/home/floriadmin/miniforge3/envs/mlc/bin/python -m mlc_llm gen_config ../dist/models/XAgentLlama-7B-preview --quantization q4f32_1 --conv-template llama-2 --output /tmp/tmpq9jzxnoc [2024-03-18 19:56:52] INFO auto_config.py:115: Found model configuration: ../dist/models/XAgentLlama-7B-preview/config.json [2024-03-18 19:56:52] INFO auto_config.py:153: Found model type: llama. Use `--model-type` to override. [2024-03-18 19:56:52] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (16384) [2024-03-18 19:56:52] INFO llama_model.py:72: prefill_chunk_size defaults to context_window_size (16384) [2024-03-18 19:56:52] INFO config.py:106: Overriding max_batch_size from 1 to 80 [2024-03-18 19:56:52] INFO gen_config.py:133: [generation_config.json] Setting bos_token_id: 1 [2024-03-18 19:56:52] INFO gen_config.py:133: [generation_config.json] Setting eos_token_id: 2 [2024-03-18 19:56:52] INFO gen_config.py:145: Found tokenizer config: ../dist/models/XAgentLlama-7B-preview/tokenizer.model. Copying to /tmp/tmpq9jzxnoc/tokenizer.model [2024-03-18 19:56:52] INFO gen_config.py:145: Found tokenizer config: ../dist/models/XAgentLlama-7B-preview/tokenizer.json. Copying to /tmp/tmpq9jzxnoc/tokenizer.json [2024-03-18 19:56:52] INFO gen_config.py:147: Not found tokenizer config: ../dist/models/XAgentLlama-7B-preview/vocab.json [2024-03-18 19:56:52] INFO gen_config.py:147: Not found tokenizer config: ../dist/models/XAgentLlama-7B-preview/merges.txt [2024-03-18 19:56:52] INFO gen_config.py:147: Not found tokenizer config: ../dist/models/XAgentLlama-7B-preview/added_tokens.json [2024-03-18 19:56:52] INFO gen_config.py:145: Found tokenizer config: ../dist/models/XAgentLlama-7B-preview/tokenizer_config.json. Copying to /tmp/tmpq9jzxnoc/tokenizer_config.json [2024-03-18 19:56:52] INFO gen_config.py:75: [System default] Setting pad_token_id: 0 [2024-03-18 19:56:52] INFO gen_config.py:75: [System default] Setting temperature: 0.7 [2024-03-18 19:56:52] INFO gen_config.py:75: [System default] Setting presence_penalty: 0.0 [2024-03-18 19:56:52] INFO gen_config.py:75: [System default] Setting frequency_penalty: 0.0 [2024-03-18 19:56:52] INFO gen_config.py:75: [System default] Setting repetition_penalty: 1.0 [2024-03-18 19:56:52] INFO gen_config.py:75: [System default] Setting top_p: 0.95 [2024-03-18 19:56:52] INFO gen_config.py:75: [System default] Setting mean_gen_len: 128 [2024-03-18 19:56:52] INFO gen_config.py:75: [System default] Setting max_gen_len: 512 [2024-03-18 19:56:52] INFO gen_config.py:75: [System default] Setting shift_fill_factor: 0.3 [2024-03-18 19:56:52] INFO gen_config.py:198: Dumping configuration file to: /tmp/tmpq9jzxnoc/mlc-chat-config.json /home/floriadmin/miniforge3/envs/mlc/bin/python -m mlc_llm convert_weight ../dist/models/XAgentLlama-7B-preview --quantization q4f32_1 --source-format auto --output /tmp/tmpq9jzxnoc [2024-03-18 19:56:53] INFO auto_config.py:115: Found model configuration: ../dist/models/XAgentLlama-7B-preview/config.json [2024-03-18 19:56:54] INFO auto_device.py:76: Found device: cuda:0 [2024-03-18 19:56:54] INFO auto_device.py:76: Found device: cuda:1 [2024-03-18 19:56:54] INFO auto_device.py:76: Found device: cuda:2 [2024-03-18 19:56:54] INFO auto_device.py:76: Found device: cuda:3 [2024-03-18 19:56:54] INFO auto_device.py:76: Found device: cuda:4 [2024-03-18 19:56:54] INFO auto_device.py:76: Found device: cuda:5 [2024-03-18 19:56:54] INFO auto_device.py:76: Found device: cuda:6 [2024-03-18 19:56:54] INFO auto_device.py:76: Found device: cuda:7 [2024-03-18 19:56:54] INFO auto_device.py:76: Found device: cuda:8 [2024-03-18 19:56:54] INFO auto_device.py:76: Found device: cuda:9 [2024-03-18 19:56:55] INFO auto_device.py:85: Not found device: rocm:0 [2024-03-18 19:56:56] INFO auto_device.py:85: Not found device: metal:0 [2024-03-18 19:56:58] INFO auto_device.py:76: Found device: vulkan:0 [2024-03-18 19:56:58] INFO auto_device.py:76: Found device: vulkan:1 [2024-03-18 19:56:58] INFO auto_device.py:76: Found device: vulkan:2 [2024-03-18 19:56:58] INFO auto_device.py:76: Found device: vulkan:3 [2024-03-18 19:56:58] INFO auto_device.py:76: Found device: vulkan:4 [2024-03-18 19:56:58] INFO auto_device.py:76: Found device: vulkan:5 [2024-03-18 19:56:58] INFO auto_device.py:76: Found device: vulkan:6 [2024-03-18 19:56:58] INFO auto_device.py:76: Found device: vulkan:7 [2024-03-18 19:56:58] INFO auto_device.py:76: Found device: vulkan:8 [2024-03-18 19:56:58] INFO auto_device.py:76: Found device: vulkan:9 [2024-03-18 19:56:58] INFO auto_device.py:76: Found device: vulkan:10 [2024-03-18 19:56:59] INFO auto_device.py:85: Not found device: opencl:0 [2024-03-18 19:56:59] INFO auto_device.py:33: Using device: cuda:0 [2024-03-18 19:56:59] INFO auto_weight.py:70: Finding weights in: ../dist/models/XAgentLlama-7B-preview [2024-03-18 19:56:59] INFO auto_weight.py:129: Found source weight format: huggingface-torch. Source configuration: ../dist/models/XAgentLlama-7B-preview/pytorch_model.bin [2024-03-18 19:56:59] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: ../dist/models/XAgentLlama-7B-preview/model.safetensors.index.json [2024-03-18 19:56:59] INFO auto_weight.py:106: Using source weight configuration: ../dist/models/XAgentLlama-7B-preview/pytorch_model.bin. Use `--source` to override. [2024-03-18 19:56:59] INFO auto_weight.py:110: Using source weight format: huggingface-torch. Use `--source-format` to override. [2024-03-18 19:56:59] INFO auto_config.py:153: Found model type: llama. Use `--model-type` to override. [2024-03-18 19:56:59] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (16384) [2024-03-18 19:56:59] INFO llama_model.py:72: prefill_chunk_size defaults to context_window_size (16384) [2024-03-18 19:57:01] INFO huggingface_loader.py:182: Loading HF parameters from: ../dist/models/XAgentLlama-7B-preview/pytorch_model.bin Weight conversion with arguments: --config ../dist/models/XAgentLlama-7B-preview/config.json --quantization GroupQuantize(name='q4f32_1', kind='group-quant', group_size=40, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float32', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=5, max_int_value=7) --model-type llama --device cuda:0 --source ../dist/models/XAgentLlama-7B-preview/pytorch_model.bin --source-format huggingface-torch --output /tmp/tmpq9jzxnoc Start storing to cache /tmp/tmpq9jzxnoc 0%| | 0/195 [00:00 type is zero. setattr(self, word, getattr(machar, word).flat[0]) /home/floriadmin/miniforge3/envs/mlc/lib/python3.11/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) 1%|▍ | 1/195 [00:04<14:01, 4.34s/it] [2024-03-18 19:57:36] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.norm.weight", shape: (4096,), dtype: float32 1%|▍ | 1/195 [00:04<14:01, 4.34s/it] [2024-03-18 19:57:38] INFO huggingface_loader.py:164: [Quantized] Parameter: "lm_head.q_weight", shape: (32016, 515), dtype: uint32 1%|▍ | 1/195 [00:06<14:01, 4.34s/it] [2024-03-18 19:57:38] INFO huggingface_loader.py:164: [Quantized] Parameter: "lm_head.q_scale", shape: (32016, 103), dtype: float32 1%|▍ | 1/195 [00:07<14:01, 4.34s/it] 2%|█▍ | 3/195 [00:07<06:51, 2.14s/it] [2024-03-18 19:57:38] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (4096,), dtype: float32 2%|█▍ | 3/195 [00:07<06:51, 2.14s/it] [2024-03-18 19:57:39] INFO group_quantization.py:232: Compiling quantize function for key: ((12288, 4096), float32, cuda, axis=1, output_transpose=False) 2%|█▍ | 3/195 [00:07<06:51, 2.14s/it] [2024-03-18 19:57:39] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 2%|█▍ | 3/195 [00:08<06:51, 2.14s/it] [2024-03-18 19:57:40] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 2%|█▍ | 3/195 [00:08<06:51, 2.14s/it] 3%|██▎ | 5/195 [00:08<04:20, 1.37s/it] [2024-03-18 19:57:40] INFO group_quantization.py:232: Compiling quantize function for key: ((4096, 4096), float32, cuda, axis=1, output_transpose=False) 3%|██▎ | 5/195 [00:08<04:20, 1.37s/it] [2024-03-18 19:57:40] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 3%|██▎ | 5/195 [00:09<04:20, 1.37s/it] [2024-03-18 19:57:40] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 3%|██▎ | 5/195 [00:09<04:20, 1.37s/it] 3%|██▊ | 6/195 [00:09<03:44, 1.19s/it] [2024-03-18 19:57:40] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (4096,), dtype: float32 3%|██▊ | 6/195 [00:09<03:44, 1.19s/it] [2024-03-18 19:57:42] INFO group_quantization.py:232: Compiling quantize function for key: ((22016, 4096), float32, cuda, axis=1, output_transpose=False) 3%|██▊ | 6/195 [00:10<03:44, 1.19s/it] [2024-03-18 19:57:42] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 3%|██▊ | 6/195 [00:11<03:44, 1.19s/it] [2024-03-18 19:57:43] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 3%|██▊ | 6/195 [00:11<03:44, 1.19s/it] 4%|███▊ | 8/195 [00:11<03:39, 1.17s/it] [2024-03-18 19:57:43] INFO group_quantization.py:232: Compiling quantize function for key: ((4096, 11008), float32, cuda, axis=1, output_transpose=False) 4%|███▊ | 8/195 [00:11<03:39, 1.17s/it] [2024-03-18 19:57:44] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 4%|███▊ | 8/195 [00:12<03:39, 1.17s/it] [2024-03-18 19:57:44] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 4%|███▊ | 8/195 [00:12<03:39, 1.17s/it] 5%|████▏ | 9/195 [00:12<03:37, 1.17s/it] [2024-03-18 19:57:44] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (4096,), dtype: float32 5%|████▏ | 9/195 [00:12<03:37, 1.17s/it] [2024-03-18 19:57:44] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 5%|████▏ | 9/195 [00:13<03:37, 1.17s/it] [2024-03-18 19:57:45] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 5%|████▏ | 9/195 [00:13<03:37, 1.17s/it] 6%|█████▏ | 11/195 [00:13<02:40, 1.14it/s] [2024-03-18 19:57:45] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 6%|█████▏ | 11/195 [00:13<02:40, 1.14it/s] [2024-03-18 19:57:45] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 6%|█████▏ | 11/195 [00:13<02:40, 1.14it/s] 6%|█████▌ | 12/195 [00:13<02:15, 1.35it/s] [2024-03-18 19:57:45] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (4096,), dtype: float32 6%|█████▌ | 12/195 [00:13<02:15, 1.35it/s] [2024-03-18 19:57:46] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 6%|█████▌ | 12/195 [00:15<02:15, 1.35it/s] [2024-03-18 19:57:47] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 6%|█████▌ | 12/195 [00:15<02:15, 1.35it/s] 7%|██████▌ | 14/195 [00:15<02:24, 1.26it/s] [2024-03-18 19:57:47] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 7%|██████▌ | 14/195 [00:16<02:24, 1.26it/s] [2024-03-18 19:57:47] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 7%|██████▌ | 14/195 [00:16<02:24, 1.26it/s] 8%|███████ | 15/195 [00:16<02:20, 1.28it/s] [2024-03-18 19:57:47] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (4096,), dtype: float32 8%|███████ | 15/195 [00:16<02:20, 1.28it/s] [2024-03-18 19:57:48] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 8%|███████ | 15/195 [00:16<02:20, 1.28it/s] [2024-03-18 19:57:48] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 8%|███████ | 15/195 [00:16<02:20, 1.28it/s] 9%|███████▉ | 17/195 [00:16<01:53, 1.57it/s] [2024-03-18 19:57:48] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 9%|███████▉ | 17/195 [00:17<01:53, 1.57it/s] [2024-03-18 19:57:48] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 9%|███████▉ | 17/195 [00:17<01:53, 1.57it/s] 9%|████████▍ | 18/195 [00:17<01:39, 1.78it/s] [2024-03-18 19:57:48] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (4096,), dtype: float32 9%|████████▍ | 18/195 [00:17<01:39, 1.78it/s] [2024-03-18 19:57:50] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 9%|████████▍ | 18/195 [00:18<01:39, 1.78it/s] [2024-03-18 19:57:50] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 9%|████████▍ | 18/195 [00:18<01:39, 1.78it/s] 10%|█████████▎ | 20/195 [00:18<01:57, 1.49it/s] [2024-03-18 19:57:51] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 10%|█████████▎ | 20/195 [00:19<01:57, 1.49it/s] [2024-03-18 19:57:51] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 10%|█████████▎ | 20/195 [00:19<01:57, 1.49it/s] 11%|█████████▊ | 21/195 [00:19<01:57, 1.48it/s] [2024-03-18 19:57:51] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (4096,), dtype: float32 11%|█████████▊ | 21/195 [00:19<01:57, 1.48it/s] [2024-03-18 19:57:52] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 11%|█████████▊ | 21/195 [00:20<01:57, 1.48it/s] [2024-03-18 19:57:52] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 11%|█████████▊ | 21/195 [00:20<01:57, 1.48it/s] 12%|██████████▋ | 23/195 [00:20<01:39, 1.73it/s] [2024-03-18 19:57:52] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 12%|██████████▋ | 23/195 [00:20<01:39, 1.73it/s] [2024-03-18 19:57:52] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 12%|██████████▋ | 23/195 [00:20<01:39, 1.73it/s] 12%|███████████▏ | 24/195 [00:20<01:29, 1.91it/s] [2024-03-18 19:57:52] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (4096,), dtype: float32 12%|███████████▏ | 24/195 [00:20<01:29, 1.91it/s] [2024-03-18 19:57:53] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 12%|███████████▏ | 24/195 [00:22<01:29, 1.91it/s] [2024-03-18 19:57:54] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 12%|███████████▏ | 24/195 [00:22<01:29, 1.91it/s] 13%|████████████▏ | 26/195 [00:22<01:46, 1.59it/s] [2024-03-18 19:57:54] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 13%|████████████▏ | 26/195 [00:23<01:46, 1.59it/s] [2024-03-18 19:57:54] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 13%|████████████▏ | 26/195 [00:23<01:46, 1.59it/s] 14%|████████████▌ | 27/195 [00:23<01:49, 1.53it/s] [2024-03-18 19:57:54] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (4096,), dtype: float32 14%|████████████▌ | 27/195 [00:23<01:49, 1.53it/s] [2024-03-18 19:57:55] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 14%|████████████▌ | 27/195 [00:24<01:49, 1.53it/s] [2024-03-18 19:57:55] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 14%|████████████▌ | 27/195 [00:24<01:49, 1.53it/s] 15%|█████████████▌ | 29/195 [00:24<01:41, 1.64it/s] [2024-03-18 19:57:56] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 15%|█████████████▌ | 29/195 [00:24<01:41, 1.64it/s] [2024-03-18 19:57:56] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 15%|█████████████▌ | 29/195 [00:24<01:41, 1.64it/s] 15%|██████████████ | 30/195 [00:24<01:28, 1.86it/s] [2024-03-18 19:57:56] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (4096,), dtype: float32 15%|██████████████ | 30/195 [00:24<01:28, 1.86it/s] [2024-03-18 19:57:57] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 15%|██████████████ | 30/195 [00:25<01:28, 1.86it/s] [2024-03-18 19:57:57] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 15%|██████████████ | 30/195 [00:26<01:28, 1.86it/s] 16%|██████████████▉ | 32/195 [00:26<01:46, 1.53it/s] [2024-03-18 19:57:58] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 16%|██████████████▉ | 32/195 [00:26<01:46, 1.53it/s] [2024-03-18 19:57:58] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 16%|██████████████▉ | 32/195 [00:26<01:46, 1.53it/s] 17%|███████████████▍ | 33/195 [00:26<01:50, 1.47it/s] [2024-03-18 19:57:58] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (4096,), dtype: float32 17%|███████████████▍ | 33/195 [00:26<01:50, 1.47it/s] [2024-03-18 19:57:59] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 17%|███████████████▍ | 33/195 [00:27<01:50, 1.47it/s] [2024-03-18 19:57:59] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 17%|███████████████▍ | 33/195 [00:27<01:50, 1.47it/s] 18%|████████████████▎ | 35/195 [00:27<01:31, 1.75it/s] [2024-03-18 19:57:59] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 18%|████████████████▎ | 35/195 [00:27<01:31, 1.75it/s] [2024-03-18 19:57:59] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 18%|████████████████▎ | 35/195 [00:28<01:31, 1.75it/s] 18%|████████████████▊ | 36/195 [00:28<01:21, 1.94it/s] [2024-03-18 19:57:59] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (4096,), dtype: float32 18%|████████████████▊ | 36/195 [00:28<01:21, 1.94it/s] [2024-03-18 19:58:01] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 18%|████████████████▊ | 36/195 [00:29<01:21, 1.94it/s] [2024-03-18 19:58:01] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 18%|████████████████▊ | 36/195 [00:29<01:21, 1.94it/s] 19%|█████████████████▋ | 38/195 [00:29<01:38, 1.59it/s] [2024-03-18 19:58:02] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 19%|█████████████████▋ | 38/195 [00:30<01:38, 1.59it/s] [2024-03-18 19:58:02] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 19%|█████████████████▋ | 38/195 [00:30<01:38, 1.59it/s] 20%|██████████████████▏ | 39/195 [00:30<01:41, 1.54it/s] [2024-03-18 19:58:02] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (4096,), dtype: float32 20%|██████████████████▏ | 39/195 [00:30<01:41, 1.54it/s] [2024-03-18 19:58:02] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 20%|██████████████████▏ | 39/195 [00:31<01:41, 1.54it/s] [2024-03-18 19:58:02] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 20%|██████████████████▏ | 39/195 [00:31<01:41, 1.54it/s] 21%|███████████████████▏ | 41/195 [00:31<01:25, 1.79it/s] [2024-03-18 19:58:03] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 21%|███████████████████▏ | 41/195 [00:31<01:25, 1.79it/s] [2024-03-18 19:58:03] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 21%|███████████████████▏ | 41/195 [00:31<01:25, 1.79it/s] 22%|███████████████████▌ | 42/195 [00:31<01:15, 2.03it/s] [2024-03-18 19:58:03] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (4096,), dtype: float32 22%|███████████████████▌ | 42/195 [00:31<01:15, 2.03it/s] [2024-03-18 19:58:04] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 22%|███████████████████▌ | 42/195 [00:32<01:15, 2.03it/s] [2024-03-18 19:58:04] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 22%|███████████████████▌ | 42/195 [00:32<01:15, 2.03it/s] 23%|████████████████████▌ | 44/195 [00:33<01:30, 1.68it/s] [2024-03-18 19:58:05] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 23%|████████████████████▌ | 44/195 [00:33<01:30, 1.68it/s] [2024-03-18 19:58:05] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 23%|████████████████████▌ | 44/195 [00:33<01:30, 1.68it/s] 23%|█████████████████████ | 45/195 [00:33<01:35, 1.56it/s] [2024-03-18 19:58:05] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (4096,), dtype: float32 23%|█████████████████████ | 45/195 [00:33<01:35, 1.56it/s] [2024-03-18 19:58:06] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 23%|█████████████████████ | 45/195 [00:34<01:35, 1.56it/s] [2024-03-18 19:58:06] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 23%|█████████████████████ | 45/195 [00:34<01:35, 1.56it/s] 24%|█████████████████████▉ | 47/195 [00:34<01:20, 1.84it/s] [2024-03-18 19:58:06] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 24%|█████████████████████▉ | 47/195 [00:34<01:20, 1.84it/s] [2024-03-18 19:58:06] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 24%|█████████████████████▉ | 47/195 [00:34<01:20, 1.84it/s] 25%|██████████████████████▍ | 48/195 [00:34<01:12, 2.02it/s] [2024-03-18 19:58:06] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (4096,), dtype: float32 25%|██████████████████████▍ | 48/195 [00:34<01:12, 2.02it/s] [2024-03-18 19:58:07] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 25%|██████████████████████▍ | 48/195 [00:36<01:12, 2.02it/s] [2024-03-18 19:58:08] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 25%|██████████████████████▍ | 48/195 [00:36<01:12, 2.02it/s] 26%|███████████████████████▎ | 50/195 [00:36<01:28, 1.64it/s] [2024-03-18 19:58:08] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 26%|███████████████████████▎ | 50/195 [00:37<01:28, 1.64it/s] [2024-03-18 19:58:08] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 26%|███████████████████████▎ | 50/195 [00:37<01:28, 1.64it/s] 26%|███████████████████████▊ | 51/195 [00:37<01:31, 1.58it/s] [2024-03-18 19:58:08] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (4096,), dtype: float32 26%|███████████████████████▊ | 51/195 [00:37<01:31, 1.58it/s] [2024-03-18 19:58:09] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 26%|███████████████████████▊ | 51/195 [00:37<01:31, 1.58it/s] [2024-03-18 19:58:09] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 26%|███████████████████████▊ | 51/195 [00:38<01:31, 1.58it/s] 27%|████████████████████████▋ | 53/195 [00:38<01:17, 1.83it/s] [2024-03-18 19:58:09] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 27%|████████████████████████▋ | 53/195 [00:38<01:17, 1.83it/s] [2024-03-18 19:58:09] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 27%|████████████████████████▋ | 53/195 [00:38<01:17, 1.83it/s] 28%|█████████████████████████▏ | 54/195 [00:38<01:08, 2.07it/s] [2024-03-18 19:58:09] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (4096,), dtype: float32 28%|█████████████████████████▏ | 54/195 [00:38<01:08, 2.07it/s] [2024-03-18 19:58:11] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 28%|█████████████████████████▏ | 54/195 [00:39<01:08, 2.07it/s] [2024-03-18 19:58:11] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 28%|█████████████████████████▏ | 54/195 [00:39<01:08, 2.07it/s] 29%|██████████████████████████▏ | 56/195 [00:39<01:21, 1.71it/s] [2024-03-18 19:58:12] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 29%|██████████████████████████▏ | 56/195 [00:40<01:21, 1.71it/s] [2024-03-18 19:58:12] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 29%|██████████████████████████▏ | 56/195 [00:40<01:21, 1.71it/s] 29%|██████████████████████████▌ | 57/195 [00:40<01:26, 1.59it/s] [2024-03-18 19:58:12] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (4096,), dtype: float32 29%|██████████████████████████▌ | 57/195 [00:40<01:26, 1.59it/s] [2024-03-18 19:58:12] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 29%|██████████████████████████▌ | 57/195 [00:41<01:26, 1.59it/s] [2024-03-18 19:58:13] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 29%|██████████████████████████▌ | 57/195 [00:41<01:26, 1.59it/s] 30%|███████████████████████████▌ | 59/195 [00:41<01:13, 1.85it/s] [2024-03-18 19:58:13] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 30%|███████████████████████████▌ | 59/195 [00:41<01:13, 1.85it/s] [2024-03-18 19:58:13] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 30%|███████████████████████████▌ | 59/195 [00:41<01:13, 1.85it/s] 31%|████████████████████████████ | 60/195 [00:41<01:06, 2.04it/s] [2024-03-18 19:58:13] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (4096,), dtype: float32 31%|████████████████████████████ | 60/195 [00:41<01:06, 2.04it/s] [2024-03-18 19:58:14] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 31%|████████████████████████████ | 60/195 [00:42<01:06, 2.04it/s] [2024-03-18 19:58:14] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 31%|████████████████████████████ | 60/195 [00:43<01:06, 2.04it/s] 32%|████████████████████████████▉ | 62/195 [00:43<01:19, 1.68it/s] [2024-03-18 19:58:15] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 32%|████████████████████████████▉ | 62/195 [00:43<01:19, 1.68it/s] [2024-03-18 19:58:15] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 32%|████████████████████████████▉ | 62/195 [00:43<01:19, 1.68it/s] 32%|█████████████████████████████▍ | 63/195 [00:43<01:22, 1.59it/s] [2024-03-18 19:58:15] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (4096,), dtype: float32 32%|█████████████████████████████▍ | 63/195 [00:43<01:22, 1.59it/s] [2024-03-18 19:58:16] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 32%|█████████████████████████████▍ | 63/195 [00:44<01:22, 1.59it/s] [2024-03-18 19:58:16] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 32%|█████████████████████████████▍ | 63/195 [00:44<01:22, 1.59it/s] 33%|██████████████████████████████▎ | 65/195 [00:44<01:11, 1.82it/s] [2024-03-18 19:58:16] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 33%|██████████████████████████████▎ | 65/195 [00:45<01:11, 1.82it/s] [2024-03-18 19:58:16] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 33%|██████████████████████████████▎ | 65/195 [00:45<01:11, 1.82it/s] 34%|██████████████████████████████▊ | 66/195 [00:45<01:03, 2.05it/s] [2024-03-18 19:58:16] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (4096,), dtype: float32 34%|██████████████████████████████▊ | 66/195 [00:45<01:03, 2.05it/s] [2024-03-18 19:58:18] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 34%|██████████████████████████████▊ | 66/195 [00:46<01:03, 2.05it/s] [2024-03-18 19:58:18] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 34%|██████████████████████████████▊ | 66/195 [00:46<01:03, 2.05it/s] 35%|███████████████████████████████▋ | 68/195 [00:46<01:21, 1.56it/s] [2024-03-18 19:58:19] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 35%|███████████████████████████████▋ | 68/195 [00:47<01:21, 1.56it/s] [2024-03-18 19:58:19] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 35%|███████████████████████████████▋ | 68/195 [00:47<01:21, 1.56it/s] 35%|████████████████████████████████▏ | 69/195 [00:47<01:29, 1.40it/s] [2024-03-18 19:58:19] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (4096,), dtype: float32 35%|████████████████████████████████▏ | 69/195 [00:47<01:29, 1.40it/s] [2024-03-18 19:58:20] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 35%|████████████████████████████████▏ | 69/195 [00:48<01:29, 1.40it/s] [2024-03-18 19:58:20] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 35%|████████████████████████████████▏ | 69/195 [00:48<01:29, 1.40it/s] 36%|█████████████████████████████████▏ | 71/195 [00:48<01:12, 1.70it/s] [2024-03-18 19:58:20] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 36%|█████████████████████████████████▏ | 71/195 [00:48<01:12, 1.70it/s] [2024-03-18 19:58:20] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 36%|█████████████████████████████████▏ | 71/195 [00:48<01:12, 1.70it/s] 37%|█████████████████████████████████▌ | 72/195 [00:48<01:05, 1.89it/s] [2024-03-18 19:58:20] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (4096,), dtype: float32 37%|█████████████████████████████████▌ | 72/195 [00:48<01:05, 1.89it/s] [2024-03-18 19:58:21] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 37%|█████████████████████████████████▌ | 72/195 [00:50<01:05, 1.89it/s] [2024-03-18 19:58:22] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 37%|█████████████████████████████████▌ | 72/195 [00:50<01:05, 1.89it/s] 38%|██████████████████████████████████▌ | 74/195 [00:50<01:15, 1.61it/s] [2024-03-18 19:58:22] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 38%|██████████████████████████████████▌ | 74/195 [00:51<01:15, 1.61it/s] [2024-03-18 19:58:22] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 38%|██████████████████████████████████▌ | 74/195 [00:51<01:15, 1.61it/s] 38%|███████████████████████████████████ | 75/195 [00:51<01:16, 1.56it/s] [2024-03-18 19:58:22] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (4096,), dtype: float32 38%|███████████████████████████████████ | 75/195 [00:51<01:16, 1.56it/s] [2024-03-18 19:58:23] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 38%|███████████████████████████████████ | 75/195 [00:51<01:16, 1.56it/s] [2024-03-18 19:58:23] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 38%|███████████████████████████████████ | 75/195 [00:51<01:16, 1.56it/s] 39%|███████████████████████████████████▉ | 77/195 [00:51<01:05, 1.81it/s] [2024-03-18 19:58:23] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 39%|███████████████████████████████████▉ | 77/195 [00:52<01:05, 1.81it/s] [2024-03-18 19:58:23] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 39%|███████████████████████████████████▉ | 77/195 [00:52<01:05, 1.81it/s] 40%|████████████████████████████████████▍ | 78/195 [00:52<00:57, 2.05it/s] [2024-03-18 19:58:23] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (4096,), dtype: float32 40%|████████████████████████████████████▍ | 78/195 [00:52<00:57, 2.05it/s] [2024-03-18 19:58:25] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 40%|████████████████████████████████████▍ | 78/195 [00:53<00:57, 2.05it/s] [2024-03-18 19:58:25] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 40%|████████████████████████████████████▍ | 78/195 [00:53<00:57, 2.05it/s] 41%|█████████████████████████████████████▎ | 80/195 [00:53<01:08, 1.69it/s] [2024-03-18 19:58:26] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 41%|█████████████████████████████████████▎ | 80/195 [00:54<01:08, 1.69it/s] [2024-03-18 19:58:26] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 41%|█████████████████████████████████████▎ | 80/195 [00:54<01:08, 1.69it/s] 42%|█████████████████████████████████████▊ | 81/195 [00:54<01:12, 1.58it/s] [2024-03-18 19:58:26] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (4096,), dtype: float32 42%|█████████████████████████████████████▊ | 81/195 [00:54<01:12, 1.58it/s] [2024-03-18 19:58:26] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 42%|█████████████████████████████████████▊ | 81/195 [00:55<01:12, 1.58it/s] [2024-03-18 19:58:26] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 42%|█████████████████████████████████████▊ | 81/195 [00:55<01:12, 1.58it/s] 43%|██████████████████████████████████████▋ | 83/195 [00:55<01:00, 1.85it/s] [2024-03-18 19:58:27] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 43%|██████████████████████████████████████▋ | 83/195 [00:55<01:00, 1.85it/s] [2024-03-18 19:58:27] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 43%|██████████████████████████████████████▋ | 83/195 [00:55<01:00, 1.85it/s] 43%|███████████████████████████████████████▏ | 84/195 [00:55<00:54, 2.04it/s] [2024-03-18 19:58:27] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (4096,), dtype: float32 43%|███████████████████████████████████████▏ | 84/195 [00:55<00:54, 2.04it/s] [2024-03-18 19:58:28] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 43%|███████████████████████████████████████▏ | 84/195 [00:56<00:54, 2.04it/s] [2024-03-18 19:58:28] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 43%|███████████████████████████████████████▏ | 84/195 [00:57<00:54, 2.04it/s] 44%|████████████████████████████████████████▏ | 86/195 [00:57<01:05, 1.66it/s] [2024-03-18 19:58:29] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 44%|████████████████████████████████████████▏ | 86/195 [00:57<01:05, 1.66it/s] [2024-03-18 19:58:29] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 44%|████████████████████████████████████████▏ | 86/195 [00:57<01:05, 1.66it/s] 45%|████████████████████████████████████████▌ | 87/195 [00:57<01:07, 1.60it/s] [2024-03-18 19:58:29] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (4096,), dtype: float32 45%|████████████████████████████████████████▌ | 87/195 [00:57<01:07, 1.60it/s] [2024-03-18 19:58:30] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 45%|████████████████████████████████████████▌ | 87/195 [00:58<01:07, 1.60it/s] [2024-03-18 19:58:30] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 45%|████████████████████████████████████████▌ | 87/195 [00:58<01:07, 1.60it/s] 46%|█████████████████████████████████████████▌ | 89/195 [00:58<00:57, 1.83it/s] [2024-03-18 19:58:30] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 46%|█████████████████████████████████████████▌ | 89/195 [00:58<00:57, 1.83it/s] [2024-03-18 19:58:30] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 46%|█████████████████████████████████████████▌ | 89/195 [00:58<00:57, 1.83it/s] 46%|██████████████████████████████████████████ | 90/195 [00:58<00:51, 2.05it/s] [2024-03-18 19:58:30] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (4096,), dtype: float32 46%|██████████████████████████████████████████ | 90/195 [00:58<00:51, 2.05it/s] [2024-03-18 19:58:31] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 46%|██████████████████████████████████████████ | 90/195 [01:00<00:51, 2.05it/s] [2024-03-18 19:58:32] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 46%|██████████████████████████████████████████ | 90/195 [01:00<00:51, 2.05it/s] 47%|██████████████████████████████████████████▉ | 92/195 [01:00<01:00, 1.70it/s] [2024-03-18 19:58:32] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 47%|██████████████████████████████████████████▉ | 92/195 [01:01<01:00, 1.70it/s] [2024-03-18 19:58:32] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 47%|██████████████████████████████████████████▉ | 92/195 [01:01<01:00, 1.70it/s] 48%|███████████████████████████████████████████▍ | 93/195 [01:01<01:03, 1.60it/s] [2024-03-18 19:58:32] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (4096,), dtype: float32 48%|███████████████████████████████████████████▍ | 93/195 [01:01<01:03, 1.60it/s] [2024-03-18 19:58:33] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 48%|███████████████████████████████████████████▍ | 93/195 [01:01<01:03, 1.60it/s] [2024-03-18 19:58:33] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 48%|███████████████████████████████████████████▍ | 93/195 [01:02<01:03, 1.60it/s] 49%|████████████████████████████████████████████▎ | 95/195 [01:02<00:53, 1.87it/s] [2024-03-18 19:58:33] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 49%|████████████████████████████████████████████▎ | 95/195 [01:02<00:53, 1.87it/s] [2024-03-18 19:58:34] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 49%|████████████████████████████████████████████▎ | 95/195 [01:02<00:53, 1.87it/s] 49%|████████████████████████████████████████████▊ | 96/195 [01:02<00:48, 2.05it/s] [2024-03-18 19:58:34] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (4096,), dtype: float32 49%|████████████████████████████████████████████▊ | 96/195 [01:02<00:48, 2.05it/s] [2024-03-18 19:58:35] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 49%|████████████████████████████████████████████▊ | 96/195 [01:03<00:48, 2.05it/s] [2024-03-18 19:58:35] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 49%|████████████████████████████████████████████▊ | 96/195 [01:03<00:48, 2.05it/s] 50%|█████████████████████████████████████████████▋ | 98/195 [01:03<00:56, 1.72it/s] [2024-03-18 19:58:36] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 50%|█████████████████████████████████████████████▋ | 98/195 [01:04<00:56, 1.72it/s] [2024-03-18 19:58:36] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 50%|█████████████████████████████████████████████▋ | 98/195 [01:04<00:56, 1.72it/s] 51%|██████████████████████████████████████████████▏ | 99/195 [01:04<00:58, 1.65it/s] [2024-03-18 19:58:36] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (4096,), dtype: float32 51%|██████████████████████████████████████████████▏ | 99/195 [01:04<00:58, 1.65it/s] [2024-03-18 19:58:36] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 51%|██████████████████████████████████████████████▏ | 99/195 [01:05<00:58, 1.65it/s] [2024-03-18 19:58:37] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 51%|██████████████████████████████████████████████▏ | 99/195 [01:05<00:58, 1.65it/s] 52%|██████████████████████████████████████████████▌ | 101/195 [01:05<00:50, 1.87it/s] [2024-03-18 19:58:37] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 52%|██████████████████████████████████████████████▌ | 101/195 [01:05<00:50, 1.87it/s] [2024-03-18 19:58:37] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 52%|██████████████████████████████████████████████▌ | 101/195 [01:05<00:50, 1.87it/s] 52%|███████████████████████████████████████████████ | 102/195 [01:05<00:44, 2.10it/s] [2024-03-18 19:58:37] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (4096,), dtype: float32 52%|███████████████████████████████████████████████ | 102/195 [01:05<00:44, 2.10it/s] [2024-03-18 19:58:38] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 52%|███████████████████████████████████████████████ | 102/195 [01:06<00:44, 2.10it/s] [2024-03-18 19:58:38] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 52%|███████████████████████████████████████████████ | 102/195 [01:07<00:44, 2.10it/s] 53%|████████████████████████████████████████████████ | 104/195 [01:07<00:53, 1.71it/s] [2024-03-18 19:58:39] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 53%|████████████████████████████████████████████████ | 104/195 [01:07<00:53, 1.71it/s] [2024-03-18 19:58:39] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 53%|████████████████████████████████████████████████ | 104/195 [01:07<00:53, 1.71it/s] 54%|████████████████████████████████████████████████▍ | 105/195 [01:07<00:56, 1.58it/s] [2024-03-18 19:58:39] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (4096,), dtype: float32 54%|████████████████████████████████████████████████▍ | 105/195 [01:07<00:56, 1.58it/s] [2024-03-18 19:58:40] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 54%|████████████████████████████████████████████████▍ | 105/195 [01:08<00:56, 1.58it/s] [2024-03-18 19:58:40] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 54%|████████████████████████████████████████████████▍ | 105/195 [01:08<00:56, 1.58it/s] 55%|█████████████████████████████████████████████████▍ | 107/195 [01:08<00:47, 1.85it/s] [2024-03-18 19:58:40] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 55%|█████████████████████████████████████████████████▍ | 107/195 [01:08<00:47, 1.85it/s] [2024-03-18 19:58:40] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 55%|█████████████████████████████████████████████████▍ | 107/195 [01:09<00:47, 1.85it/s] 55%|█████████████████████████████████████████████████▊ | 108/195 [01:09<00:42, 2.04it/s] [2024-03-18 19:58:40] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (4096,), dtype: float32 55%|█████████████████████████████████████████████████▊ | 108/195 [01:09<00:42, 2.04it/s] [2024-03-18 19:58:42] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 55%|█████████████████████████████████████████████████▊ | 108/195 [01:10<00:42, 2.04it/s] [2024-03-18 19:58:42] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 55%|█████████████████████████████████████████████████▊ | 108/195 [01:10<00:42, 2.04it/s] 56%|██████████████████████████████████████████████████▊ | 110/195 [01:10<00:56, 1.50it/s] [2024-03-18 19:58:43] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 56%|██████████████████████████████████████████████████▊ | 110/195 [01:11<00:56, 1.50it/s] [2024-03-18 19:58:43] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 56%|██████████████████████████████████████████████████▊ | 110/195 [01:11<00:56, 1.50it/s] 57%|███████████████████████████████████████████████████▏ | 111/195 [01:11<00:56, 1.48it/s] [2024-03-18 19:58:43] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (4096,), dtype: float32 57%|███████████████████████████████████████████████████▏ | 111/195 [01:11<00:56, 1.48it/s] [2024-03-18 19:58:44] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 57%|███████████████████████████████████████████████████▏ | 111/195 [01:12<00:56, 1.48it/s] [2024-03-18 19:58:44] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 57%|███████████████████████████████████████████████████▏ | 111/195 [01:12<00:56, 1.48it/s] 58%|████████████████████████████████████████████████████▏ | 113/195 [01:12<00:47, 1.72it/s] [2024-03-18 19:58:44] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 58%|████████████████████████████████████████████████████▏ | 113/195 [01:12<00:47, 1.72it/s] [2024-03-18 19:58:44] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 58%|████████████████████████████████████████████████████▏ | 113/195 [01:12<00:47, 1.72it/s] 58%|████████████████████████████████████████████████████▌ | 114/195 [01:12<00:41, 1.95it/s] [2024-03-18 19:58:44] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (4096,), dtype: float32 58%|████████████████████████████████████████████████████▌ | 114/195 [01:12<00:41, 1.95it/s] [2024-03-18 19:58:45] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 58%|████████████████████████████████████████████████████▌ | 114/195 [01:14<00:41, 1.95it/s] [2024-03-18 19:58:45] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 58%|████████████████████████████████████████████████████▌ | 114/195 [01:14<00:41, 1.95it/s] 59%|█████████████████████████████████████████████████████▌ | 116/195 [01:14<00:47, 1.66it/s] [2024-03-18 19:58:46] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 59%|█████████████████████████████████████████████████████▌ | 116/195 [01:14<00:47, 1.66it/s] [2024-03-18 19:58:46] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 59%|█████████████████████████████████████████████████████▌ | 116/195 [01:14<00:47, 1.66it/s] 60%|██████████████████████████████████████████████████████ | 117/195 [01:15<00:49, 1.57it/s] [2024-03-18 19:58:46] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (4096,), dtype: float32 60%|██████████████████████████████████████████████████████ | 117/195 [01:15<00:49, 1.57it/s] [2024-03-18 19:58:47] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 60%|██████████████████████████████████████████████████████ | 117/195 [01:15<00:49, 1.57it/s] [2024-03-18 19:58:47] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 60%|██████████████████████████████████████████████████████ | 117/195 [01:15<00:49, 1.57it/s] 61%|██████████████████████████████████████████████████████▉ | 119/195 [01:15<00:41, 1.84it/s] [2024-03-18 19:58:47] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 61%|██████████████████████████████████████████████████████▉ | 119/195 [01:16<00:41, 1.84it/s] [2024-03-18 19:58:47] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 61%|██████████████████████████████████████████████████████▉ | 119/195 [01:16<00:41, 1.84it/s] 62%|███████████████████████████████████████████████████████▍ | 120/195 [01:16<00:37, 2.02it/s] [2024-03-18 19:58:47] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (4096,), dtype: float32 62%|███████████████████████████████████████████████████████▍ | 120/195 [01:16<00:37, 2.02it/s] [2024-03-18 19:58:49] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 62%|███████████████████████████████████████████████████████▍ | 120/195 [01:17<00:37, 2.02it/s] [2024-03-18 19:58:49] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 62%|███████████████████████████████████████████████████████▍ | 120/195 [01:17<00:37, 2.02it/s] 63%|████████████████████████████████████████████████████████▎ | 122/195 [01:17<00:44, 1.65it/s] [2024-03-18 19:58:49] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 63%|████████████████████████████████████████████████████████▎ | 122/195 [01:18<00:44, 1.65it/s] [2024-03-18 19:58:50] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 63%|████████████████████████████████████████████████████████▎ | 122/195 [01:18<00:44, 1.65it/s] 63%|████████████████████████████████████████████████████████▊ | 123/195 [01:18<00:44, 1.60it/s] [2024-03-18 19:58:50] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (4096,), dtype: float32 63%|████████████████████████████████████████████████████████▊ | 123/195 [01:18<00:44, 1.60it/s] [2024-03-18 19:58:50] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 63%|████████████████████████████████████████████████████████▊ | 123/195 [01:19<00:44, 1.60it/s] [2024-03-18 19:58:50] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 63%|████████████████████████████████████████████████████████▊ | 123/195 [01:19<00:44, 1.60it/s] 64%|█████████████████████████████████████████████████████████▋ | 125/195 [01:19<00:37, 1.84it/s] [2024-03-18 19:58:51] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 64%|█████████████████████████████████████████████████████████▋ | 125/195 [01:19<00:37, 1.84it/s] [2024-03-18 19:58:51] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 64%|█████████████████████████████████████████████████████████▋ | 125/195 [01:19<00:37, 1.84it/s] 65%|██████████████████████████████████████████████████████████▏ | 126/195 [01:19<00:33, 2.08it/s] [2024-03-18 19:58:51] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (4096,), dtype: float32 65%|██████████████████████████████████████████████████████████▏ | 126/195 [01:19<00:33, 2.08it/s] [2024-03-18 19:58:52] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 65%|██████████████████████████████████████████████████████████▏ | 126/195 [01:20<00:33, 2.08it/s] [2024-03-18 19:58:52] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 65%|██████████████████████████████████████████████████████████▏ | 126/195 [01:20<00:33, 2.08it/s] 66%|███████████████████████████████████████████████████████████ | 128/195 [01:20<00:39, 1.72it/s] [2024-03-18 19:58:53] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 66%|███████████████████████████████████████████████████████████ | 128/195 [01:21<00:39, 1.72it/s] [2024-03-18 19:58:53] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 66%|███████████████████████████████████████████████████████████ | 128/195 [01:21<00:39, 1.72it/s] 66%|███████████████████████████████████████████████████████████▌ | 129/195 [01:21<00:41, 1.59it/s] [2024-03-18 19:58:53] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (4096,), dtype: float32 66%|███████████████████████████████████████████████████████████▌ | 129/195 [01:21<00:41, 1.59it/s] [2024-03-18 19:58:54] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 66%|███████████████████████████████████████████████████████████▌ | 129/195 [01:22<00:41, 1.59it/s] [2024-03-18 19:58:54] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 66%|███████████████████████████████████████████████████████████▌ | 129/195 [01:22<00:41, 1.59it/s] 67%|████████████████████████████████████████████████████████████▍ | 131/195 [01:22<00:35, 1.81it/s] [2024-03-18 19:58:54] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 67%|████████████████████████████████████████████████████████████▍ | 131/195 [01:22<00:35, 1.81it/s] [2024-03-18 19:58:54] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 67%|████████████████████████████████████████████████████████████▍ | 131/195 [01:22<00:35, 1.81it/s] 68%|████████████████████████████████████████████████████████████▉ | 132/195 [01:22<00:31, 1.99it/s] [2024-03-18 19:58:54] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (4096,), dtype: float32 68%|████████████████████████████████████████████████████████████▉ | 132/195 [01:22<00:31, 1.99it/s] [2024-03-18 19:58:55] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 68%|████████████████████████████████████████████████████████████▉ | 132/195 [01:24<00:31, 1.99it/s] [2024-03-18 19:58:56] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 68%|████████████████████████████████████████████████████████████▉ | 132/195 [01:24<00:31, 1.99it/s] 69%|█████████████████████████████████████████████████████████████▊ | 134/195 [01:24<00:36, 1.68it/s] [2024-03-18 19:58:56] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 69%|█████████████████████████████████████████████████████████████▊ | 134/195 [01:25<00:36, 1.68it/s] [2024-03-18 19:58:56] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 69%|█████████████████████████████████████████████████████████████▊ | 134/195 [01:25<00:36, 1.68it/s] 69%|██████████████████████████████████████████████████████████████▎ | 135/195 [01:25<00:37, 1.61it/s] [2024-03-18 19:58:56] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (4096,), dtype: float32 69%|██████████████████████████████████████████████████████████████▎ | 135/195 [01:25<00:37, 1.61it/s] [2024-03-18 19:58:57] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 69%|██████████████████████████████████████████████████████████████▎ | 135/195 [01:25<00:37, 1.61it/s] [2024-03-18 19:58:57] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 69%|██████████████████████████████████████████████████████████████▎ | 135/195 [01:25<00:37, 1.61it/s] 70%|███████████████████████████████████████████████████████████████▏ | 137/195 [01:25<00:31, 1.85it/s] [2024-03-18 19:58:57] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 70%|███████████████████████████████████████████████████████████████▏ | 137/195 [01:26<00:31, 1.85it/s] [2024-03-18 19:58:57] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 70%|███████████████████████████████████████████████████████████████▏ | 137/195 [01:26<00:31, 1.85it/s] 71%|███████████████████████████████████████████████████████████████▋ | 138/195 [01:26<00:27, 2.08it/s] [2024-03-18 19:58:57] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (4096,), dtype: float32 71%|███████████████████████████████████████████████████████████████▋ | 138/195 [01:26<00:27, 2.08it/s] [2024-03-18 19:58:59] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 71%|███████████████████████████████████████████████████████████████▋ | 138/195 [01:27<00:27, 2.08it/s] [2024-03-18 19:58:59] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 71%|███████████████████████████████████████████████████████████████▋ | 138/195 [01:27<00:27, 2.08it/s] 72%|████████████████████████████████████████████████████████████████▌ | 140/195 [01:27<00:32, 1.70it/s] [2024-03-18 19:59:00] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 72%|████████████████████████████████████████████████████████████████▌ | 140/195 [01:28<00:32, 1.70it/s] [2024-03-18 19:59:00] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 72%|████████████████████████████████████████████████████████████████▌ | 140/195 [01:28<00:32, 1.70it/s] 72%|█████████████████████████████████████████████████████████████████ | 141/195 [01:28<00:34, 1.58it/s] [2024-03-18 19:59:00] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (4096,), dtype: float32 72%|█████████████████████████████████████████████████████████████████ | 141/195 [01:28<00:34, 1.58it/s] [2024-03-18 19:59:00] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 72%|█████████████████████████████████████████████████████████████████ | 141/195 [01:29<00:34, 1.58it/s] [2024-03-18 19:59:01] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 72%|█████████████████████████████████████████████████████████████████ | 141/195 [01:29<00:34, 1.58it/s] 73%|██████████████████████████████████████████████████████████████████ | 143/195 [01:29<00:28, 1.85it/s] [2024-03-18 19:59:01] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 73%|██████████████████████████████████████████████████████████████████ | 143/195 [01:29<00:28, 1.85it/s] [2024-03-18 19:59:01] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 73%|██████████████████████████████████████████████████████████████████ | 143/195 [01:29<00:28, 1.85it/s] 74%|██████████████████████████████████████████████████████████████████▍ | 144/195 [01:29<00:24, 2.05it/s] [2024-03-18 19:59:01] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (4096,), dtype: float32 74%|██████████████████████████████████████████████████████████████████▍ | 144/195 [01:29<00:24, 2.05it/s] [2024-03-18 19:59:02] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 74%|██████████████████████████████████████████████████████████████████▍ | 144/195 [01:30<00:24, 2.05it/s] [2024-03-18 19:59:02] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 74%|██████████████████████████████████████████████████████████████████▍ | 144/195 [01:31<00:24, 2.05it/s] 75%|███████████████████████████████████████████████████████████████████▍ | 146/195 [01:31<00:28, 1.71it/s] [2024-03-18 19:59:03] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 75%|███████████████████████████████████████████████████████████████████▍ | 146/195 [01:31<00:28, 1.71it/s] [2024-03-18 19:59:03] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 75%|███████████████████████████████████████████████████████████████████▍ | 146/195 [01:31<00:28, 1.71it/s] 75%|███████████████████████████████████████████████████████████████████▊ | 147/195 [01:31<00:30, 1.60it/s] [2024-03-18 19:59:03] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (4096,), dtype: float32 75%|███████████████████████████████████████████████████████████████████▊ | 147/195 [01:31<00:30, 1.60it/s] [2024-03-18 19:59:04] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 75%|███████████████████████████████████████████████████████████████████▊ | 147/195 [01:32<00:30, 1.60it/s] [2024-03-18 19:59:04] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 75%|███████████████████████████████████████████████████████████████████▊ | 147/195 [01:32<00:30, 1.60it/s] 76%|████████████████████████████████████████████████████████████████████▊ | 149/195 [01:32<00:26, 1.77it/s] [2024-03-18 19:59:04] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 76%|████████████████████████████████████████████████████████████████████▊ | 149/195 [01:33<00:26, 1.77it/s] [2024-03-18 19:59:04] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 76%|████████████████████████████████████████████████████████████████████▊ | 149/195 [01:33<00:26, 1.77it/s] 77%|█████████████████████████████████████████████████████████████████████▏ | 150/195 [01:33<00:22, 1.98it/s] [2024-03-18 19:59:04] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (4096,), dtype: float32 77%|█████████████████████████████████████████████████████████████████████▏ | 150/195 [01:33<00:22, 1.98it/s] [2024-03-18 19:59:06] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 77%|█████████████████████████████████████████████████████████████████████▏ | 150/195 [01:34<00:22, 1.98it/s] [2024-03-18 19:59:06] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 77%|█████████████████████████████████████████████████████████████████████▏ | 150/195 [01:34<00:22, 1.98it/s] 78%|██████████████████████████████████████████████████████████████████████▏ | 152/195 [01:34<00:26, 1.64it/s] [2024-03-18 19:59:06] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 78%|██████████████████████████████████████████████████████████████████████▏ | 152/195 [01:35<00:26, 1.64it/s] [2024-03-18 19:59:07] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 78%|██████████████████████████████████████████████████████████████████████▏ | 152/195 [01:35<00:26, 1.64it/s] 78%|██████████████████████████████████████████████████████████████████████▌ | 153/195 [01:35<00:27, 1.54it/s] [2024-03-18 19:59:07] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (4096,), dtype: float32 78%|██████████████████████████████████████████████████████████████████████▌ | 153/195 [01:35<00:27, 1.54it/s] [2024-03-18 19:59:07] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 78%|██████████████████████████████████████████████████████████████████████▌ | 153/195 [01:36<00:27, 1.54it/s] [2024-03-18 19:59:07] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 78%|██████████████████████████████████████████████████████████████████████▌ | 153/195 [01:36<00:27, 1.54it/s] 79%|███████████████████████████████████████████████████████████████████████▌ | 155/195 [01:36<00:21, 1.82it/s] [2024-03-18 19:59:08] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 79%|███████████████████████████████████████████████████████████████████████▌ | 155/195 [01:36<00:21, 1.82it/s] [2024-03-18 19:59:08] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 79%|███████████████████████████████████████████████████████████████████████▌ | 155/195 [01:36<00:21, 1.82it/s] 80%|████████████████████████████████████████████████████████████████████████ | 156/195 [01:36<00:19, 1.99it/s] [2024-03-18 19:59:08] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (4096,), dtype: float32 80%|████████████████████████████████████████████████████████████████████████ | 156/195 [01:36<00:19, 1.99it/s] [2024-03-18 19:59:09] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 80%|████████████████████████████████████████████████████████████████████████ | 156/195 [01:37<00:19, 1.99it/s] [2024-03-18 19:59:09] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 80%|████████████████████████████████████████████████████████████████████████ | 156/195 [01:38<00:19, 1.99it/s] 81%|████████████████████████████████████████████████████████████████████████▉ | 158/195 [01:38<00:22, 1.66it/s] [2024-03-18 19:59:10] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 81%|████████████████████████████████████████████████████████████████████████▉ | 158/195 [01:38<00:22, 1.66it/s] [2024-03-18 19:59:10] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 81%|████████████████████████████████████████████████████████████████████████▉ | 158/195 [01:38<00:22, 1.66it/s] 82%|█████████████████████████████████████████████████████████████████████████▍ | 159/195 [01:38<00:22, 1.59it/s] [2024-03-18 19:59:10] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (4096,), dtype: float32 82%|█████████████████████████████████████████████████████████████████████████▍ | 159/195 [01:38<00:22, 1.59it/s] [2024-03-18 19:59:11] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 82%|█████████████████████████████████████████████████████████████████████████▍ | 159/195 [01:39<00:22, 1.59it/s] [2024-03-18 19:59:11] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 82%|█████████████████████████████████████████████████████████████████████████▍ | 159/195 [01:39<00:22, 1.59it/s] 83%|██████████████████████████████████████████████████████████████████████████▎ | 161/195 [01:39<00:18, 1.84it/s] [2024-03-18 19:59:11] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 83%|██████████████████████████████████████████████████████████████████████████▎ | 161/195 [01:39<00:18, 1.84it/s] [2024-03-18 19:59:11] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 83%|██████████████████████████████████████████████████████████████████████████▎ | 161/195 [01:39<00:18, 1.84it/s] 83%|██████████████████████████████████████████████████████████████████████████▊ | 162/195 [01:39<00:15, 2.07it/s] [2024-03-18 19:59:11] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (4096,), dtype: float32 83%|██████████████████████████████████████████████████████████████████████████▊ | 162/195 [01:39<00:15, 2.07it/s] [2024-03-18 19:59:12] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 83%|██████████████████████████████████████████████████████████████████████████▊ | 162/195 [01:41<00:15, 2.07it/s] [2024-03-18 19:59:13] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 83%|██████████████████████████████████████████████████████████████████████████▊ | 162/195 [01:41<00:15, 2.07it/s] 84%|███████████████████████████████████████████████████████████████████████████▋ | 164/195 [01:41<00:18, 1.68it/s] [2024-03-18 19:59:13] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 84%|███████████████████████████████████████████████████████████████████████████▋ | 164/195 [01:42<00:18, 1.68it/s] [2024-03-18 19:59:13] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 84%|███████████████████████████████████████████████████████████████████████████▋ | 164/195 [01:42<00:18, 1.68it/s] 85%|████████████████████████████████████████████████████████████████████████████▏ | 165/195 [01:42<00:19, 1.58it/s] [2024-03-18 19:59:13] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (4096,), dtype: float32 85%|████████████████████████████████████████████████████████████████████████████▏ | 165/195 [01:42<00:19, 1.58it/s] [2024-03-18 19:59:14] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 85%|████████████████████████████████████████████████████████████████████████████▏ | 165/195 [01:42<00:19, 1.58it/s] [2024-03-18 19:59:14] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 85%|████████████████████████████████████████████████████████████████████████████▏ | 165/195 [01:42<00:19, 1.58it/s] 86%|█████████████████████████████████████████████████████████████████████████████ | 167/195 [01:42<00:15, 1.85it/s] [2024-03-18 19:59:14] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 86%|█████████████████████████████████████████████████████████████████████████████ | 167/195 [01:43<00:15, 1.85it/s] [2024-03-18 19:59:15] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 86%|█████████████████████████████████████████████████████████████████████████████ | 167/195 [01:43<00:15, 1.85it/s] 86%|█████████████████████████████████████████████████████████████████████████████▌ | 168/195 [01:43<00:13, 2.01it/s] [2024-03-18 19:59:15] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (4096,), dtype: float32 86%|█████████████████████████████████████████████████████████████████████████████▌ | 168/195 [01:43<00:13, 2.01it/s] [2024-03-18 19:59:16] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 86%|█████████████████████████████████████████████████████████████████████████████▌ | 168/195 [01:44<00:13, 2.01it/s] [2024-03-18 19:59:16] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 86%|█████████████████████████████████████████████████████████████████████████████▌ | 168/195 [01:44<00:13, 2.01it/s] 87%|██████████████████████████████████████████████████████████████████████████████▍ | 170/195 [01:44<00:14, 1.70it/s] [2024-03-18 19:59:17] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 87%|██████████████████████████████████████████████████████████████████████████████▍ | 170/195 [01:45<00:14, 1.70it/s] [2024-03-18 19:59:17] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 87%|██████████████████████████████████████████████████████████████████████████████▍ | 170/195 [01:45<00:14, 1.70it/s] 88%|██████████████████████████████████████████████████████████████████████████████▉ | 171/195 [01:45<00:14, 1.64it/s] [2024-03-18 19:59:17] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.28.input_layernorm.weight", shape: (4096,), dtype: float32 88%|██████████████████████████████████████████████████████████████████████████████▉ | 171/195 [01:45<00:14, 1.64it/s] [2024-03-18 19:59:17] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 88%|██████████████████████████████████████████████████████████████████████████████▉ | 171/195 [01:46<00:14, 1.64it/s] [2024-03-18 19:59:18] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 88%|██████████████████████████████████████████████████████████████████████████████▉ | 171/195 [01:46<00:14, 1.64it/s] 89%|███████████████████████████████████████████████████████████████████████████████▊ | 173/195 [01:46<00:11, 1.85it/s] [2024-03-18 19:59:18] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 89%|███████████████████████████████████████████████████████████████████████████████▊ | 173/195 [01:46<00:11, 1.85it/s] [2024-03-18 19:59:18] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 89%|███████████████████████████████████████████████████████████████████████████████▊ | 173/195 [01:46<00:11, 1.85it/s] 89%|████████████████████████████████████████████████████████████████████████████████▎ | 174/195 [01:46<00:10, 2.09it/s] [2024-03-18 19:59:18] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.28.post_attention_layernorm.weight", shape: (4096,), dtype: float32 89%|████████████████████████████████████████████████████████████████████████████████▎ | 174/195 [01:46<00:10, 2.09it/s] [2024-03-18 19:59:19] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 89%|████████████████████████████████████████████████████████████████████████████████▎ | 174/195 [01:47<00:10, 2.09it/s] [2024-03-18 19:59:19] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 89%|████████████████████████████████████████████████████████████████████████████████▎ | 174/195 [01:48<00:10, 2.09it/s] 90%|█████████████████████████████████████████████████████████████████████████████████▏ | 176/195 [01:48<00:11, 1.71it/s] [2024-03-18 19:59:20] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 90%|█████████████████████████████████████████████████████████████████████████████████▏ | 176/195 [01:48<00:11, 1.71it/s] [2024-03-18 19:59:20] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 90%|█████████████████████████████████████████████████████████████████████████████████▏ | 176/195 [01:48<00:11, 1.71it/s] 91%|█████████████████████████████████████████████████████████████████████████████████▋ | 177/195 [01:48<00:11, 1.59it/s] [2024-03-18 19:59:20] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.29.input_layernorm.weight", shape: (4096,), dtype: float32 91%|█████████████████████████████████████████████████████████████████████████████████▋ | 177/195 [01:48<00:11, 1.59it/s] [2024-03-18 19:59:21] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 91%|█████████████████████████████████████████████████████████████████████████████████▋ | 177/195 [01:49<00:11, 1.59it/s] [2024-03-18 19:59:21] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 91%|█████████████████████████████████████████████████████████████████████████████████▋ | 177/195 [01:49<00:11, 1.59it/s] 92%|██████████████████████████████████████████████████████████████████████████████████▌ | 179/195 [01:49<00:08, 1.86it/s] [2024-03-18 19:59:21] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 92%|██████████████████████████████████████████████████████████████████████████████████▌ | 179/195 [01:49<00:08, 1.86it/s] [2024-03-18 19:59:21] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 92%|██████████████████████████████████████████████████████████████████████████████████▌ | 179/195 [01:49<00:08, 1.86it/s] 92%|███████████████████████████████████████████████████████████████████████████████████ | 180/195 [01:49<00:07, 2.05it/s] [2024-03-18 19:59:21] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.29.post_attention_layernorm.weight", shape: (4096,), dtype: float32 92%|███████████████████████████████████████████████████████████████████████████████████ | 180/195 [01:49<00:07, 2.05it/s] [2024-03-18 19:59:22] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 92%|███████████████████████████████████████████████████████████████████████████████████ | 180/195 [01:51<00:07, 2.05it/s] [2024-03-18 19:59:23] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 92%|███████████████████████████████████████████████████████████████████████████████████ | 180/195 [01:51<00:07, 2.05it/s] 93%|████████████████████████████████████████████████████████████████████████████████████ | 182/195 [01:51<00:07, 1.72it/s] [2024-03-18 19:59:23] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 93%|████████████████████████████████████████████████████████████████████████████████████ | 182/195 [01:52<00:07, 1.72it/s] [2024-03-18 19:59:23] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 93%|████████████████████████████████████████████████████████████████████████████████████ | 182/195 [01:52<00:07, 1.72it/s] 94%|████████████████████████████████████████████████████████████████████████████████████▍ | 183/195 [01:52<00:07, 1.65it/s] [2024-03-18 19:59:23] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.30.input_layernorm.weight", shape: (4096,), dtype: float32 94%|████████████████████████████████████████████████████████████████████████████████████▍ | 183/195 [01:52<00:07, 1.65it/s] [2024-03-18 19:59:24] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 94%|████████████████████████████████████████████████████████████████████████████████████▍ | 183/195 [01:52<00:07, 1.65it/s] [2024-03-18 19:59:24] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 94%|████████████████████████████████████████████████████████████████████████████████████▍ | 183/195 [01:52<00:07, 1.65it/s] 95%|█████████████████████████████████████████████████████████████████████████████████████▍ | 185/195 [01:52<00:05, 1.86it/s] [2024-03-18 19:59:24] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 95%|█████████████████████████████████████████████████████████████████████████████████████▍ | 185/195 [01:53<00:05, 1.86it/s] [2024-03-18 19:59:24] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 95%|█████████████████████████████████████████████████████████████████████████████████████▍ | 185/195 [01:53<00:05, 1.86it/s] 95%|█████████████████████████████████████████████████████████████████████████████████████▊ | 186/195 [01:53<00:04, 2.09it/s] [2024-03-18 19:59:24] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.30.post_attention_layernorm.weight", shape: (4096,), dtype: float32 95%|█████████████████████████████████████████████████████████████████████████████████████▊ | 186/195 [01:53<00:04, 2.09it/s] [2024-03-18 19:59:26] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 95%|█████████████████████████████████████████████████████████████████████████████████████▊ | 186/195 [01:54<00:04, 2.09it/s] [2024-03-18 19:59:26] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 95%|█████████████████████████████████████████████████████████████████████████████████████▊ | 186/195 [01:54<00:04, 2.09it/s] 96%|██████████████████████████████████████████████████████████████████████████████████████▊ | 188/195 [01:54<00:04, 1.74it/s] [2024-03-18 19:59:27] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 96%|██████████████████████████████████████████████████████████████████████████████████████▊ | 188/195 [01:55<00:04, 1.74it/s] [2024-03-18 19:59:27] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 96%|██████████████████████████████████████████████████████████████████████████████████████▊ | 188/195 [01:55<00:04, 1.74it/s] 97%|███████████████████████████████████████████████████████████████████████████████████████▏ | 189/195 [01:55<00:03, 1.61it/s] [2024-03-18 19:59:27] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.31.input_layernorm.weight", shape: (4096,), dtype: float32 97%|███████████████████████████████████████████████████████████████████████████████████████▏ | 189/195 [01:55<00:03, 1.61it/s] [2024-03-18 19:59:27] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_weight", shape: (12288, 515), dtype: uint32 97%|███████████████████████████████████████████████████████████████████████████████████████▏ | 189/195 [01:56<00:03, 1.61it/s] [2024-03-18 19:59:28] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_scale", shape: (12288, 103), dtype: float32 97%|███████████████████████████████████████████████████████████████████████████████████████▏ | 189/195 [01:56<00:03, 1.61it/s] 98%|████████████████████████████████████████████████████████████████████████████████████████▏ | 191/195 [01:56<00:02, 1.84it/s] [2024-03-18 19:59:28] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_weight", shape: (4096, 515), dtype: uint32 98%|████████████████████████████████████████████████████████████████████████████████████████▏ | 191/195 [01:56<00:02, 1.84it/s] [2024-03-18 19:59:28] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_scale", shape: (4096, 103), dtype: float32 98%|████████████████████████████████████████████████████████████████████████████████████████▏ | 191/195 [01:56<00:02, 1.84it/s] 98%|████████████████████████████████████████████████████████████████████████████████████████▌ | 192/195 [01:56<00:01, 2.03it/s] [2024-03-18 19:59:28] INFO huggingface_loader.py:172: [Not quantized] Parameter: "model.layers.31.post_attention_layernorm.weight", shape: (4096,), dtype: float32 98%|████████████████████████████████████████████████████████████████████████████████████████▌ | 192/195 [01:56<00:01, 2.03it/s] [2024-03-18 19:59:29] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_weight", shape: (22016, 515), dtype: uint32 98%|████████████████████████████████████████████████████████████████████████████████████████▌ | 192/195 [01:57<00:01, 2.03it/s] [2024-03-18 19:59:29] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_scale", shape: (22016, 103), dtype: float32 98%|████████████████████████████████████████████████████████████████████████████████████████▌ | 192/195 [01:58<00:01, 2.03it/s] 99%|█████████████████████████████████████████████████████████████████████████████████████████▌| 194/195 [01:58<00:00, 1.67it/s] [2024-03-18 19:59:30] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_weight", shape: (4096, 1380), dtype: uint32 99%|█████████████████████████████████████████████████████████████████████████████████████████▌| 194/195 [01:58<00:00, 1.67it/s] [2024-03-18 19:59:30] INFO huggingface_loader.py:164: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_scale", shape: (4096, 276), dtype: float32 99%|█████████████████████████████████████████████████████████████████████████████████████████▌| 194/195 [01:58<00:00, 1.67it/s] 100%|██████████████████████████████████████████████████████████████████████████████████████████| 195/195 [01:58<00:00, 1.60it/s] 100%|██████████████████████████████████████████████████████████████████████████████████████████| 195/195 [01:58<00:00, 1.64it/s] [2024-03-18 19:59:30] INFO huggingface_loader.py:194: Unloading HF weight file: ../dist/models/XAgentLlama-7B-preview/pytorch_model.bin [2024-03-18 19:59:31] INFO stats.py:76: Time usage: HF loading: 30.817 sec; Pre-quantization mapping: 22.408 sec; Quantization: 3.776 sec [2024-03-18 19:59:31] INFO stats.py:90: RAM usage: Peak RAM: 12.552 GB. Total bytes loaded from disk: 12.552 GB [2024-03-18 19:59:31] INFO convert_weight.py:156: Parameter size after quantization: 3.786 GB [2024-03-18 19:59:31] INFO convert_weight.py:161: Total parameters: 6,738,546,688 [2024-03-18 19:59:31] INFO convert_weight.py:162: Bits per parameter: 4.826 [2024-03-18 19:59:31] INFO convert_weight.py:167: Saved to directory: /tmp/tmpq9jzxnoc All finished, 115 total shards committed, record saved to /tmp/tmpq9jzxnoc/ndarray-cache.json Also saved a bf16 record to /tmp/tmpq9jzxnoc/ndarray-cache-b16.json