.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
15%|████████████████▎ | 37/243 [00:10<00:38, 5.34it/s]
16%|█████████████████▏ | 39/243 [00:10<00:34, 5.95it/s]
[2024-01-30 00:51:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.36.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
16%|█████████████████▏ | 39/243 [00:10<00:34, 5.95it/s]
[2024-01-30 00:51:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.36.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
16%|█████████████████▏ | 39/243 [00:10<00:34, 5.95it/s]
[2024-01-30 00:51:47] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.37.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
16%|█████████████████▏ | 39/243 [00:10<00:34, 5.95it/s]
[2024-01-30 00:51:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.37.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
16%|█████████████████▏ | 39/243 [00:10<00:34, 5.95it/s]
[2024-01-30 00:51:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.37.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
16%|█████████████████▏ | 39/243 [00:10<00:34, 5.95it/s]
17%|██████████████████▍ | 42/243 [00:10<00:27, 7.36it/s]
[2024-01-30 00:51:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.37.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
17%|██████████████████▍ | 42/243 [00:11<00:27, 7.36it/s]
[2024-01-30 00:51:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.37.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
17%|██████████████████▍ | 42/243 [00:11<00:27, 7.36it/s]
18%|██████████████████▉ | 43/243 [00:11<00:37, 5.36it/s]
[2024-01-30 00:51:48] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.37.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
18%|██████████████████▉ | 43/243 [00:11<00:37, 5.36it/s]
[2024-01-30 00:51:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.37.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
18%|██████████████████▉ | 43/243 [00:11<00:37, 5.36it/s]
[2024-01-30 00:51:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.37.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
18%|██████████████████▉ | 43/243 [00:11<00:37, 5.36it/s]
19%|███████████████████▊ | 45/243 [00:11<00:32, 6.01it/s]
[2024-01-30 00:51:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.37.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
19%|███████████████████▊ | 45/243 [00:11<00:32, 6.01it/s]
[2024-01-30 00:51:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.37.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
19%|███████████████████▊ | 45/243 [00:11<00:32, 6.01it/s]
[2024-01-30 00:51:48] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.38.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
19%|███████████████████▊ | 45/243 [00:11<00:32, 6.01it/s]
[2024-01-30 00:51:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.38.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
19%|███████████████████▊ | 45/243 [00:11<00:32, 6.01it/s]
[2024-01-30 00:51:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.38.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
19%|███████████████████▊ | 45/243 [00:11<00:32, 6.01it/s]
20%|█████████████████████▏ | 48/243 [00:11<00:26, 7.40it/s]
[2024-01-30 00:51:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.38.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
20%|█████████████████████▏ | 48/243 [00:12<00:26, 7.40it/s]
[2024-01-30 00:51:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.38.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
20%|█████████████████████▏ | 48/243 [00:12<00:26, 7.40it/s]
20%|█████████████████████▌ | 49/243 [00:12<00:35, 5.40it/s]
[2024-01-30 00:51:49] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.38.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
20%|█████████████████████▌ | 49/243 [00:12<00:35, 5.40it/s]
[2024-01-30 00:51:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.38.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
20%|█████████████████████▌ | 49/243 [00:12<00:35, 5.40it/s]
[2024-01-30 00:51:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.38.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
20%|█████████████████████▌ | 49/243 [00:12<00:35, 5.40it/s]
21%|██████████████████████▍ | 51/243 [00:12<00:31, 6.06it/s]
[2024-01-30 00:51:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.38.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
21%|██████████████████████▍ | 51/243 [00:12<00:31, 6.06it/s]
[2024-01-30 00:51:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.38.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
21%|██████████████████████▍ | 51/243 [00:12<00:31, 6.06it/s]
[2024-01-30 00:51:49] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.39.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
21%|██████████████████████▍ | 51/243 [00:12<00:31, 6.06it/s]
[2024-01-30 00:51:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.39.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
21%|██████████████████████▍ | 51/243 [00:12<00:31, 6.06it/s]
[2024-01-30 00:51:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.39.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
21%|██████████████████████▍ | 51/243 [00:12<00:31, 6.06it/s]
22%|███████████████████████▊ | 54/243 [00:12<00:25, 7.45it/s]
[2024-01-30 00:51:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.39.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
22%|███████████████████████▊ | 54/243 [00:13<00:25, 7.45it/s]
[2024-01-30 00:51:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.39.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
22%|███████████████████████▊ | 54/243 [00:13<00:25, 7.45it/s]
23%|████████████████████████▏ | 55/243 [00:13<00:34, 5.39it/s]
[2024-01-30 00:51:50] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.39.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
23%|████████████████████████▏ | 55/243 [00:13<00:34, 5.39it/s]
[2024-01-30 00:51:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.39.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
23%|████████████████████████▏ | 55/243 [00:13<00:34, 5.39it/s]
[2024-01-30 00:51:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.39.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
23%|████████████████████████▏ | 55/243 [00:13<00:34, 5.39it/s]
23%|█████████████████████████ | 57/243 [00:13<00:30, 6.02it/s]
[2024-01-30 00:51:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.39.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
23%|█████████████████████████ | 57/243 [00:13<00:30, 6.02it/s]
[2024-01-30 00:51:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.39.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
23%|█████████████████████████ | 57/243 [00:13<00:30, 6.02it/s]
[2024-01-30 00:51:50] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.norm.weight[0m", shape: (5120,), dtype: float16 |
|
23%|█████████████████████████ | 57/243 [00:13<00:30, 6.02it/s]
[2024-01-30 00:51:50] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model-00003-of-00003.bin |
|
23%|█████████████████████████ | 57/243 [00:13<00:30, 6.02it/s]
[2024-01-30 00:51:50] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model-00001-of-00003.bin |
|
23%|█████████████████████████ | 57/243 [00:13<00:30, 6.02it/s]
[2024-01-30 00:51:54] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.embed_tokens.q_weight[0m", shape: (32000, 640), dtype: uint32 |
|
23%|█████████████████████████ | 57/243 [00:17<00:30, 6.02it/s]
[2024-01-30 00:51:54] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.embed_tokens.q_scale[0m", shape: (32000, 160), dtype: float16 |
|
23%|█████████████████████████ | 57/243 [00:17<00:30, 6.02it/s]
25%|██████████████████████████▍ | 60/243 [00:17<01:58, 1.54it/s]
[2024-01-30 00:51:54] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.0.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
25%|██████████████████████████▍ | 60/243 [00:17<01:58, 1.54it/s]
[2024-01-30 00:51:54] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
25%|██████████████████████████▍ | 60/243 [00:17<01:58, 1.54it/s]
[2024-01-30 00:51:54] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
25%|██████████████████████████▍ | 60/243 [00:17<01:58, 1.54it/s]
26%|███████████████████████████▎ | 62/243 [00:17<01:30, 2.01it/s]
[2024-01-30 00:51:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
26%|███████████████████████████▎ | 62/243 [00:18<01:30, 2.01it/s]
[2024-01-30 00:51:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
26%|███████████████████████████▎ | 62/243 [00:18<01:30, 2.01it/s]
26%|███████████████████████████▋ | 63/243 [00:18<01:28, 2.04it/s]
[2024-01-30 00:51:55] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.0.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
26%|███████████████████████████▋ | 63/243 [00:18<01:28, 2.04it/s]
[2024-01-30 00:51:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
26%|███████████████████████████▋ | 63/243 [00:18<01:28, 2.04it/s]
[2024-01-30 00:51:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
26%|███████████████████████████▋ | 63/243 [00:18<01:28, 2.04it/s]
27%|████████████████████████████▌ | 65/243 [00:18<01:06, 2.68it/s]
[2024-01-30 00:51:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
27%|████████████████████████████▌ | 65/243 [00:18<01:06, 2.68it/s]
[2024-01-30 00:51:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
27%|████████████████████████████▌ | 65/243 [00:18<01:06, 2.68it/s]
[2024-01-30 00:51:55] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.1.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
27%|████████████████████████████▌ | 65/243 [00:18<01:06, 2.68it/s]
[2024-01-30 00:51:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
27%|████████████████████████████▌ | 65/243 [00:18<01:06, 2.68it/s]
[2024-01-30 00:51:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
27%|████████████████████████████▌ | 65/243 [00:18<01:06, 2.68it/s]
28%|█████████████████████████████▉ | 68/243 [00:18<00:45, 3.89it/s]
[2024-01-30 00:51:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
28%|█████████████████████████████▉ | 68/243 [00:19<00:45, 3.89it/s]
[2024-01-30 00:51:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
28%|█████████████████████████████▉ | 68/243 [00:19<00:45, 3.89it/s]
28%|██████████████████████████████▍ | 69/243 [00:19<00:50, 3.48it/s]
[2024-01-30 00:51:56] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.1.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
28%|██████████████████████████████▍ | 69/243 [00:19<00:50, 3.48it/s]
[2024-01-30 00:51:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
28%|██████████████████████████████▍ | 69/243 [00:19<00:50, 3.48it/s]
[2024-01-30 00:51:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
28%|██████████████████████████████▍ | 69/243 [00:19<00:50, 3.48it/s]
29%|███████████████████████████████▎ | 71/243 [00:19<00:40, 4.25it/s]
[2024-01-30 00:51:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
29%|███████████████████████████████▎ | 71/243 [00:19<00:40, 4.25it/s]
[2024-01-30 00:51:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
29%|███████████████████████████████▎ | 71/243 [00:19<00:40, 4.25it/s]
[2024-01-30 00:51:56] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.10.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
29%|███████████████████████████████▎ | 71/243 [00:19<00:40, 4.25it/s]
[2024-01-30 00:51:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
29%|███████████████████████████████▎ | 71/243 [00:19<00:40, 4.25it/s]
[2024-01-30 00:51:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
29%|███████████████████████████████▎ | 71/243 [00:19<00:40, 4.25it/s]
30%|████████████████████████████████▌ | 74/243 [00:19<00:29, 5.67it/s]
[2024-01-30 00:51:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
30%|████████████████████████████████▌ | 74/243 [00:20<00:29, 5.67it/s]
[2024-01-30 00:51:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
30%|████████████████████████████████▌ | 74/243 [00:20<00:29, 5.67it/s]
31%|█████████████████████████████████ | 75/243 [00:20<00:37, 4.53it/s]
[2024-01-30 00:51:57] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.10.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
31%|█████████████████████████████████ | 75/243 [00:20<00:37, 4.53it/s]
[2024-01-30 00:51:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
31%|█████████████████████████████████ | 75/243 [00:20<00:37, 4.53it/s]
[2024-01-30 00:51:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
31%|█████████████████████████████████ | 75/243 [00:20<00:37, 4.53it/s]
32%|█████████████████████████████████▉ | 77/243 [00:20<00:31, 5.27it/s]
[2024-01-30 00:51:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
32%|█████████████████████████████████▉ | 77/243 [00:20<00:31, 5.27it/s]
[2024-01-30 00:51:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
32%|█████████████████████████████████▉ | 77/243 [00:20<00:31, 5.27it/s]
[2024-01-30 00:51:57] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.11.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
32%|█████████████████████████████████▉ | 77/243 [00:20<00:31, 5.27it/s]
[2024-01-30 00:51:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
32%|█████████████████████████████████▉ | 77/243 [00:20<00:31, 5.27it/s]
[2024-01-30 00:51:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
32%|█████████████████████████████████▉ | 77/243 [00:20<00:31, 5.27it/s]
33%|███████████████████████████████████▏ | 80/243 [00:20<00:24, 6.69it/s]
[2024-01-30 00:51:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
33%|███████████████████████████████████▏ | 80/243 [00:21<00:24, 6.69it/s]
[2024-01-30 00:51:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
33%|███████████████████████████████████▏ | 80/243 [00:21<00:24, 6.69it/s]
33%|███████████████████████████████████▋ | 81/243 [00:21<00:32, 5.05it/s]
[2024-01-30 00:51:58] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.11.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
33%|███████████████████████████████████▋ | 81/243 [00:21<00:32, 5.05it/s]
[2024-01-30 00:51:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
33%|███████████████████████████████████▋ | 81/243 [00:21<00:32, 5.05it/s]
[2024-01-30 00:51:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
33%|███████████████████████████████████▋ | 81/243 [00:21<00:32, 5.05it/s]
34%|████████████████████████████████████▌ | 83/243 [00:21<00:28, 5.71it/s]
[2024-01-30 00:51:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
34%|████████████████████████████████████▌ | 83/243 [00:21<00:28, 5.71it/s]
[2024-01-30 00:51:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
34%|████████████████████████████████████▌ | 83/243 [00:21<00:28, 5.71it/s]
[2024-01-30 00:51:58] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.12.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
34%|████████████████████████████████████▌ | 83/243 [00:21<00:28, 5.71it/s]
[2024-01-30 00:51:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
34%|████████████████████████████████████▌ | 83/243 [00:21<00:28, 5.71it/s]
[2024-01-30 00:51:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
34%|████████████████████████████████████▌ | 83/243 [00:21<00:28, 5.71it/s]
35%|█████████████████████████████████████▊ | 86/243 [00:21<00:22, 7.11it/s]
[2024-01-30 00:51:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
35%|█████████████████████████████████████▊ | 86/243 [00:22<00:22, 7.11it/s]
[2024-01-30 00:51:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
35%|█████████████████████████████████████▊ | 86/243 [00:22<00:22, 7.11it/s]
36%|██████████████████████████████████████▎ | 87/243 [00:22<00:29, 5.26it/s]
[2024-01-30 00:51:59] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.12.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
36%|██████████████████████████████████████▎ | 87/243 [00:22<00:29, 5.26it/s]
[2024-01-30 00:51:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
36%|██████████████████████████████████████▎ | 87/243 [00:22<00:29, 5.26it/s]
[2024-01-30 00:51:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
36%|██████████████████████████████████████▎ | 87/243 [00:22<00:29, 5.26it/s]
37%|███████████████████████████████████████▏ | 89/243 [00:22<00:25, 5.93it/s]
[2024-01-30 00:51:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
37%|███████████████████████████████████████▏ | 89/243 [00:22<00:25, 5.93it/s]
[2024-01-30 00:51:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
37%|███████████████████████████████████████▏ | 89/243 [00:22<00:25, 5.93it/s]
[2024-01-30 00:51:59] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.13.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
37%|███████████████████████████████████████▏ | 89/243 [00:22<00:25, 5.93it/s]
[2024-01-30 00:51:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
37%|███████████████████████████████████████▏ | 89/243 [00:22<00:25, 5.93it/s]
[2024-01-30 00:51:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
37%|███████████████████████████████████████▏ | 89/243 [00:22<00:25, 5.93it/s]
38%|████████████████████████████████████████▌ | 92/243 [00:22<00:21, 7.17it/s]
[2024-01-30 00:52:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
38%|████████████████████████████████████████▌ | 92/243 [00:23<00:21, 7.17it/s]
[2024-01-30 00:52:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
38%|████████████████████████████████████████▌ | 92/243 [00:23<00:21, 7.17it/s]
38%|████████████████████████████████████████▉ | 93/243 [00:23<00:28, 5.21it/s]
[2024-01-30 00:52:00] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.13.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
38%|████████████████████████████████████████▉ | 93/243 [00:23<00:28, 5.21it/s]
[2024-01-30 00:52:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
38%|████████████████████████████████████████▉ | 93/243 [00:23<00:28, 5.21it/s]
[2024-01-30 00:52:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
38%|████████████████████████████████████████▉ | 93/243 [00:23<00:28, 5.21it/s]
39%|█████████████████████████████████████████▊ | 95/243 [00:23<00:25, 5.90it/s]
[2024-01-30 00:52:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
39%|█████████████████████████████████████████▊ | 95/243 [00:23<00:25, 5.90it/s]
[2024-01-30 00:52:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
39%|█████████████████████████████████████████▊ | 95/243 [00:23<00:25, 5.90it/s]
[2024-01-30 00:52:00] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.14.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
39%|█████████████████████████████████████████▊ | 95/243 [00:23<00:25, 5.90it/s]
[2024-01-30 00:52:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
39%|█████████████████████████████████████████▊ | 95/243 [00:23<00:25, 5.90it/s]
[2024-01-30 00:52:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
39%|█████████████████████████████████████████▊ | 95/243 [00:23<00:25, 5.90it/s]
40%|███████████████████████████████████████████▏ | 98/243 [00:23<00:20, 7.16it/s]
[2024-01-30 00:52:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
40%|███████████████████████████████████████████▏ | 98/243 [00:24<00:20, 7.16it/s]
[2024-01-30 00:52:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
40%|███████████████████████████████████████████▏ | 98/243 [00:24<00:20, 7.16it/s]
41%|███████████████████████████████████████████▌ | 99/243 [00:24<00:28, 5.10it/s]
[2024-01-30 00:52:01] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.14.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
41%|███████████████████████████████████████████▌ | 99/243 [00:24<00:28, 5.10it/s]
[2024-01-30 00:52:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
41%|███████████████████████████████████████████▌ | 99/243 [00:24<00:28, 5.10it/s]
[2024-01-30 00:52:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
41%|███████████████████████████████████████████▌ | 99/243 [00:24<00:28, 5.10it/s]
42%|████████████████████████████████████████████ | 101/243 [00:24<00:25, 5.66it/s]
[2024-01-30 00:52:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
42%|████████████████████████████████████████████ | 101/243 [00:24<00:25, 5.66it/s]
[2024-01-30 00:52:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
42%|████████████████████████████████████████████ | 101/243 [00:24<00:25, 5.66it/s]
[2024-01-30 00:52:01] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model-00002-of-00003.bin |
|
42%|████████████████████████████████████████████ | 101/243 [00:24<00:25, 5.66it/s]
[2024-01-30 00:52:13] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
42%|████████████████████████████████████████████ | 101/243 [00:36<00:25, 5.66it/s]
[2024-01-30 00:52:13] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
42%|████████████████████████████████████████████ | 101/243 [00:36<00:25, 5.66it/s]
42%|████████████████████████████████████████████▉ | 103/243 [00:36<04:42, 2.02s/it]
[2024-01-30 00:52:13] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.2.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
42%|████████████████████████████████████████████▉ | 103/243 [00:36<04:42, 2.02s/it]
[2024-01-30 00:52:13] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
42%|████████████████████████████████████████████▉ | 103/243 [00:36<04:42, 2.02s/it]
[2024-01-30 00:52:13] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
42%|████████████████████████████████████████████▉ | 103/243 [00:36<04:42, 2.02s/it]
43%|█████████████████████████████████████████████▊ | 105/243 [00:36<03:18, 1.44s/it]
[2024-01-30 00:52:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
43%|█████████████████████████████████████████████▊ | 105/243 [00:37<03:18, 1.44s/it]
[2024-01-30 00:52:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
43%|█████████████████████████████████████████████▊ | 105/243 [00:37<03:18, 1.44s/it]
44%|██████████████████████████████████████████████▏ | 106/243 [00:37<02:53, 1.26s/it]
[2024-01-30 00:52:14] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.2.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
44%|██████████████████████████████████████████████▏ | 106/243 [00:37<02:53, 1.26s/it]
[2024-01-30 00:52:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
44%|██████████████████████████████████████████████▏ | 106/243 [00:37<02:53, 1.26s/it]
[2024-01-30 00:52:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
44%|██████████████████████████████████████████████▏ | 106/243 [00:37<02:53, 1.26s/it]
44%|███████████████████████████████████████████████ | 108/243 [00:37<01:58, 1.14it/s]
[2024-01-30 00:52:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
44%|███████████████████████████████████████████████ | 108/243 [00:37<01:58, 1.14it/s]
[2024-01-30 00:52:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
44%|███████████████████████████████████████████████ | 108/243 [00:37<01:58, 1.14it/s]
[2024-01-30 00:52:14] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.3.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
44%|███████████████████████████████████████████████ | 108/243 [00:37<01:58, 1.14it/s]
[2024-01-30 00:52:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
44%|███████████████████████████████████████████████ | 108/243 [00:37<01:58, 1.14it/s]
[2024-01-30 00:52:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
44%|███████████████████████████████████████████████ | 108/243 [00:37<01:58, 1.14it/s]
46%|████████████████████████████████████████████████▍ | 111/243 [00:37<01:12, 1.82it/s]
[2024-01-30 00:52:15] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
46%|████████████████████████████████████████████████▍ | 111/243 [00:38<01:12, 1.82it/s]
[2024-01-30 00:52:15] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
46%|████████████████████████████████████████████████▍ | 111/243 [00:38<01:12, 1.82it/s]
46%|████████████████████████████████████████████████▊ | 112/243 [00:38<01:10, 1.85it/s]
[2024-01-30 00:52:15] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.3.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
46%|████████████████████████████████████████████████▊ | 112/243 [00:38<01:10, 1.85it/s]
[2024-01-30 00:52:15] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
46%|████████████████████████████████████████████████▊ | 112/243 [00:38<01:10, 1.85it/s]
[2024-01-30 00:52:15] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
46%|████████████████████████████████████████████████▊ | 112/243 [00:38<01:10, 1.85it/s]
47%|█████████████████████████████████████████████████▋ | 114/243 [00:38<00:52, 2.47it/s]
[2024-01-30 00:52:15] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
47%|█████████████████████████████████████████████████▋ | 114/243 [00:38<00:52, 2.47it/s]
[2024-01-30 00:52:15] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
47%|█████████████████████████████████████████████████▋ | 114/243 [00:38<00:52, 2.47it/s]
[2024-01-30 00:52:15] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.4.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
47%|█████████████████████████████████████████████████▋ | 114/243 [00:38<00:52, 2.47it/s]
[2024-01-30 00:52:15] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
47%|█████████████████████████████████████████████████▋ | 114/243 [00:38<00:52, 2.47it/s]
[2024-01-30 00:52:15] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
47%|█████████████████████████████████████████████████▋ | 114/243 [00:38<00:52, 2.47it/s]
48%|███████████████████████████████████████████████████ | 117/243 [00:38<00:34, 3.61it/s]
[2024-01-30 00:52:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
48%|███████████████████████████████████████████████████ | 117/243 [00:39<00:34, 3.61it/s]
[2024-01-30 00:52:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
48%|███████████████████████████████████████████████████ | 117/243 [00:39<00:34, 3.61it/s]
49%|███████████████████████████████████████████████████▍ | 118/243 [00:39<00:38, 3.26it/s]
[2024-01-30 00:52:16] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.4.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
49%|███████████████████████████████████████████████████▍ | 118/243 [00:39<00:38, 3.26it/s]
[2024-01-30 00:52:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
49%|███████████████████████████████████████████████████▍ | 118/243 [00:39<00:38, 3.26it/s]
[2024-01-30 00:52:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
49%|███████████████████████████████████████████████████▍ | 118/243 [00:39<00:38, 3.26it/s]
49%|████████████████████████████████████████████████████▎ | 120/243 [00:39<00:30, 4.01it/s]
[2024-01-30 00:52:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
49%|████████████████████████████████████████████████████▎ | 120/243 [00:39<00:30, 4.01it/s]
[2024-01-30 00:52:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
49%|████████████████████████████████████████████████████▎ | 120/243 [00:39<00:30, 4.01it/s]
[2024-01-30 00:52:16] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.5.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
49%|████████████████████████████████████████████████████▎ | 120/243 [00:39<00:30, 4.01it/s]
[2024-01-30 00:52:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
49%|████████████████████████████████████████████████████▎ | 120/243 [00:39<00:30, 4.01it/s]
[2024-01-30 00:52:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
49%|████████████████████████████████████████████████████▎ | 120/243 [00:39<00:30, 4.01it/s]
51%|█████████████████████████████████████████████████████▋ | 123/243 [00:39<00:22, 5.41it/s]
[2024-01-30 00:52:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
51%|█████████████████████████████████████████████████████▋ | 123/243 [00:40<00:22, 5.41it/s]
[2024-01-30 00:52:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
51%|█████████████████████████████████████████████████████▋ | 123/243 [00:40<00:22, 5.41it/s]
51%|██████████████████████████████████████████████████████ | 124/243 [00:40<00:27, 4.37it/s]
[2024-01-30 00:52:17] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.5.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
51%|██████████████████████████████████████████████████████ | 124/243 [00:40<00:27, 4.37it/s]
[2024-01-30 00:52:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
51%|██████████████████████████████████████████████████████ | 124/243 [00:40<00:27, 4.37it/s]
[2024-01-30 00:52:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
51%|██████████████████████████████████████████████████████ | 124/243 [00:40<00:27, 4.37it/s]
52%|██████████████████████████████████████████████████████▉ | 126/243 [00:40<00:22, 5.09it/s]
[2024-01-30 00:52:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
52%|██████████████████████████████████████████████████████▉ | 126/243 [00:40<00:22, 5.09it/s]
[2024-01-30 00:52:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
52%|██████████████████████████████████████████████████████▉ | 126/243 [00:40<00:22, 5.09it/s]
[2024-01-30 00:52:17] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.6.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
52%|██████████████████████████████████████████████████████▉ | 126/243 [00:40<00:22, 5.09it/s]
[2024-01-30 00:52:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
52%|██████████████████████████████████████████████████████▉ | 126/243 [00:40<00:22, 5.09it/s]
[2024-01-30 00:52:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
52%|██████████████████████████████████████████████████████▉ | 126/243 [00:40<00:22, 5.09it/s]
53%|████████████████████████████████████████████████████████▎ | 129/243 [00:40<00:17, 6.49it/s]
[2024-01-30 00:52:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
53%|████████████████████████████████████████████████████████▎ | 129/243 [00:41<00:17, 6.49it/s]
[2024-01-30 00:52:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
53%|████████████████████████████████████████████████████████▎ | 129/243 [00:41<00:17, 6.49it/s]
53%|████████████████████████████████████████████████████████▋ | 130/243 [00:41<00:22, 4.92it/s]
[2024-01-30 00:52:18] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.6.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
53%|████████████████████████████████████████████████████████▋ | 130/243 [00:41<00:22, 4.92it/s]
[2024-01-30 00:52:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
53%|████████████████████████████████████████████████████████▋ | 130/243 [00:41<00:22, 4.92it/s]
[2024-01-30 00:52:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
53%|████████████████████████████████████████████████████████▋ | 130/243 [00:41<00:22, 4.92it/s]
54%|█████████████████████████████████████████████████████████▌ | 132/243 [00:41<00:19, 5.61it/s]
[2024-01-30 00:52:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
54%|█████████████████████████████████████████████████████████▌ | 132/243 [00:41<00:19, 5.61it/s]
[2024-01-30 00:52:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
54%|█████████████████████████████████████████████████████████▌ | 132/243 [00:41<00:19, 5.61it/s]
[2024-01-30 00:52:18] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.7.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
54%|█████████████████████████████████████████████████████████▌ | 132/243 [00:41<00:19, 5.61it/s]
[2024-01-30 00:52:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
54%|█████████████████████████████████████████████████████████▌ | 132/243 [00:41<00:19, 5.61it/s]
[2024-01-30 00:52:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
54%|█████████████████████████████████████████████████████████▌ | 132/243 [00:41<00:19, 5.61it/s]
56%|██████████████████████████████████████████████████████████▉ | 135/243 [00:41<00:15, 6.99it/s]
[2024-01-30 00:52:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
56%|██████████████████████████████████████████████████████████▉ | 135/243 [00:42<00:15, 6.99it/s]
[2024-01-30 00:52:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
56%|██████████████████████████████████████████████████████████▉ | 135/243 [00:42<00:15, 6.99it/s]
56%|███████████████████████████████████████████████████████████▎ | 136/243 [00:42<00:20, 5.16it/s]
[2024-01-30 00:52:19] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.7.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
56%|███████████████████████████████████████████████████████████▎ | 136/243 [00:42<00:20, 5.16it/s]
[2024-01-30 00:52:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
56%|███████████████████████████████████████████████████████████▎ | 136/243 [00:42<00:20, 5.16it/s]
[2024-01-30 00:52:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
56%|███████████████████████████████████████████████████████████▎ | 136/243 [00:42<00:20, 5.16it/s]
57%|████████████████████████████████████████████████████████████▏ | 138/243 [00:42<00:18, 5.83it/s]
[2024-01-30 00:52:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
57%|████████████████████████████████████████████████████████████▏ | 138/243 [00:42<00:18, 5.83it/s]
[2024-01-30 00:52:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
57%|████████████████████████████████████████████████████████████▏ | 138/243 [00:42<00:18, 5.83it/s]
[2024-01-30 00:52:19] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.8.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
57%|████████████████████████████████████████████████████████████▏ | 138/243 [00:42<00:18, 5.83it/s]
[2024-01-30 00:52:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
57%|████████████████████████████████████████████████████████████▏ | 138/243 [00:42<00:18, 5.83it/s]
[2024-01-30 00:52:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
57%|████████████████████████████████████████████████████████████▏ | 138/243 [00:42<00:18, 5.83it/s]
58%|█████████████████████████████████████████████████████████████▌ | 141/243 [00:42<00:14, 7.19it/s]
[2024-01-30 00:52:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
58%|█████████████████████████████████████████████████████████████▌ | 141/243 [00:43<00:14, 7.19it/s]
[2024-01-30 00:52:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
58%|█████████████████████████████████████████████████████████████▌ | 141/243 [00:43<00:14, 7.19it/s]
58%|█████████████████████████████████████████████████████████████▉ | 142/243 [00:43<00:19, 5.25it/s]
[2024-01-30 00:52:20] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.8.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
58%|█████████████████████████████████████████████████████████████▉ | 142/243 [00:43<00:19, 5.25it/s]
[2024-01-30 00:52:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
58%|█████████████████████████████████████████████████████████████▉ | 142/243 [00:43<00:19, 5.25it/s]
[2024-01-30 00:52:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
58%|█████████████████████████████████████████████████████████████▉ | 142/243 [00:43<00:19, 5.25it/s]
59%|██████████████████████████████████████████████████████████████▊ | 144/243 [00:43<00:16, 5.90it/s]
[2024-01-30 00:52:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
59%|██████████████████████████████████████████████████████████████▊ | 144/243 [00:43<00:16, 5.90it/s]
[2024-01-30 00:52:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
59%|██████████████████████████████████████████████████████████████▊ | 144/243 [00:43<00:16, 5.90it/s]
[2024-01-30 00:52:20] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.9.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
59%|██████████████████████████████████████████████████████████████▊ | 144/243 [00:43<00:16, 5.90it/s]
[2024-01-30 00:52:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
59%|██████████████████████████████████████████████████████████████▊ | 144/243 [00:43<00:16, 5.90it/s]
[2024-01-30 00:52:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
59%|██████████████████████████████████████████████████████████████▊ | 144/243 [00:43<00:16, 5.90it/s]
60%|████████████████████████████████████████████████████████████████ | 147/243 [00:43<00:13, 7.11it/s]
[2024-01-30 00:52:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
60%|████████████████████████████████████████████████████████████████ | 147/243 [00:44<00:13, 7.11it/s]
[2024-01-30 00:52:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
60%|████████████████████████████████████████████████████████████████ | 147/243 [00:44<00:13, 7.11it/s]
61%|████████████████████████████████████████████████████████████████▌ | 148/243 [00:44<00:18, 5.13it/s]
[2024-01-30 00:52:21] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.9.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
61%|████████████████████████████████████████████████████████████████▌ | 148/243 [00:44<00:18, 5.13it/s]
[2024-01-30 00:52:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
61%|████████████████████████████████████████████████████████████████▌ | 148/243 [00:44<00:18, 5.13it/s]
[2024-01-30 00:52:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
61%|████████████████████████████████████████████████████████████████▌ | 148/243 [00:44<00:18, 5.13it/s]
62%|█████████████████████████████████████████████████████████████████▍ | 150/243 [00:44<00:16, 5.68it/s]
[2024-01-30 00:52:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
62%|█████████████████████████████████████████████████████████████████▍ | 150/243 [00:44<00:16, 5.68it/s]
[2024-01-30 00:52:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
62%|█████████████████████████████████████████████████████████████████▍ | 150/243 [00:44<00:16, 5.68it/s]
[2024-01-30 00:52:21] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.15.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
62%|█████████████████████████████████████████████████████████████████▍ | 150/243 [00:44<00:16, 5.68it/s]
[2024-01-30 00:52:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
62%|█████████████████████████████████████████████████████████████████▍ | 150/243 [00:44<00:16, 5.68it/s]
[2024-01-30 00:52:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
62%|█████████████████████████████████████████████████████████████████▍ | 150/243 [00:44<00:16, 5.68it/s]
63%|██████████████████████████████████████████████████████████████████▋ | 153/243 [00:44<00:13, 6.64it/s]
[2024-01-30 00:52:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
63%|██████████████████████████████████████████████████████████████████▋ | 153/243 [00:45<00:13, 6.64it/s]
[2024-01-30 00:52:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
63%|██████████████████████████████████████████████████████████████████▋ | 153/243 [00:45<00:13, 6.64it/s]
63%|███████████████████████████████████████████████████████████████████▏ | 154/243 [00:45<00:19, 4.56it/s]
[2024-01-30 00:52:22] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.15.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
63%|███████████████████████████████████████████████████████████████████▏ | 154/243 [00:45<00:19, 4.56it/s]
[2024-01-30 00:52:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
63%|███████████████████████████████████████████████████████████████████▏ | 154/243 [00:45<00:19, 4.56it/s]
[2024-01-30 00:52:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
63%|███████████████████████████████████████████████████████████████████▏ | 154/243 [00:45<00:19, 4.56it/s]
64%|████████████████████████████████████████████████████████████████████ | 156/243 [00:45<00:14, 5.97it/s]
[2024-01-30 00:52:22] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.16.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
64%|████████████████████████████████████████████████████████████████████ | 156/243 [00:45<00:14, 5.97it/s]
[2024-01-30 00:52:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
64%|████████████████████████████████████████████████████████████████████ | 156/243 [00:45<00:14, 5.97it/s]
[2024-01-30 00:52:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
64%|████████████████████████████████████████████████████████████████████ | 156/243 [00:45<00:14, 5.97it/s]
65%|████████████████████████████████████████████████████████████████████▉ | 158/243 [00:45<00:13, 6.41it/s]
[2024-01-30 00:52:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
65%|████████████████████████████████████████████████████████████████████▉ | 158/243 [00:46<00:13, 6.41it/s]
[2024-01-30 00:52:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
65%|████████████████████████████████████████████████████████████████████▉ | 158/243 [00:46<00:13, 6.41it/s]
65%|█████████████████████████████████████████████████████████████████████▎ | 159/243 [00:46<00:19, 4.23it/s]
[2024-01-30 00:52:23] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.16.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
65%|█████████████████████████████████████████████████████████████████████▎ | 159/243 [00:46<00:19, 4.23it/s]
[2024-01-30 00:52:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
65%|█████████████████████████████████████████████████████████████████████▎ | 159/243 [00:46<00:19, 4.23it/s]
[2024-01-30 00:52:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
65%|█████████████████████████████████████████████████████████████████████▎ | 159/243 [00:46<00:19, 4.23it/s]
66%|██████████████████████████████████████████████████████████████████████▏ | 161/243 [00:46<00:17, 4.74it/s]
[2024-01-30 00:52:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
66%|██████████████████████████████████████████████████████████████████████▏ | 161/243 [00:46<00:17, 4.74it/s]
[2024-01-30 00:52:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
66%|██████████████████████████████████████████████████████████████████████▏ | 161/243 [00:46<00:17, 4.74it/s]
67%|██████████████████████████████████████████████████████████████████████▋ | 162/243 [00:46<00:15, 5.25it/s]
[2024-01-30 00:52:23] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.17.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
67%|██████████████████████████████████████████████████████████████████████▋ | 162/243 [00:46<00:15, 5.25it/s]
[2024-01-30 00:52:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
67%|██████████████████████████████████████████████████████████████████████▋ | 162/243 [00:47<00:15, 5.25it/s]
[2024-01-30 00:52:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
67%|██████████████████████████████████████████████████████████████████████▋ | 162/243 [00:47<00:15, 5.25it/s]
67%|███████████████████████████████████████████████████████████████████████▌ | 164/243 [00:47<00:13, 5.93it/s]
[2024-01-30 00:52:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
67%|███████████████████████████████████████████████████████████████████████▌ | 164/243 [00:47<00:13, 5.93it/s]
[2024-01-30 00:52:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
67%|███████████████████████████████████████████████████████████████████████▌ | 164/243 [00:47<00:13, 5.93it/s]
68%|███████████████████████████████████████████████████████████████████████▉ | 165/243 [00:47<00:19, 3.91it/s]
[2024-01-30 00:52:24] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.17.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
68%|███████████████████████████████████████████████████████████████████████▉ | 165/243 [00:47<00:19, 3.91it/s]
[2024-01-30 00:52:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
68%|███████████████████████████████████████████████████████████████████████▉ | 165/243 [00:48<00:19, 3.91it/s]
[2024-01-30 00:52:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
68%|███████████████████████████████████████████████████████████████████████▉ | 165/243 [00:48<00:19, 3.91it/s]
69%|████████████████████████████████████████████████████████████████████████▊ | 167/243 [00:48<00:16, 4.52it/s]
[2024-01-30 00:52:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
69%|████████████████████████████████████████████████████████████████████████▊ | 167/243 [00:48<00:16, 4.52it/s]
[2024-01-30 00:52:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
69%|████████████████████████████████████████████████████████████████████████▊ | 167/243 [00:48<00:16, 4.52it/s]
69%|█████████████████████████████████████████████████████████████████████████▎ | 168/243 [00:48<00:14, 5.08it/s]
[2024-01-30 00:52:25] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.18.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
69%|█████████████████████████████████████████████████████████████████████████▎ | 168/243 [00:48<00:14, 5.08it/s]
[2024-01-30 00:52:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
69%|█████████████████████████████████████████████████████████████████████████▎ | 168/243 [00:48<00:14, 5.08it/s]
[2024-01-30 00:52:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
69%|█████████████████████████████████████████████████████████████████████████▎ | 168/243 [00:48<00:14, 5.08it/s]
70%|██████████████████████████████████████████████████████████████████████████▏ | 170/243 [00:48<00:12, 5.82it/s]
[2024-01-30 00:52:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
70%|██████████████████████████████████████████████████████████████████████████▏ | 170/243 [00:48<00:12, 5.82it/s]
[2024-01-30 00:52:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
70%|██████████████████████████████████████████████████████████████████████████▏ | 170/243 [00:48<00:12, 5.82it/s]
70%|██████████████████████████████████████████████████████████████████████████▌ | 171/243 [00:48<00:18, 3.83it/s]
[2024-01-30 00:52:26] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.18.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
70%|██████████████████████████████████████████████████████████████████████████▌ | 171/243 [00:48<00:18, 3.83it/s]
[2024-01-30 00:52:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
70%|██████████████████████████████████████████████████████████████████████████▌ | 171/243 [00:49<00:18, 3.83it/s]
[2024-01-30 00:52:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
70%|██████████████████████████████████████████████████████████████████████████▌ | 171/243 [00:49<00:18, 3.83it/s]
71%|███████████████████████████████████████████████████████████████████████████▍ | 173/243 [00:49<00:15, 4.46it/s]
[2024-01-30 00:52:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
71%|███████████████████████████████████████████████████████████████████████████▍ | 173/243 [00:49<00:15, 4.46it/s]
[2024-01-30 00:52:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
71%|███████████████████████████████████████████████████████████████████████████▍ | 173/243 [00:49<00:15, 4.46it/s]
72%|███████████████████████████████████████████████████████████████████████████▉ | 174/243 [00:49<00:13, 5.03it/s]
[2024-01-30 00:52:26] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.19.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
72%|███████████████████████████████████████████████████████████████████████████▉ | 174/243 [00:49<00:13, 5.03it/s]
[2024-01-30 00:52:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
72%|███████████████████████████████████████████████████████████████████████████▉ | 174/243 [00:49<00:13, 5.03it/s]
[2024-01-30 00:52:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
72%|███████████████████████████████████████████████████████████████████████████▉ | 174/243 [00:49<00:13, 5.03it/s]
72%|████████████████████████████████████████████████████████████████████████████▊ | 176/243 [00:49<00:11, 5.80it/s]
[2024-01-30 00:52:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
72%|████████████████████████████████████████████████████████████████████████████▊ | 176/243 [00:50<00:11, 5.80it/s]
[2024-01-30 00:52:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
72%|████████████████████████████████████████████████████████████████████████████▊ | 176/243 [00:50<00:11, 5.80it/s]
73%|█████████████████████████████████████████████████████████████████████████████▏ | 177/243 [00:50<00:17, 3.81it/s]
[2024-01-30 00:52:27] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.19.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
73%|█████████████████████████████████████████████████████████████████████████████▏ | 177/243 [00:50<00:17, 3.81it/s]
[2024-01-30 00:52:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
73%|█████████████████████████████████████████████████████████████████████████████▏ | 177/243 [00:50<00:17, 3.81it/s]
[2024-01-30 00:52:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
73%|█████████████████████████████████████████████████████████████████████████████▏ | 177/243 [00:50<00:17, 3.81it/s]
74%|██████████████████████████████████████████████████████████████████████████████ | 179/243 [00:50<00:14, 4.45it/s]
[2024-01-30 00:52:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
74%|██████████████████████████████████████████████████████████████████████████████ | 179/243 [00:50<00:14, 4.45it/s]
[2024-01-30 00:52:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
74%|██████████████████████████████████████████████████████████████████████████████ | 179/243 [00:50<00:14, 4.45it/s]
74%|██████████████████████████████████████████████████████████████████████████████▌ | 180/243 [00:50<00:12, 5.02it/s]
[2024-01-30 00:52:27] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.20.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
74%|██████████████████████████████████████████████████████████████████████████████▌ | 180/243 [00:50<00:12, 5.02it/s]
[2024-01-30 00:52:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
74%|██████████████████████████████████████████████████████████████████████████████▌ | 180/243 [00:50<00:12, 5.02it/s]
[2024-01-30 00:52:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
74%|██████████████████████████████████████████████████████████████████████████████▌ | 180/243 [00:50<00:12, 5.02it/s]
75%|███████████████████████████████████████████████████████████████████████████████▍ | 182/243 [00:50<00:10, 5.80it/s]
[2024-01-30 00:52:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
75%|███████████████████████████████████████████████████████████████████████████████▍ | 182/243 [00:51<00:10, 5.80it/s]
[2024-01-30 00:52:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
75%|███████████████████████████████████████████████████████████████████████████████▍ | 182/243 [00:51<00:10, 5.80it/s]
75%|███████████████████████████████████████████████████████████████████████████████▊ | 183/243 [00:51<00:15, 3.80it/s]
[2024-01-30 00:52:28] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.20.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
75%|███████████████████████████████████████████████████████████████████████████████▊ | 183/243 [00:51<00:15, 3.80it/s]
[2024-01-30 00:52:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
75%|███████████████████████████████████████████████████████████████████████████████▊ | 183/243 [00:51<00:15, 3.80it/s]
[2024-01-30 00:52:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
75%|███████████████████████████████████████████████████████████████████████████████▊ | 183/243 [00:51<00:15, 3.80it/s]
76%|████████████████████████████████████████████████████████████████████████████████▋ | 185/243 [00:51<00:13, 4.44it/s]
[2024-01-30 00:52:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
76%|████████████████████████████████████████████████████████████████████████████████▋ | 185/243 [00:51<00:13, 4.44it/s]
[2024-01-30 00:52:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
76%|████████████████████████████████████████████████████████████████████████████████▋ | 185/243 [00:51<00:13, 4.44it/s]
77%|█████████████████████████████████████████████████████████████████████████████████▏ | 186/243 [00:51<00:11, 5.01it/s]
[2024-01-30 00:52:29] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.21.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
77%|█████████████████████████████████████████████████████████████████████████████████▏ | 186/243 [00:51<00:11, 5.01it/s]
[2024-01-30 00:52:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
77%|█████████████████████████████████████████████████████████████████████████████████▏ | 186/243 [00:52<00:11, 5.01it/s]
[2024-01-30 00:52:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
77%|█████████████████████████████████████████████████████████████████████████████████▏ | 186/243 [00:52<00:11, 5.01it/s]
77%|██████████████████████████████████████████████████████████████████████████████████ | 188/243 [00:52<00:09, 5.80it/s]
[2024-01-30 00:52:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
77%|██████████████████████████████████████████████████████████████████████████████████ | 188/243 [00:52<00:09, 5.80it/s]
[2024-01-30 00:52:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
77%|██████████████████████████████████████████████████████████████████████████████████ | 188/243 [00:52<00:09, 5.80it/s]
78%|██████████████████████████████████████████████████████████████████████████████████▍ | 189/243 [00:52<00:14, 3.82it/s]
[2024-01-30 00:52:29] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.21.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
78%|██████████████████████████████████████████████████████████████████████████████████▍ | 189/243 [00:52<00:14, 3.82it/s]
[2024-01-30 00:52:30] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
78%|██████████████████████████████████████████████████████████████████████████████████▍ | 189/243 [00:53<00:14, 3.82it/s]
[2024-01-30 00:52:30] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
78%|██████████████████████████████████████████████████████████████████████████████████▍ | 189/243 [00:53<00:14, 3.82it/s]
79%|███████████████████████████████████████████████████████████████████████████████████▎ | 191/243 [00:53<00:11, 4.48it/s]
[2024-01-30 00:52:30] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
79%|███████████████████████████████████████████████████████████████████████████████████▎ | 191/243 [00:53<00:11, 4.48it/s]
[2024-01-30 00:52:30] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
79%|███████████████████████████████████████████████████████████████████████████████████▎ | 191/243 [00:53<00:11, 4.48it/s]
79%|███████████████████████████████████████████████████████████████████████████████████▊ | 192/243 [00:53<00:10, 5.04it/s]
[2024-01-30 00:52:30] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.22.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
79%|███████████████████████████████████████████████████████████████████████████████████▊ | 192/243 [00:53<00:10, 5.04it/s]
[2024-01-30 00:52:30] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.22.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
79%|███████████████████████████████████████████████████████████████████████████████████▊ | 192/243 [00:53<00:10, 5.04it/s]
[2024-01-30 00:52:30] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.22.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
79%|███████████████████████████████████████████████████████████████████████████████████▊ | 192/243 [00:53<00:10, 5.04it/s]
80%|████████████████████████████████████████████████████████████████████████████████████▋ | 194/243 [00:53<00:08, 5.81it/s]
[2024-01-30 00:52:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.22.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
80%|████████████████████████████████████████████████████████████████████████████████████▋ | 194/243 [00:54<00:08, 5.81it/s]
[2024-01-30 00:52:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.22.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
80%|████████████████████████████████████████████████████████████████████████████████████▋ | 194/243 [00:54<00:08, 5.81it/s]
80%|█████████████████████████████████████████████████████████████████████████████████████ | 195/243 [00:54<00:12, 3.83it/s]
[2024-01-30 00:52:31] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.22.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
80%|█████████████████████████████████████████████████████████████████████████████████████ | 195/243 [00:54<00:12, 3.83it/s]
[2024-01-30 00:52:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
80%|█████████████████████████████████████████████████████████████████████████████████████ | 195/243 [00:54<00:12, 3.83it/s]
[2024-01-30 00:52:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
80%|█████████████████████████████████████████████████████████████████████████████████████ | 195/243 [00:54<00:12, 3.83it/s]
81%|█████████████████████████████████████████████████████████████████████████████████████▉ | 197/243 [00:54<00:10, 4.47it/s]
[2024-01-30 00:52:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
81%|█████████████████████████████████████████████████████████████████████████████████████▉ | 197/243 [00:54<00:10, 4.47it/s]
[2024-01-30 00:52:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
81%|█████████████████████████████████████████████████████████████████████████████████████▉ | 197/243 [00:54<00:10, 4.47it/s]
81%|██████████████████████████████████████████████████████████████████████████████████████▎ | 198/243 [00:54<00:08, 5.04it/s]
[2024-01-30 00:52:31] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.23.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
81%|██████████████████████████████████████████████████████████████████████████████████████▎ | 198/243 [00:54<00:08, 5.04it/s]
[2024-01-30 00:52:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.23.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
81%|██████████████████████████████████████████████████████████████████████████████████████▎ | 198/243 [00:54<00:08, 5.04it/s]
[2024-01-30 00:52:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.23.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
81%|██████████████████████████████████████████████████████████████████████████████████████▎ | 198/243 [00:54<00:08, 5.04it/s]
82%|███████████████████████████████████████████████████████████████████████████████████████▏ | 200/243 [00:54<00:07, 5.82it/s]
[2024-01-30 00:52:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.23.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
82%|███████████████████████████████████████████████████████████████████████████████████████▏ | 200/243 [00:55<00:07, 5.82it/s]
[2024-01-30 00:52:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.23.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
82%|███████████████████████████████████████████████████████████████████████████████████████▏ | 200/243 [00:55<00:07, 5.82it/s]
83%|███████████████████████████████████████████████████████████████████████████████████████▋ | 201/243 [00:55<00:10, 3.82it/s]
[2024-01-30 00:52:32] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.23.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
83%|███████████████████████████████████████████████████████████████████████████████████████▋ | 201/243 [00:55<00:10, 3.82it/s]
[2024-01-30 00:52:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
83%|███████████████████████████████████████████████████████████████████████████████████████▋ | 201/243 [00:55<00:10, 3.82it/s]
[2024-01-30 00:52:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
83%|███████████████████████████████████████████████████████████████████████████████████████▋ | 201/243 [00:55<00:10, 3.82it/s]
84%|████████████████████████████████████████████████████████████████████████████████████████▌ | 203/243 [00:55<00:08, 4.47it/s]
[2024-01-30 00:52:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
84%|████████████████████████████████████████████████████████████████████████████████████████▌ | 203/243 [00:55<00:08, 4.47it/s]
[2024-01-30 00:52:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
84%|████████████████████████████████████████████████████████████████████████████████████████▌ | 203/243 [00:55<00:08, 4.47it/s]
84%|████████████████████████████████████████████████████████████████████████████████████████▉ | 204/243 [00:55<00:07, 5.04it/s]
[2024-01-30 00:52:32] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.24.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
84%|████████████████████████████████████████████████████████████████████████████████████████▉ | 204/243 [00:55<00:07, 5.04it/s]
[2024-01-30 00:52:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.24.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
84%|████████████████████████████████████████████████████████████████████████████████████████▉ | 204/243 [00:56<00:07, 5.04it/s]
[2024-01-30 00:52:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.24.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
84%|████████████████████████████████████████████████████████████████████████████████████████▉ | 204/243 [00:56<00:07, 5.04it/s]
85%|█████████████████████████████████████████████████████████████████████████████████████████▊ | 206/243 [00:56<00:06, 5.84it/s]
[2024-01-30 00:52:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.24.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
85%|█████████████████████████████████████████████████████████████████████████████████████████▊ | 206/243 [00:56<00:06, 5.84it/s]
[2024-01-30 00:52:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.24.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
85%|█████████████████████████████████████████████████████████████████████████████████████████▊ | 206/243 [00:56<00:06, 5.84it/s]
85%|██████████████████████████████████████████████████████████████████████████████████████████▎ | 207/243 [00:56<00:09, 3.81it/s]
[2024-01-30 00:52:33] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.24.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
85%|██████████████████████████████████████████████████████████████████████████████████████████▎ | 207/243 [00:56<00:09, 3.81it/s]
[2024-01-30 00:52:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.24.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
85%|██████████████████████████████████████████████████████████████████████████████████████████▎ | 207/243 [00:56<00:09, 3.81it/s]
[2024-01-30 00:52:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.24.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
85%|██████████████████████████████████████████████████████████████████████████████████████████▎ | 207/243 [00:56<00:09, 3.81it/s]
86%|███████████████████████████████████████████████████████████████████████████████████████████▏ | 209/243 [00:56<00:07, 4.45it/s]
[2024-01-30 00:52:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.24.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
86%|███████████████████████████████████████████████████████████████████████████████████████████▏ | 209/243 [00:57<00:07, 4.45it/s]
[2024-01-30 00:52:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.24.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
86%|███████████████████████████████████████████████████████████████████████████████████████████▏ | 209/243 [00:57<00:07, 4.45it/s]
86%|███████████████████████████████████████████████████████████████████████████████████████████▌ | 210/243 [00:57<00:06, 5.02it/s]
[2024-01-30 00:52:34] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.25.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
86%|███████████████████████████████████████████████████████████████████████████████████████████▌ | 210/243 [00:57<00:06, 5.02it/s]
[2024-01-30 00:52:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.25.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
86%|███████████████████████████████████████████████████████████████████████████████████████████▌ | 210/243 [00:57<00:06, 5.02it/s]
[2024-01-30 00:52:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.25.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
86%|███████████████████████████████████████████████████████████████████████████████████████████▌ | 210/243 [00:57<00:06, 5.02it/s]
87%|████████████████████████████████████████████████████████████████████████████████████████████▍ | 212/243 [00:57<00:05, 5.81it/s]
[2024-01-30 00:52:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.25.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
87%|████████████████████████████████████████████████████████████████████████████████████████████▍ | 212/243 [00:57<00:05, 5.81it/s]
[2024-01-30 00:52:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.25.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
87%|████████████████████████████████████████████████████████████████████████████████████████████▍ | 212/243 [00:57<00:05, 5.81it/s]
88%|████████████████████████████████████████████████████████████████████████████████████████████▉ | 213/243 [00:57<00:07, 3.81it/s]
[2024-01-30 00:52:35] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.25.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
88%|████████████████████████████████████████████████████████████████████████████████████████████▉ | 213/243 [00:57<00:07, 3.81it/s]
[2024-01-30 00:52:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.25.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
88%|████████████████████████████████████████████████████████████████████████████████████████████▉ | 213/243 [00:58<00:07, 3.81it/s]
[2024-01-30 00:52:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.25.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
88%|████████████████████████████████████████████████████████████████████████████████████████████▉ | 213/243 [00:58<00:07, 3.81it/s]
88%|█████████████████████████████████████████████████████████████████████████████████████████████▊ | 215/243 [00:58<00:06, 4.44it/s]
[2024-01-30 00:52:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.25.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
88%|█████████████████████████████████████████████████████████████████████████████████████████████▊ | 215/243 [00:58<00:06, 4.44it/s]
[2024-01-30 00:52:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.25.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
88%|█████████████████████████████████████████████████████████████████████████████████████████████▊ | 215/243 [00:58<00:06, 4.44it/s]
89%|██████████████████████████████████████████████████████████████████████████████████████████████▏ | 216/243 [00:58<00:05, 5.01it/s]
[2024-01-30 00:52:35] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.26.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
89%|██████████████████████████████████████████████████████████████████████████████████████████████▏ | 216/243 [00:58<00:05, 5.01it/s]
[2024-01-30 00:52:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.26.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
89%|██████████████████████████████████████████████████████████████████████████████████████████████▏ | 216/243 [00:58<00:05, 5.01it/s]
[2024-01-30 00:52:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.26.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
89%|██████████████████████████████████████████████████████████████████████████████████████████████▏ | 216/243 [00:58<00:05, 5.01it/s]
90%|███████████████████████████████████████████████████████████████████████████████████████████████ | 218/243 [00:58<00:04, 5.80it/s]
[2024-01-30 00:52:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.26.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
90%|███████████████████████████████████████████████████████████████████████████████████████████████ | 218/243 [00:59<00:04, 5.80it/s]
[2024-01-30 00:52:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.26.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
90%|███████████████████████████████████████████████████████████████████████████████████████████████ | 218/243 [00:59<00:04, 5.80it/s]
90%|███████████████████████████████████████████████████████████████████████████████████████████████▌ | 219/243 [00:59<00:06, 3.82it/s]
[2024-01-30 00:52:36] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.26.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
90%|███████████████████████████████████████████████████████████████████████████████████████████████▌ | 219/243 [00:59<00:06, 3.82it/s]
[2024-01-30 00:52:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.26.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
90%|███████████████████████████████████████████████████████████████████████████████████████████████▌ | 219/243 [00:59<00:06, 3.82it/s]
[2024-01-30 00:52:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.26.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
90%|███████████████████████████████████████████████████████████████████████████████████████████████▌ | 219/243 [00:59<00:06, 3.82it/s]
91%|████████████████████████████████████████████████████████████████████████████████████████████████▍ | 221/243 [00:59<00:05, 4.40it/s]
[2024-01-30 00:52:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.26.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
91%|████████████████████████████████████████████████████████████████████████████████████████████████▍ | 221/243 [00:59<00:05, 4.40it/s]
[2024-01-30 00:52:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.26.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
91%|████████████████████████████████████████████████████████████████████████████████████████████████▍ | 221/243 [00:59<00:05, 4.40it/s]
91%|████████████████████████████████████████████████████████████████████████████████████████████████▊ | 222/243 [00:59<00:04, 4.97it/s]
[2024-01-30 00:52:36] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.27.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
91%|████████████████████████████████████████████████████████████████████████████████████████████████▊ | 222/243 [00:59<00:04, 4.97it/s]
[2024-01-30 00:52:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.27.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
91%|████████████████████████████████████████████████████████████████████████████████████████████████▊ | 222/243 [00:59<00:04, 4.97it/s]
[2024-01-30 00:52:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.27.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
91%|████████████████████████████████████████████████████████████████████████████████████████████████▊ | 222/243 [00:59<00:04, 4.97it/s]
92%|█████████████████████████████████████████████████████████████████████████████████████████████████▋ | 224/243 [00:59<00:03, 5.75it/s]
[2024-01-30 00:52:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.27.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
92%|█████████████████████████████████████████████████████████████████████████████████████████████████▋ | 224/243 [01:00<00:03, 5.75it/s]
[2024-01-30 00:52:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.27.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
92%|█████████████████████████████████████████████████████████████████████████████████████████████████▋ | 224/243 [01:00<00:03, 5.75it/s]
93%|██████████████████████████████████████████████████████████████████████████████████████████████████▏ | 225/243 [01:00<00:04, 3.81it/s]
[2024-01-30 00:52:37] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.27.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
93%|██████████████████████████████████████████████████████████████████████████████████████████████████▏ | 225/243 [01:00<00:04, 3.81it/s]
[2024-01-30 00:52:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.27.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
93%|██████████████████████████████████████████████████████████████████████████████████████████████████▏ | 225/243 [01:00<00:04, 3.81it/s]
[2024-01-30 00:52:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.27.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
93%|██████████████████████████████████████████████████████████████████████████████████████████████████▏ | 225/243 [01:00<00:04, 3.81it/s]
93%|███████████████████████████████████████████████████████████████████████████████████████████████████ | 227/243 [01:00<00:03, 4.39it/s]
[2024-01-30 00:52:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.27.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
93%|███████████████████████████████████████████████████████████████████████████████████████████████████ | 227/243 [01:00<00:03, 4.39it/s]
[2024-01-30 00:52:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.27.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
93%|███████████████████████████████████████████████████████████████████████████████████████████████████ | 227/243 [01:00<00:03, 4.39it/s]
94%|███████████████████████████████████████████████████████████████████████████████████████████████████▍ | 228/243 [01:00<00:03, 4.96it/s]
[2024-01-30 00:52:38] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.28.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
94%|███████████████████████████████████████████████████████████████████████████████████████████████████▍ | 228/243 [01:00<00:03, 4.96it/s]
[2024-01-30 00:52:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.28.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
94%|███████████████████████████████████████████████████████████████████████████████████████████████████▍ | 228/243 [01:01<00:03, 4.96it/s]
[2024-01-30 00:52:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.28.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
94%|███████████████████████████████████████████████████████████████████████████████████████████████████▍ | 228/243 [01:01<00:03, 4.96it/s]
95%|████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 230/243 [01:01<00:02, 5.74it/s]
[2024-01-30 00:52:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.28.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
95%|████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 230/243 [01:01<00:02, 5.74it/s]
[2024-01-30 00:52:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.28.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
95%|████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 230/243 [01:01<00:02, 5.74it/s]
95%|████████████████████████████████████████████████████████████████████████████████████████████████████▊ | 231/243 [01:01<00:03, 3.80it/s]
[2024-01-30 00:52:38] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.28.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
95%|████████████████████████████████████████████████████████████████████████████████████████████████████▊ | 231/243 [01:01<00:03, 3.80it/s]
[2024-01-30 00:52:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.28.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
95%|████████████████████████████████████████████████████████████████████████████████████████████████████▊ | 231/243 [01:02<00:03, 3.80it/s]
[2024-01-30 00:52:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.28.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
95%|████████████████████████████████████████████████████████████████████████████████████████████████████▊ | 231/243 [01:02<00:03, 3.80it/s]
96%|█████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 233/243 [01:02<00:02, 4.39it/s]
[2024-01-30 00:52:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.28.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
96%|█████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 233/243 [01:02<00:02, 4.39it/s]
[2024-01-30 00:52:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.28.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
96%|█████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 233/243 [01:02<00:02, 4.39it/s]
96%|██████████████████████████████████████████████████████████████████████████████████████████████████████ | 234/243 [01:02<00:01, 4.96it/s]
[2024-01-30 00:52:39] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.29.input_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
96%|██████████████████████████████████████████████████████████████████████████████████████████████████████ | 234/243 [01:02<00:01, 4.96it/s]
[2024-01-30 00:52:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.29.mlp.down_proj.q_weight[0m", shape: (5120, 1728), dtype: uint32 |
|
96%|██████████████████████████████████████████████████████████████████████████████████████████████████████ | 234/243 [01:02<00:01, 4.96it/s]
[2024-01-30 00:52:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.29.mlp.down_proj.q_scale[0m", shape: (5120, 432), dtype: float16 |
|
96%|██████████████████████████████████████████████████████████████████████████████████████████████████████ | 234/243 [01:02<00:01, 4.96it/s]
97%|██████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 236/243 [01:02<00:01, 5.81it/s]
[2024-01-30 00:52:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.29.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
97%|██████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 236/243 [01:03<00:01, 5.81it/s]
[2024-01-30 00:52:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.29.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
97%|██████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 236/243 [01:03<00:01, 5.81it/s]
98%|███████████████████████████████████████████████████████████████████████████████████████████████████████▍ | 237/243 [01:03<00:01, 3.82it/s]
[2024-01-30 00:52:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.29.post_attention_layernorm.weight[0m", shape: (5120,), dtype: float16 |
|
98%|███████████████████████████████████████████████████████████████████████████████████████████████████████▍ | 237/243 [01:03<00:01, 3.82it/s]
[2024-01-30 00:52:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.29.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
98%|███████████████████████████████████████████████████████████████████████████████████████████████████████▍ | 237/243 [01:03<00:01, 3.82it/s]
[2024-01-30 00:52:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.29.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
98%|███████████████████████████████████████████████████████████████████████████████████████████████████████▍ | 237/243 [01:03<00:01, 3.82it/s]
98%|████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 239/243 [01:03<00:00, 4.42it/s]
[2024-01-30 00:52:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.29.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
98%|████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 239/243 [01:03<00:00, 4.42it/s]
[2024-01-30 00:52:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.29.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
98%|████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 239/243 [01:03<00:00, 4.42it/s]
99%|████████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 240/243 [01:03<00:00, 5.00it/s]
[2024-01-30 00:52:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.30.mlp.gate_up_proj.q_weight[0m", shape: (27648, 640), dtype: uint32 |
|
99%|████████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 240/243 [01:04<00:00, 5.00it/s]
[2024-01-30 00:52:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.30.mlp.gate_up_proj.q_scale[0m", shape: (27648, 160), dtype: float16 |
|
99%|████████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 240/243 [01:04<00:00, 5.00it/s]
99%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▏| 241/243 [01:04<00:00, 3.73it/s]
[2024-01-30 00:52:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.30.self_attn.qkv_proj.q_weight[0m", shape: (15360, 640), dtype: uint32 |
|
99%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▏| 241/243 [01:04<00:00, 3.73it/s]
[2024-01-30 00:52:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.30.self_attn.qkv_proj.q_scale[0m", shape: (15360, 160), dtype: float16 |
|
99%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▏| 241/243 [01:04<00:00, 3.73it/s]
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▌| 242/243 [01:04<00:00, 3.64it/s]
[2024-01-30 00:52:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.30.self_attn.o_proj.q_weight[0m", shape: (5120, 640), dtype: uint32 |
|
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▌| 242/243 [01:04<00:00, 3.64it/s]
[2024-01-30 00:52:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.30.self_attn.o_proj.q_scale[0m", shape: (5120, 160), dtype: float16 |
|
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▌| 242/243 [01:04<00:00, 3.64it/s]
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████| 243/243 [01:04<00:00, 3.77it/s] |
| [2024-01-30 00:52:41] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model-00001-of-00003.bin |
| [2024-01-30 00:52:42] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model-00002-of-00003.bin |
| [2024-01-30 00:52:42] INFO stats.py:76: [92mTime usage[0m: HF loading: 19.855 sec; Pre-quantization mapping: 40.581 sec; Quantization: 1.120 sec |
| [2024-01-30 00:52:42] INFO stats.py:90: [92mRAM usage[0m: Peak RAM: 36.979 GB. Total bytes loaded from disk: 48.488 GB |
| [2024-01-30 00:52:42] INFO convert_weight.py:121: [92mParameter size[0m after quantization: 6.819 GB |
| [2024-01-30 00:52:42] INFO convert_weight.py:126: [92mTotal parameters[0m: 13,015,864,320 |
| [2024-01-30 00:52:42] INFO convert_weight.py:127: [92mBits per parameter[0m: 4.500 |
| Start storing to cache /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y |
|
[0001/0405] saving lm_head.q_weight
[0002/0405] saving lm_head.q_scale
[0003/0405] saving model.layers.30.input_layernorm.weight
[0004/0405] saving model.layers.30.mlp.down_proj.q_weight
[0005/0405] saving model.layers.30.mlp.down_proj.q_scale
[0006/0405] saving model.layers.30.post_attention_layernorm.weight
[0007/0405] saving model.layers.31.input_layernorm.weight
[0008/0405] saving model.layers.31.mlp.down_proj.q_weight
[0009/0405] saving model.layers.31.mlp.down_proj.q_scale
[0010/0405] saving model.layers.31.mlp.gate_up_proj.q_weight
[0011/0405] saving model.layers.31.mlp.gate_up_proj.q_scale
[0012/0405] saving model.layers.31.post_attention_layernorm.weight
[0013/0405] saving model.layers.31.self_attn.qkv_proj.q_weight
[0014/0405] saving model.layers.31.self_attn.qkv_proj.q_scale
[0015/0405] saving model.layers.31.self_attn.o_proj.q_weight
[0016/0405] saving model.layers.31.self_attn.o_proj.q_scale
[0017/0405] saving model.layers.32.input_layernorm.weight
[0018/0405] saving model.layers.32.mlp.down_proj.q_weight
[0019/0405] saving model.layers.32.mlp.down_proj.q_scale
[0020/0405] saving model.layers.32.mlp.gate_up_proj.q_weight
[0021/0405] saving model.layers.32.mlp.gate_up_proj.q_scale
[0022/0405] saving model.layers.32.post_attention_layernorm.weight
[0023/0405] saving model.layers.32.self_attn.qkv_proj.q_weight
[0024/0405] saving model.layers.32.self_attn.qkv_proj.q_scale
[0025/0405] saving model.layers.32.self_attn.o_proj.q_weight
[0026/0405] saving model.layers.32.self_attn.o_proj.q_scale
[0027/0405] saving model.layers.33.input_layernorm.weight
[0028/0405] saving model.layers.33.mlp.down_proj.q_weight
[0029/0405] saving model.layers.33.mlp.down_proj.q_scale
[0030/0405] saving model.layers.33.mlp.gate_up_proj.q_weight
[0031/0405] saving model.layers.33.mlp.gate_up_proj.q_scale
[0032/0405] saving model.layers.33.post_attention_layernorm.weight
[0033/0405] saving model.layers.33.self_attn.qkv_proj.q_weight
[0034/0405] saving model.layers.33.self_attn.qkv_proj.q_scale
[0035/0405] saving model.layers.33.self_attn.o_proj.q_weight
[0036/0405] saving model.layers.33.self_attn.o_proj.q_scale
[0037/0405] saving model.layers.34.input_layernorm.weight
[0038/0405] saving model.layers.34.mlp.down_proj.q_weight
[0039/0405] saving model.layers.34.mlp.down_proj.q_scale
[0040/0405] saving model.layers.34.mlp.gate_up_proj.q_weight
[0041/0405] saving model.layers.34.mlp.gate_up_proj.q_scale
[0042/0405] saving model.layers.34.post_attention_layernorm.weight
[0043/0405] saving model.layers.34.self_attn.qkv_proj.q_weight
[0044/0405] saving model.layers.34.self_attn.qkv_proj.q_scale
[0045/0405] saving model.layers.34.self_attn.o_proj.q_weight
[0046/0405] saving model.layers.34.self_attn.o_proj.q_scale
[0047/0405] saving model.layers.35.input_layernorm.weight
[0048/0405] saving model.layers.35.mlp.down_proj.q_weight
[0049/0405] saving model.layers.35.mlp.down_proj.q_scale
[0050/0405] saving model.layers.35.mlp.gate_up_proj.q_weight
[0051/0405] saving model.layers.35.mlp.gate_up_proj.q_scale
[0052/0405] saving model.layers.35.post_attention_layernorm.weight
[0053/0405] saving model.layers.35.self_attn.qkv_proj.q_weight
[0054/0405] saving model.layers.35.self_attn.qkv_proj.q_scale
[0055/0405] saving model.layers.35.self_attn.o_proj.q_weight
[0056/0405] saving model.layers.35.self_attn.o_proj.q_scale
[0057/0405] saving model.layers.36.input_layernorm.weight
[0058/0405] saving model.layers.36.mlp.down_proj.q_weight
[0059/0405] saving model.layers.36.mlp.down_proj.q_scale
[0060/0405] saving model.layers.36.mlp.gate_up_proj.q_weight
[0061/0405] saving model.layers.36.mlp.gate_up_proj.q_scale
[0062/0405] saving model.layers.36.post_attention_layernorm.weight
[0063/0405] saving model.layers.36.self_attn.qkv_proj.q_weight
[0064/0405] saving model.layers.36.self_attn.qkv_proj.q_scale
[0065/0405] saving model.layers.36.self_attn.o_proj.q_weight
[0066/0405] saving model.layers.36.self_attn.o_proj.q_scale
[0067/0405] saving model.layers.37.input_layernorm.weight
[0068/0405] saving model.layers.37.mlp.down_proj.q_weight
[0069/0405] saving model.layers.37.mlp.down_proj.q_scale
[0070/0405] saving model.layers.37.mlp.gate_up_proj.q_weight
[0071/0405] saving model.layers.37.mlp.gate_up_proj.q_scale
[0072/0405] saving model.layers.37.post_attention_layernorm.weight
[0073/0405] saving model.layers.37.self_attn.qkv_proj.q_weight
[0074/0405] saving model.layers.37.self_attn.qkv_proj.q_scale
[0075/0405] saving model.layers.37.self_attn.o_proj.q_weight
[0076/0405] saving model.layers.37.self_attn.o_proj.q_scale
[0077/0405] saving model.layers.38.input_layernorm.weight
[0078/0405] saving model.layers.38.mlp.down_proj.q_weight
[0079/0405] saving model.layers.38.mlp.down_proj.q_scale
[0080/0405] saving model.layers.38.mlp.gate_up_proj.q_weight
[0081/0405] saving model.layers.38.mlp.gate_up_proj.q_scale
[0082/0405] saving model.layers.38.post_attention_layernorm.weight
[0083/0405] saving model.layers.38.self_attn.qkv_proj.q_weight
[0084/0405] saving model.layers.38.self_attn.qkv_proj.q_scale
[0085/0405] saving model.layers.38.self_attn.o_proj.q_weight
[0086/0405] saving model.layers.38.self_attn.o_proj.q_scale
[0087/0405] saving model.layers.39.input_layernorm.weight
[0088/0405] saving model.layers.39.mlp.down_proj.q_weight
[0089/0405] saving model.layers.39.mlp.down_proj.q_scale
[0090/0405] saving model.layers.39.mlp.gate_up_proj.q_weight
[0091/0405] saving model.layers.39.mlp.gate_up_proj.q_scale
[0092/0405] saving model.layers.39.post_attention_layernorm.weight
[0093/0405] saving model.layers.39.self_attn.qkv_proj.q_weight
[0094/0405] saving model.layers.39.self_attn.qkv_proj.q_scale
[0095/0405] saving model.layers.39.self_attn.o_proj.q_weight
[0096/0405] saving model.layers.39.self_attn.o_proj.q_scale
[0097/0405] saving model.norm.weight
[0098/0405] saving model.embed_tokens.q_weight
[0099/0405] saving model.embed_tokens.q_scale
[0100/0405] saving model.layers.0.input_layernorm.weight
[0101/0405] saving model.layers.0.mlp.down_proj.q_weight
[0102/0405] saving model.layers.0.mlp.down_proj.q_scale
[0103/0405] saving model.layers.0.mlp.gate_up_proj.q_weight
[0104/0405] saving model.layers.0.mlp.gate_up_proj.q_scale
[0105/0405] saving model.layers.0.post_attention_layernorm.weight
[0106/0405] saving model.layers.0.self_attn.qkv_proj.q_weight
[0107/0405] saving model.layers.0.self_attn.qkv_proj.q_scale
[0108/0405] saving model.layers.0.self_attn.o_proj.q_weight
[0109/0405] saving model.layers.0.self_attn.o_proj.q_scale
[0110/0405] saving model.layers.1.input_layernorm.weight
[0111/0405] saving model.layers.1.mlp.down_proj.q_weight
[0112/0405] saving model.layers.1.mlp.down_proj.q_scale
[0113/0405] saving model.layers.1.mlp.gate_up_proj.q_weight
[0114/0405] saving model.layers.1.mlp.gate_up_proj.q_scale
[0115/0405] saving model.layers.1.post_attention_layernorm.weight
[0116/0405] saving model.layers.1.self_attn.qkv_proj.q_weight
[0117/0405] saving model.layers.1.self_attn.qkv_proj.q_scale
[0118/0405] saving model.layers.1.self_attn.o_proj.q_weight
[0119/0405] saving model.layers.1.self_attn.o_proj.q_scale
[0120/0405] saving model.layers.10.input_layernorm.weight
[0121/0405] saving model.layers.10.mlp.down_proj.q_weight
[0122/0405] saving model.layers.10.mlp.down_proj.q_scale
[0123/0405] saving model.layers.10.mlp.gate_up_proj.q_weight
[0124/0405] saving model.layers.10.mlp.gate_up_proj.q_scale
[0125/0405] saving model.layers.10.post_attention_layernorm.weight
[0126/0405] saving model.layers.10.self_attn.qkv_proj.q_weight
[0127/0405] saving model.layers.10.self_attn.qkv_proj.q_scale
[0128/0405] saving model.layers.10.self_attn.o_proj.q_weight
[0129/0405] saving model.layers.10.self_attn.o_proj.q_scale
[0130/0405] saving model.layers.11.input_layernorm.weight
[0131/0405] saving model.layers.11.mlp.down_proj.q_weight
[0132/0405] saving model.layers.11.mlp.down_proj.q_scale
[0133/0405] saving model.layers.11.mlp.gate_up_proj.q_weight
[0134/0405] saving model.layers.11.mlp.gate_up_proj.q_scale
[0135/0405] saving model.layers.11.post_attention_layernorm.weight
[0136/0405] saving model.layers.11.self_attn.qkv_proj.q_weight
[0137/0405] saving model.layers.11.self_attn.qkv_proj.q_scale
[0138/0405] saving model.layers.11.self_attn.o_proj.q_weight
[0139/0405] saving model.layers.11.self_attn.o_proj.q_scale
[0140/0405] saving model.layers.12.input_layernorm.weight
[0141/0405] saving model.layers.12.mlp.down_proj.q_weight
[0142/0405] saving model.layers.12.mlp.down_proj.q_scale
[0143/0405] saving model.layers.12.mlp.gate_up_proj.q_weight
[0144/0405] saving model.layers.12.mlp.gate_up_proj.q_scale
[0145/0405] saving model.layers.12.post_attention_layernorm.weight
[0146/0405] saving model.layers.12.self_attn.qkv_proj.q_weight
[0147/0405] saving model.layers.12.self_attn.qkv_proj.q_scale
[0148/0405] saving model.layers.12.self_attn.o_proj.q_weight
[0149/0405] saving model.layers.12.self_attn.o_proj.q_scale
[0150/0405] saving model.layers.13.input_layernorm.weight
[0151/0405] saving model.layers.13.mlp.down_proj.q_weight
[0152/0405] saving model.layers.13.mlp.down_proj.q_scale
[0153/0405] saving model.layers.13.mlp.gate_up_proj.q_weight
[0154/0405] saving model.layers.13.mlp.gate_up_proj.q_scale
[0155/0405] saving model.layers.13.post_attention_layernorm.weight
[0156/0405] saving model.layers.13.self_attn.qkv_proj.q_weight
[0157/0405] saving model.layers.13.self_attn.qkv_proj.q_scale
[0158/0405] saving model.layers.13.self_attn.o_proj.q_weight
[0159/0405] saving model.layers.13.self_attn.o_proj.q_scale
[0160/0405] saving model.layers.14.input_layernorm.weight
[0161/0405] saving model.layers.14.mlp.down_proj.q_weight
[0162/0405] saving model.layers.14.mlp.down_proj.q_scale
[0163/0405] saving model.layers.14.mlp.gate_up_proj.q_weight
[0164/0405] saving model.layers.14.mlp.gate_up_proj.q_scale
[0165/0405] saving model.layers.14.post_attention_layernorm.weight
[0166/0405] saving model.layers.14.self_attn.qkv_proj.q_weight
[0167/0405] saving model.layers.14.self_attn.qkv_proj.q_scale
[0168/0405] saving model.layers.14.self_attn.o_proj.q_weight
[0169/0405] saving model.layers.14.self_attn.o_proj.q_scale
[0170/0405] saving model.layers.15.self_attn.qkv_proj.q_weight
[0171/0405] saving model.layers.15.self_attn.qkv_proj.q_scale
[0172/0405] saving model.layers.2.input_layernorm.weight
[0173/0405] saving model.layers.2.mlp.down_proj.q_weight
[0174/0405] saving model.layers.2.mlp.down_proj.q_scale
[0175/0405] saving model.layers.2.mlp.gate_up_proj.q_weight
[0176/0405] saving model.layers.2.mlp.gate_up_proj.q_scale
[0177/0405] saving model.layers.2.post_attention_layernorm.weight
[0178/0405] saving model.layers.2.self_attn.qkv_proj.q_weight
[0179/0405] saving model.layers.2.self_attn.qkv_proj.q_scale
[0180/0405] saving model.layers.2.self_attn.o_proj.q_weight
[0181/0405] saving model.layers.2.self_attn.o_proj.q_scale
[0182/0405] saving model.layers.3.input_layernorm.weight
[0183/0405] saving model.layers.3.mlp.down_proj.q_weight
[0184/0405] saving model.layers.3.mlp.down_proj.q_scale
[0185/0405] saving model.layers.3.mlp.gate_up_proj.q_weight
[0186/0405] saving model.layers.3.mlp.gate_up_proj.q_scale
[0187/0405] saving model.layers.3.post_attention_layernorm.weight
[0188/0405] saving model.layers.3.self_attn.qkv_proj.q_weight
[0189/0405] saving model.layers.3.self_attn.qkv_proj.q_scale
[0190/0405] saving model.layers.3.self_attn.o_proj.q_weight
[0191/0405] saving model.layers.3.self_attn.o_proj.q_scale
[0192/0405] saving model.layers.4.input_layernorm.weight
[0193/0405] saving model.layers.4.mlp.down_proj.q_weight
[0194/0405] saving model.layers.4.mlp.down_proj.q_scale
[0195/0405] saving model.layers.4.mlp.gate_up_proj.q_weight
[0196/0405] saving model.layers.4.mlp.gate_up_proj.q_scale
[0197/0405] saving model.layers.4.post_attention_layernorm.weight
[0198/0405] saving model.layers.4.self_attn.qkv_proj.q_weight
[0199/0405] saving model.layers.4.self_attn.qkv_proj.q_scale
[0200/0405] saving model.layers.4.self_attn.o_proj.q_weight
[0201/0405] saving model.layers.4.self_attn.o_proj.q_scale
[0202/0405] saving model.layers.5.input_layernorm.weight
[0203/0405] saving model.layers.5.mlp.down_proj.q_weight
[0204/0405] saving model.layers.5.mlp.down_proj.q_scale
[0205/0405] saving model.layers.5.mlp.gate_up_proj.q_weight
[0206/0405] saving model.layers.5.mlp.gate_up_proj.q_scale
[0207/0405] saving model.layers.5.post_attention_layernorm.weight
[0208/0405] saving model.layers.5.self_attn.qkv_proj.q_weight
[0209/0405] saving model.layers.5.self_attn.qkv_proj.q_scale
[0210/0405] saving model.layers.5.self_attn.o_proj.q_weight
[0211/0405] saving model.layers.5.self_attn.o_proj.q_scale
[0212/0405] saving model.layers.6.input_layernorm.weight
[0213/0405] saving model.layers.6.mlp.down_proj.q_weight
[0214/0405] saving model.layers.6.mlp.down_proj.q_scale
[0215/0405] saving model.layers.6.mlp.gate_up_proj.q_weight
[0216/0405] saving model.layers.6.mlp.gate_up_proj.q_scale
[0217/0405] saving model.layers.6.post_attention_layernorm.weight
[0218/0405] saving model.layers.6.self_attn.qkv_proj.q_weight
[0219/0405] saving model.layers.6.self_attn.qkv_proj.q_scale
[0220/0405] saving model.layers.6.self_attn.o_proj.q_weight
[0221/0405] saving model.layers.6.self_attn.o_proj.q_scale
[0222/0405] saving model.layers.7.input_layernorm.weight
[0223/0405] saving model.layers.7.mlp.down_proj.q_weight
[0224/0405] saving model.layers.7.mlp.down_proj.q_scale
[0225/0405] saving model.layers.7.mlp.gate_up_proj.q_weight
[0226/0405] saving model.layers.7.mlp.gate_up_proj.q_scale
[0227/0405] saving model.layers.7.post_attention_layernorm.weight
[0228/0405] saving model.layers.7.self_attn.qkv_proj.q_weight
[0229/0405] saving model.layers.7.self_attn.qkv_proj.q_scale
[0230/0405] saving model.layers.7.self_attn.o_proj.q_weight
[0231/0405] saving model.layers.7.self_attn.o_proj.q_scale
[0232/0405] saving model.layers.8.input_layernorm.weight
[0233/0405] saving model.layers.8.mlp.down_proj.q_weight
[0234/0405] saving model.layers.8.mlp.down_proj.q_scale
[0235/0405] saving model.layers.8.mlp.gate_up_proj.q_weight
[0236/0405] saving model.layers.8.mlp.gate_up_proj.q_scale
[0237/0405] saving model.layers.8.post_attention_layernorm.weight
[0238/0405] saving model.layers.8.self_attn.qkv_proj.q_weight
[0239/0405] saving model.layers.8.self_attn.qkv_proj.q_scale
[0240/0405] saving model.layers.8.self_attn.o_proj.q_weight
[0241/0405] saving model.layers.8.self_attn.o_proj.q_scale
[0242/0405] saving model.layers.9.input_layernorm.weight
[0243/0405] saving model.layers.9.mlp.down_proj.q_weight
[0244/0405] saving model.layers.9.mlp.down_proj.q_scale
[0245/0405] saving model.layers.9.mlp.gate_up_proj.q_weight
[0246/0405] saving model.layers.9.mlp.gate_up_proj.q_scale
[0247/0405] saving model.layers.9.post_attention_layernorm.weight
[0248/0405] saving model.layers.9.self_attn.qkv_proj.q_weight
[0249/0405] saving model.layers.9.self_attn.qkv_proj.q_scale
[0250/0405] saving model.layers.9.self_attn.o_proj.q_weight
[0251/0405] saving model.layers.9.self_attn.o_proj.q_scale
[0252/0405] saving model.layers.15.input_layernorm.weight
[0253/0405] saving model.layers.15.mlp.down_proj.q_weight
[0254/0405] saving model.layers.15.mlp.down_proj.q_scale
[0255/0405] saving model.layers.15.mlp.gate_up_proj.q_weight
[0256/0405] saving model.layers.15.mlp.gate_up_proj.q_scale
[0257/0405] saving model.layers.15.post_attention_layernorm.weight
[0258/0405] saving model.layers.15.self_attn.o_proj.q_weight
[0259/0405] saving model.layers.15.self_attn.o_proj.q_scale
[0260/0405] saving model.layers.16.input_layernorm.weight
[0261/0405] saving model.layers.16.mlp.down_proj.q_weight
[0262/0405] saving model.layers.16.mlp.down_proj.q_scale
[0263/0405] saving model.layers.16.mlp.gate_up_proj.q_weight
[0264/0405] saving model.layers.16.mlp.gate_up_proj.q_scale
[0265/0405] saving model.layers.16.post_attention_layernorm.weight
[0266/0405] saving model.layers.16.self_attn.qkv_proj.q_weight
[0267/0405] saving model.layers.16.self_attn.qkv_proj.q_scale
[0268/0405] saving model.layers.16.self_attn.o_proj.q_weight
[0269/0405] saving model.layers.16.self_attn.o_proj.q_scale
[0270/0405] saving model.layers.17.input_layernorm.weight
[0271/0405] saving model.layers.17.mlp.down_proj.q_weight
[0272/0405] saving model.layers.17.mlp.down_proj.q_scale
[0273/0405] saving model.layers.17.mlp.gate_up_proj.q_weight
[0274/0405] saving model.layers.17.mlp.gate_up_proj.q_scale
[0275/0405] saving model.layers.17.post_attention_layernorm.weight
[0276/0405] saving model.layers.17.self_attn.qkv_proj.q_weight
[0277/0405] saving model.layers.17.self_attn.qkv_proj.q_scale
[0278/0405] saving model.layers.17.self_attn.o_proj.q_weight
[0279/0405] saving model.layers.17.self_attn.o_proj.q_scale
[0280/0405] saving model.layers.18.input_layernorm.weight
[0281/0405] saving model.layers.18.mlp.down_proj.q_weight
[0282/0405] saving model.layers.18.mlp.down_proj.q_scale
[0283/0405] saving model.layers.18.mlp.gate_up_proj.q_weight
[0284/0405] saving model.layers.18.mlp.gate_up_proj.q_scale
[0285/0405] saving model.layers.18.post_attention_layernorm.weight
[0286/0405] saving model.layers.18.self_attn.qkv_proj.q_weight
[0287/0405] saving model.layers.18.self_attn.qkv_proj.q_scale
[0288/0405] saving model.layers.18.self_attn.o_proj.q_weight
[0289/0405] saving model.layers.18.self_attn.o_proj.q_scale
[0290/0405] saving model.layers.19.input_layernorm.weight
[0291/0405] saving model.layers.19.mlp.down_proj.q_weight
[0292/0405] saving model.layers.19.mlp.down_proj.q_scale
[0293/0405] saving model.layers.19.mlp.gate_up_proj.q_weight
[0294/0405] saving model.layers.19.mlp.gate_up_proj.q_scale
[0295/0405] saving model.layers.19.post_attention_layernorm.weight
[0296/0405] saving model.layers.19.self_attn.qkv_proj.q_weight
[0297/0405] saving model.layers.19.self_attn.qkv_proj.q_scale
[0298/0405] saving model.layers.19.self_attn.o_proj.q_weight
[0299/0405] saving model.layers.19.self_attn.o_proj.q_scale
[0300/0405] saving model.layers.20.input_layernorm.weight
[0301/0405] saving model.layers.20.mlp.down_proj.q_weight
[0302/0405] saving model.layers.20.mlp.down_proj.q_scale
[0303/0405] saving model.layers.20.mlp.gate_up_proj.q_weight
[0304/0405] saving model.layers.20.mlp.gate_up_proj.q_scale
[0305/0405] saving model.layers.20.post_attention_layernorm.weight
[0306/0405] saving model.layers.20.self_attn.qkv_proj.q_weight
[0307/0405] saving model.layers.20.self_attn.qkv_proj.q_scale
[0308/0405] saving model.layers.20.self_attn.o_proj.q_weight
[0309/0405] saving model.layers.20.self_attn.o_proj.q_scale
[0310/0405] saving model.layers.21.input_layernorm.weight
[0311/0405] saving model.layers.21.mlp.down_proj.q_weight
[0312/0405] saving model.layers.21.mlp.down_proj.q_scale
[0313/0405] saving model.layers.21.mlp.gate_up_proj.q_weight
[0314/0405] saving model.layers.21.mlp.gate_up_proj.q_scale
[0315/0405] saving model.layers.21.post_attention_layernorm.weight
[0316/0405] saving model.layers.21.self_attn.qkv_proj.q_weight
[0317/0405] saving model.layers.21.self_attn.qkv_proj.q_scale
[0318/0405] saving model.layers.21.self_attn.o_proj.q_weight
[0319/0405] saving model.layers.21.self_attn.o_proj.q_scale
[0320/0405] saving model.layers.22.input_layernorm.weight
[0321/0405] saving model.layers.22.mlp.down_proj.q_weight
[0322/0405] saving model.layers.22.mlp.down_proj.q_scale
[0323/0405] saving model.layers.22.mlp.gate_up_proj.q_weight
[0324/0405] saving model.layers.22.mlp.gate_up_proj.q_scale
[0325/0405] saving model.layers.22.post_attention_layernorm.weight
[0326/0405] saving model.layers.22.self_attn.qkv_proj.q_weight
[0327/0405] saving model.layers.22.self_attn.qkv_proj.q_scale
[0328/0405] saving model.layers.22.self_attn.o_proj.q_weight
[0329/0405] saving model.layers.22.self_attn.o_proj.q_scale
[0330/0405] saving model.layers.23.input_layernorm.weight
[0331/0405] saving model.layers.23.mlp.down_proj.q_weight
[0332/0405] saving model.layers.23.mlp.down_proj.q_scale
[0333/0405] saving model.layers.23.mlp.gate_up_proj.q_weight
[0334/0405] saving model.layers.23.mlp.gate_up_proj.q_scale
[0335/0405] saving model.layers.23.post_attention_layernorm.weight
[0336/0405] saving model.layers.23.self_attn.qkv_proj.q_weight
[0337/0405] saving model.layers.23.self_attn.qkv_proj.q_scale
[0338/0405] saving model.layers.23.self_attn.o_proj.q_weight
[0339/0405] saving model.layers.23.self_attn.o_proj.q_scale
[0340/0405] saving model.layers.24.input_layernorm.weight
[0341/0405] saving model.layers.24.mlp.down_proj.q_weight
[0342/0405] saving model.layers.24.mlp.down_proj.q_scale
[0343/0405] saving model.layers.24.mlp.gate_up_proj.q_weight
[0344/0405] saving model.layers.24.mlp.gate_up_proj.q_scale
[0345/0405] saving model.layers.24.post_attention_layernorm.weight
[0346/0405] saving model.layers.24.self_attn.qkv_proj.q_weight
[0347/0405] saving model.layers.24.self_attn.qkv_proj.q_scale
[0348/0405] saving model.layers.24.self_attn.o_proj.q_weight
[0349/0405] saving model.layers.24.self_attn.o_proj.q_scale
[0350/0405] saving model.layers.25.input_layernorm.weight
[0351/0405] saving model.layers.25.mlp.down_proj.q_weight
[0352/0405] saving model.layers.25.mlp.down_proj.q_scale
[0353/0405] saving model.layers.25.mlp.gate_up_proj.q_weight
[0354/0405] saving model.layers.25.mlp.gate_up_proj.q_scale
[0355/0405] saving model.layers.25.post_attention_layernorm.weight
[0356/0405] saving model.layers.25.self_attn.qkv_proj.q_weight
[0357/0405] saving model.layers.25.self_attn.qkv_proj.q_scale
[0358/0405] saving model.layers.25.self_attn.o_proj.q_weight
[0359/0405] saving model.layers.25.self_attn.o_proj.q_scale
[0360/0405] saving model.layers.26.input_layernorm.weight
[0361/0405] saving model.layers.26.mlp.down_proj.q_weight
[0362/0405] saving model.layers.26.mlp.down_proj.q_scale
[0363/0405] saving model.layers.26.mlp.gate_up_proj.q_weight
[0364/0405] saving model.layers.26.mlp.gate_up_proj.q_scale
[0365/0405] saving model.layers.26.post_attention_layernorm.weight
[0366/0405] saving model.layers.26.self_attn.qkv_proj.q_weight
[0367/0405] saving model.layers.26.self_attn.qkv_proj.q_scale
[0368/0405] saving model.layers.26.self_attn.o_proj.q_weight
[0369/0405] saving model.layers.26.self_attn.o_proj.q_scale
[0370/0405] saving model.layers.27.input_layernorm.weight
[0371/0405] saving model.layers.27.mlp.down_proj.q_weight
[0372/0405] saving model.layers.27.mlp.down_proj.q_scale
[0373/0405] saving model.layers.27.mlp.gate_up_proj.q_weight
[0374/0405] saving model.layers.27.mlp.gate_up_proj.q_scale
[0375/0405] saving model.layers.27.post_attention_layernorm.weight
[0376/0405] saving model.layers.27.self_attn.qkv_proj.q_weight
[0377/0405] saving model.layers.27.self_attn.qkv_proj.q_scale
[0378/0405] saving model.layers.27.self_attn.o_proj.q_weight
[0379/0405] saving model.layers.27.self_attn.o_proj.q_scale
[0380/0405] saving model.layers.28.input_layernorm.weight
[0381/0405] saving model.layers.28.mlp.down_proj.q_weight
[0382/0405] saving model.layers.28.mlp.down_proj.q_scale
[0383/0405] saving model.layers.28.mlp.gate_up_proj.q_weight
[0384/0405] saving model.layers.28.mlp.gate_up_proj.q_scale
[0385/0405] saving model.layers.28.post_attention_layernorm.weight[2024-01-30 00:52:56] INFO convert_weight.py:143: Saved to directory: [1m/var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y[0m |
|
[0386/0405] saving model.layers.28.self_attn.qkv_proj.q_weight
[0387/0405] saving model.layers.28.self_attn.qkv_proj.q_scale
[0388/0405] saving model.layers.28.self_attn.o_proj.q_weight
[0389/0405] saving model.layers.28.self_attn.o_proj.q_scale
[0390/0405] saving model.layers.29.input_layernorm.weight
[0391/0405] saving model.layers.29.mlp.down_proj.q_weight
[0392/0405] saving model.layers.29.mlp.down_proj.q_scale
[0393/0405] saving model.layers.29.mlp.gate_up_proj.q_weight
[0394/0405] saving model.layers.29.mlp.gate_up_proj.q_scale
[0395/0405] saving model.layers.29.post_attention_layernorm.weight
[0396/0405] saving model.layers.29.self_attn.qkv_proj.q_weight
[0397/0405] saving model.layers.29.self_attn.qkv_proj.q_scale
[0398/0405] saving model.layers.29.self_attn.o_proj.q_weight
[0399/0405] saving model.layers.29.self_attn.o_proj.q_scale
[0400/0405] saving model.layers.30.mlp.gate_up_proj.q_weight
[0401/0405] saving model.layers.30.mlp.gate_up_proj.q_scale
[0402/0405] saving model.layers.30.self_attn.qkv_proj.q_weight
[0403/0405] saving model.layers.30.self_attn.qkv_proj.q_scale
[0404/0405] saving model.layers.30.self_attn.o_proj.q_weight
[0405/0405] saving model.layers.30.self_attn.o_proj.q_scale |
| All finished, 163 total shards committed, record saved to /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y/ndarray-cache.json |
|
|
