| /usr/bin/python3 -m mlc_llm gen_config dist/models/stablelm-2-zephyr-1_6b --quantization q4f16_1 --conv-template stablelm-2 --output /tmp/tmpuyytyuw2 --context-window-size 4096 | |
| [2024-05-24 18:11:22] INFO auto_config.py:115: [92mFound[0m model configuration: dist/models/stablelm-2-zephyr-1_6b/config.json | |
| [2024-05-24 18:11:22] INFO auto_config.py:153: [92mFound[0m model type: [1mstablelm[0m. Use `--model-type` to override. | |
| [2024-05-24 18:11:22] INFO stablelm_model.py:49: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (4096) | |
| [2024-05-24 18:11:22] INFO stablelm_model.py:66: [1mprefill_chunk_size[0m defaults to 2048 | |
| [2024-05-24 18:11:22] INFO config.py:106: Overriding [1mcontext_window_size[0m from 4096 to 4096 | |
| [2024-05-24 18:11:22] INFO config.py:106: Overriding [1mmax_batch_size[0m from 1 to 80 | |
| [2024-05-24 18:11:22] INFO gen_config.py:255: [generation_config.json] Setting [1mbos_token_id[0m: 100257 | |
| [2024-05-24 18:11:22] INFO gen_config.py:255: [generation_config.json] Setting [1meos_token_id[0m: 100257 | |
| [2024-05-24 18:11:22] INFO gen_config.py:269: [91mNot found[0m tokenizer config: dist/models/stablelm-2-zephyr-1_6b/tokenizer.model | |
| [2024-05-24 18:11:22] INFO gen_config.py:267: [92mFound[0m tokenizer config: dist/models/stablelm-2-zephyr-1_6b/tokenizer.json. Copying to [1m/tmp/tmpuyytyuw2/tokenizer.json[0m | |
| [2024-05-24 18:11:22] INFO gen_config.py:267: [92mFound[0m tokenizer config: dist/models/stablelm-2-zephyr-1_6b/vocab.json. Copying to [1m/tmp/tmpuyytyuw2/vocab.json[0m | |
| [2024-05-24 18:11:22] INFO gen_config.py:267: [92mFound[0m tokenizer config: dist/models/stablelm-2-zephyr-1_6b/merges.txt. Copying to [1m/tmp/tmpuyytyuw2/merges.txt[0m | |
| [2024-05-24 18:11:22] INFO gen_config.py:269: [91mNot found[0m tokenizer config: dist/models/stablelm-2-zephyr-1_6b/added_tokens.json | |
| [2024-05-24 18:11:22] INFO gen_config.py:267: [92mFound[0m tokenizer config: dist/models/stablelm-2-zephyr-1_6b/tokenizer_config.json. Copying to [1m/tmp/tmpuyytyuw2/tokenizer_config.json[0m | |
| [2024-05-24 18:11:23] INFO gen_config.py:80: [System default] Setting [1mpad_token_id[0m: 0 | |
| [2024-05-24 18:11:23] INFO gen_config.py:80: [System default] Setting [1mtemperature[0m: 0.7 | |
| [2024-05-24 18:11:23] INFO gen_config.py:80: [System default] Setting [1mpresence_penalty[0m: 0.0 | |
| [2024-05-24 18:11:23] INFO gen_config.py:80: [System default] Setting [1mfrequency_penalty[0m: 0.0 | |
| [2024-05-24 18:11:23] INFO gen_config.py:80: [System default] Setting [1mrepetition_penalty[0m: 1.0 | |
| [2024-05-24 18:11:23] INFO gen_config.py:80: [System default] Setting [1mtop_p[0m: 0.95 | |
| [2024-05-24 18:11:23] INFO gen_config.py:80: [System default] Setting [1mmean_gen_len[0m: 128 | |
| [2024-05-24 18:11:23] INFO gen_config.py:80: [System default] Setting [1mmax_gen_len[0m: 512 | |
| [2024-05-24 18:11:23] INFO gen_config.py:80: [System default] Setting [1mshift_fill_factor[0m: 0.3 | |
| [2024-05-24 18:11:23] INFO gen_config.py:335: Dumping configuration file to: [1m/tmp/tmpuyytyuw2/mlc-chat-config.json[0m | |
| /usr/bin/python3 -m mlc_llm convert_weight dist/models/stablelm-2-zephyr-1_6b --quantization q4f16_1 --source-format auto --output /tmp/tmpuyytyuw2 | |
| [2024-05-24 18:11:23] INFO auto_config.py:115: [92mFound[0m model configuration: dist/models/stablelm-2-zephyr-1_6b/config.json | |
| [2024-05-24 18:11:26] INFO auto_device.py:79: [92mFound[0m device: cuda:0 | |
| [2024-05-24 18:11:27] INFO auto_device.py:88: [91mNot found[0m device: rocm:0 | |
| [2024-05-24 18:11:28] INFO auto_device.py:88: [91mNot found[0m device: metal:0 | |
| [2024-05-24 18:11:29] INFO auto_device.py:88: [91mNot found[0m device: vulkan:0 | |
| [2024-05-24 18:11:30] INFO auto_device.py:88: [91mNot found[0m device: opencl:0 | |
| [2024-05-24 18:11:30] INFO auto_device.py:35: Using device: [1mcuda:0[0m | |
| [2024-05-24 18:11:30] INFO auto_weight.py:70: Finding weights in: dist/models/stablelm-2-zephyr-1_6b | |
| [2024-05-24 18:11:30] INFO auto_weight.py:136: [91mNot found[0m Huggingface PyTorch | |
| [2024-05-24 18:11:30] INFO auto_weight.py:143: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: dist/models/stablelm-2-zephyr-1_6b/model.safetensors.index.json | |
| [2024-05-24 18:11:30] INFO auto_weight.py:106: Using source weight configuration: [1mdist/models/stablelm-2-zephyr-1_6b/model.safetensors.index.json[0m. Use `--source` to override. | |
| [2024-05-24 18:11:30] INFO auto_weight.py:110: Using source weight format: [1mhuggingface-safetensor[0m. Use `--source-format` to override. | |
| [2024-05-24 18:11:30] INFO auto_config.py:153: [92mFound[0m model type: [1mstablelm[0m. Use `--model-type` to override. | |
| [2024-05-24 18:11:30] INFO stablelm_model.py:49: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (4096) | |
| [2024-05-24 18:11:30] INFO stablelm_model.py:66: [1mprefill_chunk_size[0m defaults to 2048 | |
| [1mWeight conversion with arguments:[0m | |
| [1m--config[0m dist/models/stablelm-2-zephyr-1_6b/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', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7) | |
| [1m--model-type[0m stablelm | |
| [1m--device[0m cuda:0 | |
| [1m--source[0m dist/models/stablelm-2-zephyr-1_6b/model.safetensors.index.json | |
| [1m--source-format[0m huggingface-safetensor | |
| [1m--output[0m /tmp/tmpuyytyuw2 | |
| Start storing to cache /tmp/tmpuyytyuw2 | |
| 0%| | 0/220 [00:00<?, ?it/s] [2024-05-24 18:11:32] INFO huggingface_loader.py:184: Loading HF parameters from: dist/models/stablelm-2-zephyr-1_6b/model.safetensors | |
| 0%| | 0/220 [00:00<?, ?it/s] [2024-05-24 18:11:34] INFO group_quantization.py:217: Compiling quantize function for key: ((100352, 2048), float16, cuda, axis=1, output_transpose=False) | |
| 0%| | 0/220 [00:01<?, ?it/s] [2024-05-24 18:11:37] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mlm_head.q_weight[0m", shape: (100352, 256), dtype: uint32 | |
| 0%| | 0/220 [00:04<?, ?it/s] [2024-05-24 18:11:37] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mlm_head.q_scale[0m", shape: (100352, 64), dtype: float16 | |
| 0%| | 0/220 [00:04<?, ?it/s] 0%| | 1/220 [00:04<16:16, 4.46s/it] [2024-05-24 18:11:37] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.embed_tokens.q_weight[0m", shape: (100352, 256), dtype: uint32 | |
| 0%| | 1/220 [00:04<16:16, 4.46s/it] [2024-05-24 18:11:37] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.embed_tokens.q_scale[0m", shape: (100352, 64), dtype: float16 | |
| 0%| | 1/220 [00:04<16:16, 4.46s/it] 1%| | 2/220 [00:04<07:28, 2.06s/it] [2024-05-24 18:11:37] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.0.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 1%| | 2/220 [00:04<07:28, 2.06s/it] [2024-05-24 18:11:37] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.0.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 1%| | 2/220 [00:04<07:28, 2.06s/it] [2024-05-24 18:11:37] INFO group_quantization.py:217: Compiling quantize function for key: ((2048, 5632), float16, cuda, axis=1, output_transpose=False) | |
| 1%| | 2/220 [00:04<07:28, 2.06s/it] [2024-05-24 18:11:38] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 1%| | 2/220 [00:05<07:28, 2.06s/it] [2024-05-24 18:11:38] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 1%| | 2/220 [00:05<07:28, 2.06s/it] 2%|▏ | 5/220 [00:05<02:22, 1.51it/s] [2024-05-24 18:11:38] INFO group_quantization.py:217: Compiling quantize function for key: ((11264, 2048), float16, cuda, axis=1, output_transpose=False) | |
| 2%|▏ | 5/220 [00:05<02:22, 1.51it/s] [2024-05-24 18:11:38] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 2%|▏ | 5/220 [00:05<02:22, 1.51it/s] [2024-05-24 18:11:38] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 2%|▏ | 5/220 [00:05<02:22, 1.51it/s] 3%|▎ | 6/220 [00:05<02:08, 1.66it/s] [2024-05-24 18:11:38] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.0.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 3%|▎ | 6/220 [00:05<02:08, 1.66it/s] [2024-05-24 18:11:38] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.0.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 3%|▎ | 6/220 [00:05<02:08, 1.66it/s] [2024-05-24 18:11:38] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 3%|▎ | 6/220 [00:05<02:08, 1.66it/s] [2024-05-24 18:11:38] INFO group_quantization.py:217: Compiling quantize function for key: ((6144, 2048), float16, cuda, axis=1, output_transpose=False) | |
| 3%|▎ | 6/220 [00:05<02:08, 1.66it/s] [2024-05-24 18:11:38] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 3%|▎ | 6/220 [00:05<02:08, 1.66it/s] [2024-05-24 18:11:38] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 3%|▎ | 6/220 [00:05<02:08, 1.66it/s] 5%|▍ | 10/220 [00:05<01:02, 3.36it/s] [2024-05-24 18:11:38] INFO group_quantization.py:217: Compiling quantize function for key: ((2048, 2048), float16, cuda, axis=1, output_transpose=False) | |
| 5%|▍ | 10/220 [00:05<01:02, 3.36it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 5%|▍ | 10/220 [00:06<01:02, 3.36it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 5%|▍ | 10/220 [00:06<01:02, 3.36it/s] 5%|▌ | 11/220 [00:06<01:02, 3.32it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.1.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 5%|▌ | 11/220 [00:06<01:02, 3.32it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.1.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 5%|▌ | 11/220 [00:06<01:02, 3.32it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 5%|▌ | 11/220 [00:06<01:02, 3.32it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 5%|▌ | 11/220 [00:06<01:02, 3.32it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 5%|▌ | 11/220 [00:06<01:02, 3.32it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 5%|▌ | 11/220 [00:06<01:02, 3.32it/s] 7%|▋ | 15/220 [00:06<00:34, 5.93it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.1.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 7%|▋ | 15/220 [00:06<00:34, 5.93it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.1.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 7%|▋ | 15/220 [00:06<00:34, 5.93it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 7%|▋ | 15/220 [00:06<00:34, 5.93it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 7%|▋ | 15/220 [00:06<00:34, 5.93it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 7%|▋ | 15/220 [00:06<00:34, 5.93it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 7%|▋ | 15/220 [00:06<00:34, 5.93it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 7%|▋ | 15/220 [00:06<00:34, 5.93it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.10.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 7%|▋ | 15/220 [00:06<00:34, 5.93it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.10.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 7%|▋ | 15/220 [00:06<00:34, 5.93it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 7%|▋ | 15/220 [00:06<00:34, 5.93it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 7%|▋ | 15/220 [00:06<00:34, 5.93it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 7%|▋ | 15/220 [00:06<00:34, 5.93it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 7%|▋ | 15/220 [00:06<00:34, 5.93it/s] 11%|█ | 24/220 [00:06<00:14, 13.13it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.10.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 11%|█ | 24/220 [00:06<00:14, 13.13it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.10.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 11%|█ | 24/220 [00:06<00:14, 13.13it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 11%|█ | 24/220 [00:06<00:14, 13.13it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 11%|█ | 24/220 [00:06<00:14, 13.13it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 11%|█ | 24/220 [00:06<00:14, 13.13it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 11%|█ | 24/220 [00:06<00:14, 13.13it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 11%|█ | 24/220 [00:06<00:14, 13.13it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.11.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 11%|█ | 24/220 [00:06<00:14, 13.13it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.11.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 11%|█ | 24/220 [00:06<00:14, 13.13it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 11%|█ | 24/220 [00:06<00:14, 13.13it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 11%|█ | 24/220 [00:06<00:14, 13.13it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 11%|█ | 24/220 [00:06<00:14, 13.13it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 11%|█ | 24/220 [00:06<00:14, 13.13it/s] 15%|█▌ | 33/220 [00:06<00:09, 20.66it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.11.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 15%|█▌ | 33/220 [00:06<00:09, 20.66it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.11.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 15%|█▌ | 33/220 [00:06<00:09, 20.66it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 15%|█▌ | 33/220 [00:06<00:09, 20.66it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 15%|█▌ | 33/220 [00:06<00:09, 20.66it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 15%|█▌ | 33/220 [00:06<00:09, 20.66it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 15%|█▌ | 33/220 [00:06<00:09, 20.66it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 15%|█▌ | 33/220 [00:06<00:09, 20.66it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.12.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 15%|█▌ | 33/220 [00:06<00:09, 20.66it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.12.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 15%|█▌ | 33/220 [00:06<00:09, 20.66it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 15%|█▌ | 33/220 [00:06<00:09, 20.66it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 15%|█▌ | 33/220 [00:06<00:09, 20.66it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 15%|█▌ | 33/220 [00:06<00:09, 20.66it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 15%|█▌ | 33/220 [00:06<00:09, 20.66it/s] 19%|█▉ | 42/220 [00:06<00:06, 27.97it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.12.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 19%|█▉ | 42/220 [00:06<00:06, 27.97it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.12.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 19%|█▉ | 42/220 [00:06<00:06, 27.97it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 19%|█▉ | 42/220 [00:06<00:06, 27.97it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 19%|█▉ | 42/220 [00:06<00:06, 27.97it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 19%|█▉ | 42/220 [00:06<00:06, 27.97it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 19%|█▉ | 42/220 [00:06<00:06, 27.97it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 19%|█▉ | 42/220 [00:06<00:06, 27.97it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.13.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 19%|█▉ | 42/220 [00:06<00:06, 27.97it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.13.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 19%|█▉ | 42/220 [00:06<00:06, 27.97it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 19%|█▉ | 42/220 [00:06<00:06, 27.97it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 19%|█▉ | 42/220 [00:06<00:06, 27.97it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 19%|█▉ | 42/220 [00:06<00:06, 27.97it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 19%|█▉ | 42/220 [00:07<00:06, 27.97it/s] 23%|██▎ | 51/220 [00:07<00:04, 34.67it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.13.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 23%|██▎ | 51/220 [00:07<00:04, 34.67it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.13.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 23%|██▎ | 51/220 [00:07<00:04, 34.67it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 23%|██▎ | 51/220 [00:07<00:04, 34.67it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 23%|██▎ | 51/220 [00:07<00:04, 34.67it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 23%|██▎ | 51/220 [00:07<00:04, 34.67it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 23%|██▎ | 51/220 [00:07<00:04, 34.67it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 23%|██▎ | 51/220 [00:07<00:04, 34.67it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.14.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 23%|██▎ | 51/220 [00:07<00:04, 34.67it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.14.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 23%|██▎ | 51/220 [00:07<00:04, 34.67it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 23%|██▎ | 51/220 [00:07<00:04, 34.67it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 23%|██▎ | 51/220 [00:07<00:04, 34.67it/s] [2024-05-24 18:11:39] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 23%|██▎ | 51/220 [00:07<00:04, 34.67it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 23%|██▎ | 51/220 [00:07<00:04, 34.67it/s] 27%|██▋ | 60/220 [00:07<00:03, 40.42it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.14.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 27%|██▋ | 60/220 [00:07<00:03, 40.42it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.14.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 27%|██▋ | 60/220 [00:07<00:03, 40.42it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 27%|██▋ | 60/220 [00:07<00:03, 40.42it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 27%|██▋ | 60/220 [00:07<00:03, 40.42it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 27%|██▋ | 60/220 [00:07<00:03, 40.42it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 27%|██▋ | 60/220 [00:07<00:03, 40.42it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 27%|██▋ | 60/220 [00:07<00:03, 40.42it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.15.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 27%|██▋ | 60/220 [00:07<00:03, 40.42it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.15.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 27%|██▋ | 60/220 [00:07<00:03, 40.42it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 27%|██▋ | 60/220 [00:07<00:03, 40.42it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 27%|██▋ | 60/220 [00:07<00:03, 40.42it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 27%|██▋ | 60/220 [00:07<00:03, 40.42it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 27%|██▋ | 60/220 [00:07<00:03, 40.42it/s] 31%|███▏ | 69/220 [00:07<00:03, 45.15it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.15.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 31%|███▏ | 69/220 [00:07<00:03, 45.15it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.15.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 31%|███▏ | 69/220 [00:07<00:03, 45.15it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 31%|███▏ | 69/220 [00:07<00:03, 45.15it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 31%|███▏ | 69/220 [00:07<00:03, 45.15it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 31%|███▏ | 69/220 [00:07<00:03, 45.15it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 31%|███▏ | 69/220 [00:07<00:03, 45.15it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 31%|███▏ | 69/220 [00:07<00:03, 45.15it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.16.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 31%|███▏ | 69/220 [00:07<00:03, 45.15it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.16.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 31%|███▏ | 69/220 [00:07<00:03, 45.15it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 31%|███▏ | 69/220 [00:07<00:03, 45.15it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 31%|███▏ | 69/220 [00:07<00:03, 45.15it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 31%|███▏ | 69/220 [00:07<00:03, 45.15it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 31%|███▏ | 69/220 [00:07<00:03, 45.15it/s] 35%|███▌ | 78/220 [00:07<00:02, 48.90it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.16.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 35%|███▌ | 78/220 [00:07<00:02, 48.90it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.16.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 35%|███▌ | 78/220 [00:07<00:02, 48.90it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 35%|███▌ | 78/220 [00:07<00:02, 48.90it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 35%|███▌ | 78/220 [00:07<00:02, 48.90it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 35%|███▌ | 78/220 [00:07<00:02, 48.90it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 35%|███▌ | 78/220 [00:07<00:02, 48.90it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 35%|███▌ | 78/220 [00:07<00:02, 48.90it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.17.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 35%|███▌ | 78/220 [00:07<00:02, 48.90it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.17.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 35%|███▌ | 78/220 [00:07<00:02, 48.90it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 35%|███▌ | 78/220 [00:07<00:02, 48.90it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 35%|███▌ | 78/220 [00:07<00:02, 48.90it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 35%|███▌ | 78/220 [00:07<00:02, 48.90it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 35%|███▌ | 78/220 [00:07<00:02, 48.90it/s] 40%|███▉ | 87/220 [00:07<00:02, 51.85it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.17.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 40%|███▉ | 87/220 [00:07<00:02, 51.85it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.17.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 40%|███▉ | 87/220 [00:07<00:02, 51.85it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 40%|███▉ | 87/220 [00:07<00:02, 51.85it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 40%|███▉ | 87/220 [00:07<00:02, 51.85it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 40%|███▉ | 87/220 [00:07<00:02, 51.85it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 40%|███▉ | 87/220 [00:07<00:02, 51.85it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 40%|███▉ | 87/220 [00:07<00:02, 51.85it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.18.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 40%|███▉ | 87/220 [00:07<00:02, 51.85it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.18.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 40%|███▉ | 87/220 [00:07<00:02, 51.85it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 40%|███▉ | 87/220 [00:07<00:02, 51.85it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 40%|███▉ | 87/220 [00:07<00:02, 51.85it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 40%|███▉ | 87/220 [00:07<00:02, 51.85it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 40%|███▉ | 87/220 [00:07<00:02, 51.85it/s] 44%|████▎ | 96/220 [00:07<00:02, 53.97it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.18.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 44%|████▎ | 96/220 [00:07<00:02, 53.97it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.18.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 44%|████▎ | 96/220 [00:07<00:02, 53.97it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 44%|████▎ | 96/220 [00:07<00:02, 53.97it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 44%|████▎ | 96/220 [00:07<00:02, 53.97it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 44%|████▎ | 96/220 [00:07<00:02, 53.97it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 44%|████▎ | 96/220 [00:07<00:02, 53.97it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 44%|████▎ | 96/220 [00:07<00:02, 53.97it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.19.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 44%|████▎ | 96/220 [00:07<00:02, 53.97it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.19.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 44%|████▎ | 96/220 [00:07<00:02, 53.97it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 44%|████▎ | 96/220 [00:07<00:02, 53.97it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 44%|████▎ | 96/220 [00:07<00:02, 53.97it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 44%|████▎ | 96/220 [00:07<00:02, 53.97it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 44%|████▎ | 96/220 [00:07<00:02, 53.97it/s] 48%|████▊ | 105/220 [00:07<00:02, 55.58it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.19.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 48%|████▊ | 105/220 [00:07<00:02, 55.58it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.19.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 48%|████▊ | 105/220 [00:07<00:02, 55.58it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 48%|████▊ | 105/220 [00:07<00:02, 55.58it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 48%|████▊ | 105/220 [00:07<00:02, 55.58it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 48%|████▊ | 105/220 [00:07<00:02, 55.58it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 48%|████▊ | 105/220 [00:07<00:02, 55.58it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 48%|████▊ | 105/220 [00:07<00:02, 55.58it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.2.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 48%|████▊ | 105/220 [00:07<00:02, 55.58it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.2.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 48%|████▊ | 105/220 [00:07<00:02, 55.58it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 48%|████▊ | 105/220 [00:07<00:02, 55.58it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 48%|████▊ | 105/220 [00:07<00:02, 55.58it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 48%|████▊ | 105/220 [00:08<00:02, 55.58it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 48%|████▊ | 105/220 [00:08<00:02, 55.58it/s] 52%|█████▏ | 114/220 [00:08<00:01, 56.72it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.2.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 52%|█████▏ | 114/220 [00:08<00:01, 56.72it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.2.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 52%|█████▏ | 114/220 [00:08<00:01, 56.72it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 52%|█████▏ | 114/220 [00:08<00:01, 56.72it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 52%|█████▏ | 114/220 [00:08<00:01, 56.72it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 52%|█████▏ | 114/220 [00:08<00:01, 56.72it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 52%|█████▏ | 114/220 [00:08<00:01, 56.72it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 52%|█████▏ | 114/220 [00:08<00:01, 56.72it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.20.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 52%|█████▏ | 114/220 [00:08<00:01, 56.72it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.20.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 52%|█████▏ | 114/220 [00:08<00:01, 56.72it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 52%|█████▏ | 114/220 [00:08<00:01, 56.72it/s] [2024-05-24 18:11:40] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 52%|█████▏ | 114/220 [00:08<00:01, 56.72it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 52%|█████▏ | 114/220 [00:08<00:01, 56.72it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 52%|█████▏ | 114/220 [00:08<00:01, 56.72it/s] 56%|█████▌ | 123/220 [00:08<00:01, 57.57it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.20.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 56%|█████▌ | 123/220 [00:08<00:01, 57.57it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.20.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 56%|█████▌ | 123/220 [00:08<00:01, 57.57it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 56%|█████▌ | 123/220 [00:08<00:01, 57.57it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 56%|█████▌ | 123/220 [00:08<00:01, 57.57it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 56%|█████▌ | 123/220 [00:08<00:01, 57.57it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 56%|█████▌ | 123/220 [00:08<00:01, 57.57it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 56%|█████▌ | 123/220 [00:08<00:01, 57.57it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.21.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 56%|█████▌ | 123/220 [00:08<00:01, 57.57it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.21.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 56%|█████▌ | 123/220 [00:08<00:01, 57.57it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 56%|█████▌ | 123/220 [00:08<00:01, 57.57it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 56%|█████▌ | 123/220 [00:08<00:01, 57.57it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 56%|█████▌ | 123/220 [00:08<00:01, 57.57it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 56%|█████▌ | 123/220 [00:08<00:01, 57.57it/s] 60%|██████ | 132/220 [00:08<00:01, 58.16it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.21.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 60%|██████ | 132/220 [00:08<00:01, 58.16it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.21.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 60%|██████ | 132/220 [00:08<00:01, 58.16it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 60%|██████ | 132/220 [00:08<00:01, 58.16it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 60%|██████ | 132/220 [00:08<00:01, 58.16it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 60%|██████ | 132/220 [00:08<00:01, 58.16it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 60%|██████ | 132/220 [00:08<00:01, 58.16it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 60%|██████ | 132/220 [00:08<00:01, 58.16it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.22.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 60%|██████ | 132/220 [00:08<00:01, 58.16it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.22.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 60%|██████ | 132/220 [00:08<00:01, 58.16it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.22.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 60%|██████ | 132/220 [00:08<00:01, 58.16it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.22.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 60%|██████ | 132/220 [00:08<00:01, 58.16it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.22.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 60%|██████ | 132/220 [00:08<00:01, 58.16it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.22.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 60%|██████ | 132/220 [00:08<00:01, 58.16it/s] 64%|██████▍ | 141/220 [00:08<00:01, 58.58it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.22.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 64%|██████▍ | 141/220 [00:08<00:01, 58.58it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.22.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 64%|██████▍ | 141/220 [00:08<00:01, 58.58it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.22.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 64%|██████▍ | 141/220 [00:08<00:01, 58.58it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 64%|██████▍ | 141/220 [00:08<00:01, 58.58it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 64%|██████▍ | 141/220 [00:08<00:01, 58.58it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 64%|██████▍ | 141/220 [00:08<00:01, 58.58it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 64%|██████▍ | 141/220 [00:08<00:01, 58.58it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.23.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 64%|██████▍ | 141/220 [00:08<00:01, 58.58it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.23.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 64%|██████▍ | 141/220 [00:08<00:01, 58.58it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.23.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 64%|██████▍ | 141/220 [00:08<00:01, 58.58it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.23.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 64%|██████▍ | 141/220 [00:08<00:01, 58.58it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.23.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 64%|██████▍ | 141/220 [00:08<00:01, 58.58it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.23.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 64%|██████▍ | 141/220 [00:08<00:01, 58.58it/s] 68%|██████▊ | 150/220 [00:08<00:01, 58.81it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.23.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 68%|██████▊ | 150/220 [00:08<00:01, 58.81it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.23.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 68%|██████▊ | 150/220 [00:08<00:01, 58.81it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.23.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 68%|██████▊ | 150/220 [00:08<00:01, 58.81it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 68%|██████▊ | 150/220 [00:08<00:01, 58.81it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 68%|██████▊ | 150/220 [00:08<00:01, 58.81it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 68%|██████▊ | 150/220 [00:08<00:01, 58.81it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 68%|██████▊ | 150/220 [00:08<00:01, 58.81it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.3.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 68%|██████▊ | 150/220 [00:08<00:01, 58.81it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.3.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 68%|██████▊ | 150/220 [00:08<00:01, 58.81it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 68%|██████▊ | 150/220 [00:08<00:01, 58.81it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 68%|██████▊ | 150/220 [00:08<00:01, 58.81it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 68%|██████▊ | 150/220 [00:08<00:01, 58.81it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 68%|██████▊ | 150/220 [00:08<00:01, 58.81it/s] 72%|███████▏ | 159/220 [00:08<00:01, 58.98it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.3.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 72%|███████▏ | 159/220 [00:08<00:01, 58.98it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.3.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 72%|███████▏ | 159/220 [00:08<00:01, 58.98it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 72%|███████▏ | 159/220 [00:08<00:01, 58.98it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 72%|███████▏ | 159/220 [00:08<00:01, 58.98it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 72%|███████▏ | 159/220 [00:08<00:01, 58.98it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 72%|███████▏ | 159/220 [00:08<00:01, 58.98it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 72%|███████▏ | 159/220 [00:08<00:01, 58.98it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.4.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 72%|███████▏ | 159/220 [00:08<00:01, 58.98it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.4.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 72%|███████▏ | 159/220 [00:08<00:01, 58.98it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 72%|███████▏ | 159/220 [00:08<00:01, 58.98it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 72%|███████▏ | 159/220 [00:08<00:01, 58.98it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 72%|███████▏ | 159/220 [00:08<00:01, 58.98it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 72%|███████▏ | 159/220 [00:08<00:01, 58.98it/s] 76%|███████▋ | 168/220 [00:08<00:00, 59.13it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.4.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 76%|███████▋ | 168/220 [00:08<00:00, 59.13it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.4.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 76%|███████▋ | 168/220 [00:08<00:00, 59.13it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 76%|███████▋ | 168/220 [00:08<00:00, 59.13it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 76%|███████▋ | 168/220 [00:09<00:00, 59.13it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 76%|███████▋ | 168/220 [00:09<00:00, 59.13it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 76%|███████▋ | 168/220 [00:09<00:00, 59.13it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 76%|███████▋ | 168/220 [00:09<00:00, 59.13it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.5.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 76%|███████▋ | 168/220 [00:09<00:00, 59.13it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.5.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 76%|███████▋ | 168/220 [00:09<00:00, 59.13it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 76%|███████▋ | 168/220 [00:09<00:00, 59.13it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 76%|███████▋ | 168/220 [00:09<00:00, 59.13it/s] [2024-05-24 18:11:41] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 76%|███████▋ | 168/220 [00:09<00:00, 59.13it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 76%|███████▋ | 168/220 [00:09<00:00, 59.13it/s] 80%|████████ | 177/220 [00:09<00:00, 59.21it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.5.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 80%|████████ | 177/220 [00:09<00:00, 59.21it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.5.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 80%|████████ | 177/220 [00:09<00:00, 59.21it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 80%|████████ | 177/220 [00:09<00:00, 59.21it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 80%|████████ | 177/220 [00:09<00:00, 59.21it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 80%|████████ | 177/220 [00:09<00:00, 59.21it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 80%|████████ | 177/220 [00:09<00:00, 59.21it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 80%|████████ | 177/220 [00:09<00:00, 59.21it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.6.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 80%|████████ | 177/220 [00:09<00:00, 59.21it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.6.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 80%|████████ | 177/220 [00:09<00:00, 59.21it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 80%|████████ | 177/220 [00:09<00:00, 59.21it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 80%|████████ | 177/220 [00:09<00:00, 59.21it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 80%|████████ | 177/220 [00:09<00:00, 59.21it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 80%|████████ | 177/220 [00:09<00:00, 59.21it/s] 85%|████████▍ | 186/220 [00:09<00:00, 59.30it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.6.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 85%|████████▍ | 186/220 [00:09<00:00, 59.30it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.6.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 85%|████████▍ | 186/220 [00:09<00:00, 59.30it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 85%|████████▍ | 186/220 [00:09<00:00, 59.30it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 85%|████████▍ | 186/220 [00:09<00:00, 59.30it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 85%|████████▍ | 186/220 [00:09<00:00, 59.30it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 85%|████████▍ | 186/220 [00:09<00:00, 59.30it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 85%|████████▍ | 186/220 [00:09<00:00, 59.30it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.7.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 85%|████████▍ | 186/220 [00:09<00:00, 59.30it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.7.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 85%|████████▍ | 186/220 [00:09<00:00, 59.30it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 85%|████████▍ | 186/220 [00:09<00:00, 59.30it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 85%|████████▍ | 186/220 [00:09<00:00, 59.30it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 85%|████████▍ | 186/220 [00:09<00:00, 59.30it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 85%|████████▍ | 186/220 [00:09<00:00, 59.30it/s] 89%|████████▊ | 195/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.7.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 89%|████████▊ | 195/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.7.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 89%|████████▊ | 195/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 89%|████████▊ | 195/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 89%|████████▊ | 195/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 89%|████████▊ | 195/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 89%|████████▊ | 195/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 89%|████████▊ | 195/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.8.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 89%|████████▊ | 195/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.8.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 89%|████████▊ | 195/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 89%|████████▊ | 195/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 89%|████████▊ | 195/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 89%|████████▊ | 195/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 89%|████████▊ | 195/220 [00:09<00:00, 59.50it/s] 93%|█████████▎| 204/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.8.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 93%|█████████▎| 204/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.8.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 93%|█████████▎| 204/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 93%|█████████▎| 204/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 93%|█████████▎| 204/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 93%|█████████▎| 204/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 93%|█████████▎| 204/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 93%|█████████▎| 204/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.9.input_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 93%|█████████▎| 204/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.9.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 93%|█████████▎| 204/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32 | |
| 93%|█████████▎| 204/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float16 | |
| 93%|█████████▎| 204/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32 | |
| 93%|█████████▎| 204/220 [00:09<00:00, 59.50it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float16 | |
| 93%|█████████▎| 204/220 [00:09<00:00, 59.50it/s] 97%|█████████▋| 213/220 [00:09<00:00, 59.47it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.9.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float16 | |
| 97%|█████████▋| 213/220 [00:09<00:00, 59.47it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.9.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 97%|█████████▋| 213/220 [00:09<00:00, 59.47it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float16 | |
| 97%|█████████▋| 213/220 [00:09<00:00, 59.47it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32 | |
| 97%|█████████▋| 213/220 [00:09<00:00, 59.47it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float16 | |
| 97%|█████████▋| 213/220 [00:09<00:00, 59.47it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32 | |
| 97%|█████████▋| 213/220 [00:09<00:00, 59.47it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float16 | |
| 97%|█████████▋| 213/220 [00:09<00:00, 59.47it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.norm.bias[0m", shape: (2048,), dtype: float16 | |
| 97%|█████████▋| 213/220 [00:09<00:00, 59.47it/s] [2024-05-24 18:11:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.norm.weight[0m", shape: (2048,), dtype: float16 | |
| 97%|█████████▋| 213/220 [00:09<00:00, 59.47it/s] 100%|██████████| 220/220 [00:09<00:00, 22.52it/s] | |
| [2024-05-24 18:11:42] INFO huggingface_loader.py:196: Unloading HF weight file: dist/models/stablelm-2-zephyr-1_6b/model.safetensors | |
| [2024-05-24 18:11:42] INFO stats.py:76: [92mTime usage[0m: HF loading: 1.032 sec; Pre-quantization mapping: 1.159 sec; Quantization: 4.181 sec | |
| [2024-05-24 18:11:42] INFO stats.py:90: [92mRAM usage[0m: Peak RAM: 3.063 GB. Total bytes loaded from disk: 3.063 GB | |
| [2024-05-24 18:11:42] INFO convert_weight.py:155: [92mParameter size[0m after quantization: 0.862 GB | |
| [2024-05-24 18:11:42] INFO convert_weight.py:160: [92mTotal parameters[0m: 1,644,515,328 | |
| [2024-05-24 18:11:42] INFO convert_weight.py:161: [92mBits per parameter[0m: 4.502 | |
| [2024-05-24 18:11:42] INFO convert_weight.py:166: Saved to directory: [1m/tmp/tmpuyytyuw2[0m | |
| All finished, 27 total shards committed, record saved to /tmp/tmpuyytyuw2/ndarray-cache.json | |