Initial commit

83b361f verified over 2 years ago

250 kB

	/Users/cfruan/miniconda3/envs/mlc-chat-venv/bin/python -m mlc_chat gen_config /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo --quantization q4f32_1 --conv-template codellama_instruct --output /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpewt38rmf --context-window-size 16384
	[2024-01-30 00:33:39] INFO auto_config.py:115: [92mFound[0m model configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/config.json
	[2024-01-30 00:33:39] INFO auto_config.py:153: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override.
	[2024-01-30 00:33:39] INFO llama_model.py:51: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (16384)
	[2024-01-30 00:33:39] INFO llama_model.py:71: [1mprefill_chunk_size[0m defaults to [1mcontext_window_size[0m (16384)
	[2024-01-30 00:33:39] INFO config.py:106: Overriding [1mcontext_window_size[0m from 16384 to 16384
	[2024-01-30 00:33:39] INFO config.py:106: Overriding [1mmax_batch_size[0m from 1 to 80
	[2024-01-30 00:33:39] INFO gen_config.py:116: [generation_config.json] Setting [1mbos_token_id[0m: 1
	[2024-01-30 00:33:39] INFO gen_config.py:116: [generation_config.json] Setting [1meos_token_id[0m: 2
	[2024-01-30 00:33:39] INFO gen_config.py:128: [92mFound[0m tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/tokenizer.model. Copying to [1m/var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpewt38rmf/tokenizer.model[0m
	[2024-01-30 00:33:39] INFO gen_config.py:128: [92mFound[0m tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/tokenizer.json. Copying to [1m/var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpewt38rmf/tokenizer.json[0m
	[2024-01-30 00:33:39] INFO gen_config.py:130: [91mNot found[0m tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/vocab.json
	[2024-01-30 00:33:39] INFO gen_config.py:130: [91mNot found[0m tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/merges.txt
	[2024-01-30 00:33:39] INFO gen_config.py:130: [91mNot found[0m tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/added_tokens.json
	[2024-01-30 00:33:39] INFO gen_config.py:128: [92mFound[0m tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/tokenizer_config.json. Copying to [1m/var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpewt38rmf/tokenizer_config.json[0m
	[2024-01-30 00:33:39] INFO gen_config.py:69: [System default] Setting [1mpad_token_id[0m: 0
	[2024-01-30 00:33:39] INFO gen_config.py:69: [System default] Setting [1mtemperature[0m: 0.7
	[2024-01-30 00:33:39] INFO gen_config.py:69: [System default] Setting [1mrepetition_penalty[0m: 1.0
	[2024-01-30 00:33:39] INFO gen_config.py:69: [System default] Setting [1mtop_p[0m: 0.95
	[2024-01-30 00:33:39] INFO gen_config.py:69: [System default] Setting [1mmean_gen_len[0m: 128
	[2024-01-30 00:33:39] INFO gen_config.py:69: [System default] Setting [1mmax_gen_len[0m: 512
	[2024-01-30 00:33:39] INFO gen_config.py:69: [System default] Setting [1mshift_fill_factor[0m: 0.3
	[2024-01-30 00:33:39] INFO gen_config.py:158: Dumping configuration file to: [1m/var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpewt38rmf/mlc-chat-config.json[0m
	/Users/cfruan/miniconda3/envs/mlc-chat-venv/bin/python -m mlc_chat convert_weight /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo --quantization q4f32_1 --source-format auto --output /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpewt38rmf
	[2024-01-30 00:33:39] INFO auto_config.py:115: [92mFound[0m model configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/config.json
	[2024-01-30 00:33:39] INFO auto_device.py:85: [91mNot found[0m device: cuda:0
	[2024-01-30 00:33:40] INFO auto_device.py:85: [91mNot found[0m device: rocm:0
	[2024-01-30 00:33:40] INFO auto_device.py:76: [92mFound[0m device: metal:0
	[2024-01-30 00:33:40] INFO auto_device.py:85: [91mNot found[0m device: vulkan:0
	[2024-01-30 00:33:41] INFO auto_device.py:85: [91mNot found[0m device: opencl:0
	[2024-01-30 00:33:41] INFO auto_device.py:33: Using device: [1mmetal:0[0m
	[2024-01-30 00:33:41] INFO auto_weight.py:70: Finding weights in: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo
	[2024-01-30 00:33:41] INFO auto_weight.py:120: [92mFound[0m source weight format: huggingface-torch. Source configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/pytorch_model.bin.index.json
	[2024-01-30 00:33:41] INFO auto_weight.py:143: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/model.safetensors.index.json
	[2024-01-30 00:33:41] INFO auto_weight.py:106: Using source weight configuration: [1m/var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/pytorch_model.bin.index.json[0m. Use `--source` to override.
	[2024-01-30 00:33:41] INFO auto_weight.py:110: Using source weight format: [1mhuggingface-torch[0m. Use `--source-format` to override.
	[2024-01-30 00:33:41] INFO auto_config.py:153: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override.
	[2024-01-30 00:33:41] INFO llama_model.py:51: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (16384)
	[2024-01-30 00:33:41] INFO llama_model.py:71: [1mprefill_chunk_size[0m defaults to [1mcontext_window_size[0m (16384)
	[1mWeight conversion with arguments:[0m
	[1m--config[0m /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/config.json
	[1m--quantization[0m GroupQuantize(name='q4f32_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float32', linear_weight_layout='NK', num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7)
	[1m--model-type[0m llama
	[1m--device[0m metal:0
	[1m--source[0m /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/pytorch_model.bin.index.json
	[1m--source-format[0m huggingface-torch
	[1m--output[0m /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpewt38rmf
	0%\| \| 0/195 [00:00<?, ?it/s] [2024-01-30 00:33:44] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/pytorch_model-00003-of-00003.bin
	0%\| \| 0/195 [00:00<?, ?it/s] [2024-01-30 00:33:47] INFO group_quantization.py:227: Compiling quantize function for key: ((32000, 4096), float32, metal, axis=1, output_transpose=False)
	0%\| \| 0/195 [00:02<?, ?it/s] [2024-01-30 00:33:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mlm_head.q_weight[0m", shape: (32000, 512), dtype: uint32
	0%\| \| 0/195 [00:02<?, ?it/s] [2024-01-30 00:33:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mlm_head.q_scale[0m", shape: (32000, 128), dtype: float32
	0%\| \| 0/195 [00:02<?, ?it/s] 1%\|▌ \| 1/195 [00:02<09:36, 2.97s/it] [2024-01-30 00:33:47] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.23.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	1%\|▌ \| 1/195 [00:02<09:36, 2.97s/it] [2024-01-30 00:33:47] INFO group_quantization.py:227: Compiling quantize function for key: ((4096, 11008), float32, metal, axis=1, output_transpose=False)
	1%\|▌ \| 1/195 [00:03<09:36, 2.97s/it] [2024-01-30 00:33:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.23.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	1%\|▌ \| 1/195 [00:03<09:36, 2.97s/it] [2024-01-30 00:33:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.23.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	1%\|▌ \| 1/195 [00:03<09:36, 2.97s/it] 2%\|█▋ \| 3/195 [00:03<02:35, 1.24it/s] [2024-01-30 00:33:47] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.23.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	2%\|█▋ \| 3/195 [00:03<02:35, 1.24it/s] [2024-01-30 00:33:47] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.24.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	2%\|█▋ \| 3/195 [00:03<02:35, 1.24it/s] [2024-01-30 00:33:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.24.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	2%\|█▋ \| 3/195 [00:03<02:35, 1.24it/s] [2024-01-30 00:33:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.24.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	2%\|█▋ \| 3/195 [00:03<02:35, 1.24it/s] [2024-01-30 00:33:47] INFO group_quantization.py:227: Compiling quantize function for key: ((22016, 4096), float32, metal, axis=1, output_transpose=False)
	2%\|█▋ \| 3/195 [00:03<02:35, 1.24it/s] [2024-01-30 00:33:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.24.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	2%\|█▋ \| 3/195 [00:03<02:35, 1.24it/s] [2024-01-30 00:33:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.24.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	2%\|█▋ \| 3/195 [00:03<02:35, 1.24it/s] 4%\|███▉ \| 7/195 [00:03<00:55, 3.41it/s] [2024-01-30 00:33:47] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.24.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	4%\|███▉ \| 7/195 [00:03<00:55, 3.41it/s] [2024-01-30 00:33:47] INFO group_quantization.py:227: Compiling quantize function for key: ((12288, 4096), float32, metal, axis=1, output_transpose=False)
	4%\|███▉ \| 7/195 [00:03<00:55, 3.41it/s] [2024-01-30 00:33:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.24.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	4%\|███▉ \| 7/195 [00:03<00:55, 3.41it/s] [2024-01-30 00:33:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.24.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	4%\|███▉ \| 7/195 [00:03<00:55, 3.41it/s] 5%\|████▉ \| 9/195 [00:03<00:40, 4.62it/s] [2024-01-30 00:33:47] INFO group_quantization.py:227: Compiling quantize function for key: ((4096, 4096), float32, metal, axis=1, output_transpose=False)
	5%\|████▉ \| 9/195 [00:03<00:40, 4.62it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.24.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	5%\|████▉ \| 9/195 [00:03<00:40, 4.62it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.24.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	5%\|████▉ \| 9/195 [00:03<00:40, 4.62it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.25.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	5%\|████▉ \| 9/195 [00:03<00:40, 4.62it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.25.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	5%\|████▉ \| 9/195 [00:03<00:40, 4.62it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.25.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	5%\|████▉ \| 9/195 [00:03<00:40, 4.62it/s] 6%\|██████▌ \| 12/195 [00:03<00:25, 7.09it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.25.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	6%\|██████▌ \| 12/195 [00:03<00:25, 7.09it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.25.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	6%\|██████▌ \| 12/195 [00:03<00:25, 7.09it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.25.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	6%\|██████▌ \| 12/195 [00:03<00:25, 7.09it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.25.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	6%\|██████▌ \| 12/195 [00:03<00:25, 7.09it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.25.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	6%\|██████▌ \| 12/195 [00:03<00:25, 7.09it/s] 8%\|████████▏ \| 15/195 [00:03<00:19, 9.02it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.25.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	8%\|████████▏ \| 15/195 [00:03<00:19, 9.02it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.25.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	8%\|████████▏ \| 15/195 [00:03<00:19, 9.02it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.26.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	8%\|████████▏ \| 15/195 [00:03<00:19, 9.02it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.26.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	8%\|████████▏ \| 15/195 [00:03<00:19, 9.02it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.26.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	8%\|████████▏ \| 15/195 [00:03<00:19, 9.02it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.26.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	8%\|████████▏ \| 15/195 [00:03<00:19, 9.02it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.26.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	8%\|████████▏ \| 15/195 [00:03<00:19, 9.02it/s] 10%\|██████████▍ \| 19/195 [00:03<00:14, 12.37it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.26.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	10%\|██████████▍ \| 19/195 [00:03<00:14, 12.37it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.26.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	10%\|██████████▍ \| 19/195 [00:03<00:14, 12.37it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.26.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	10%\|██████████▍ \| 19/195 [00:03<00:14, 12.37it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.26.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	10%\|██████████▍ \| 19/195 [00:03<00:14, 12.37it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.26.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	10%\|██████████▍ \| 19/195 [00:03<00:14, 12.37it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.27.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	10%\|██████████▍ \| 19/195 [00:03<00:14, 12.37it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.27.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	10%\|██████████▍ \| 19/195 [00:03<00:14, 12.37it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.27.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	10%\|██████████▍ \| 19/195 [00:03<00:14, 12.37it/s] 12%\|█████████████▏ \| 24/195 [00:03<00:09, 17.48it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.27.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	12%\|█████████████▏ \| 24/195 [00:04<00:09, 17.48it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.27.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	12%\|█████████████▏ \| 24/195 [00:04<00:09, 17.48it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.27.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	12%\|█████████████▏ \| 24/195 [00:04<00:09, 17.48it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.27.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	12%\|█████████████▏ \| 24/195 [00:04<00:09, 17.48it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.27.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	12%\|█████████████▏ \| 24/195 [00:04<00:09, 17.48it/s] 14%\|██████████████▊ \| 27/195 [00:04<00:09, 17.27it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.27.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	14%\|██████████████▊ \| 27/195 [00:04<00:09, 17.27it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.27.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	14%\|██████████████▊ \| 27/195 [00:04<00:09, 17.27it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.28.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	14%\|██████████████▊ \| 27/195 [00:04<00:09, 17.27it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.28.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	14%\|██████████████▊ \| 27/195 [00:04<00:09, 17.27it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.28.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	14%\|██████████████▊ \| 27/195 [00:04<00:09, 17.27it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.28.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	14%\|██████████████▊ \| 27/195 [00:04<00:09, 17.27it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.28.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	14%\|██████████████▊ \| 27/195 [00:04<00:09, 17.27it/s] 16%\|█████████████████ \| 31/195 [00:04<00:08, 19.34it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.28.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	16%\|█████████████████ \| 31/195 [00:04<00:08, 19.34it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.28.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	16%\|█████████████████ \| 31/195 [00:04<00:08, 19.34it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.28.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	16%\|█████████████████ \| 31/195 [00:04<00:08, 19.34it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.28.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	16%\|█████████████████ \| 31/195 [00:04<00:08, 19.34it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.28.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	16%\|█████████████████ \| 31/195 [00:04<00:08, 19.34it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.29.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	16%\|█████████████████ \| 31/195 [00:04<00:08, 19.34it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.29.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	16%\|█████████████████ \| 31/195 [00:04<00:08, 19.34it/s] [2024-01-30 00:33:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.29.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	16%\|█████████████████ \| 31/195 [00:04<00:08, 19.34it/s] 18%\|███████████████████▊ \| 36/195 [00:04<00:06, 23.62it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.29.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	18%\|███████████████████▊ \| 36/195 [00:04<00:06, 23.62it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.29.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	18%\|███████████████████▊ \| 36/195 [00:04<00:06, 23.62it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.29.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	18%\|███████████████████▊ \| 36/195 [00:04<00:06, 23.62it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.29.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	18%\|███████████████████▊ \| 36/195 [00:04<00:06, 23.62it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.29.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	18%\|███████████████████▊ \| 36/195 [00:04<00:06, 23.62it/s] 20%\|█████████████████████▍ \| 39/195 [00:04<00:07, 21.32it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.29.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	20%\|█████████████████████▍ \| 39/195 [00:04<00:07, 21.32it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.29.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	20%\|█████████████████████▍ \| 39/195 [00:04<00:07, 21.32it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.30.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	20%\|█████████████████████▍ \| 39/195 [00:04<00:07, 21.32it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.30.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	20%\|█████████████████████▍ \| 39/195 [00:04<00:07, 21.32it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.30.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	20%\|█████████████████████▍ \| 39/195 [00:04<00:07, 21.32it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.30.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	20%\|█████████████████████▍ \| 39/195 [00:04<00:07, 21.32it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.30.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	20%\|█████████████████████▍ \| 39/195 [00:04<00:07, 21.32it/s] 22%\|███████████████████████▌ \| 43/195 [00:04<00:06, 22.34it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.30.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	22%\|███████████████████████▌ \| 43/195 [00:04<00:06, 22.34it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.30.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	22%\|███████████████████████▌ \| 43/195 [00:04<00:06, 22.34it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.30.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	22%\|███████████████████████▌ \| 43/195 [00:04<00:06, 22.34it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.30.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	22%\|███████████████████████▌ \| 43/195 [00:04<00:06, 22.34it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.30.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	22%\|███████████████████████▌ \| 43/195 [00:04<00:06, 22.34it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.31.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	22%\|███████████████████████▌ \| 43/195 [00:04<00:06, 22.34it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.31.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	22%\|███████████████████████▌ \| 43/195 [00:04<00:06, 22.34it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.31.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	22%\|███████████████████████▌ \| 43/195 [00:04<00:06, 22.34it/s] 25%\|██████████████████████████▎ \| 48/195 [00:04<00:05, 26.26it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.31.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	25%\|██████████████████████████▎ \| 48/195 [00:04<00:05, 26.26it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.31.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	25%\|██████████████████████████▎ \| 48/195 [00:04<00:05, 26.26it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.31.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	25%\|██████████████████████████▎ \| 48/195 [00:05<00:05, 26.26it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.31.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	25%\|██████████████████████████▎ \| 48/195 [00:05<00:05, 26.26it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.31.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	25%\|██████████████████████████▎ \| 48/195 [00:05<00:05, 26.26it/s] 26%\|███████████████████████████▉ \| 51/195 [00:05<00:06, 23.05it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.31.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	26%\|███████████████████████████▉ \| 51/195 [00:05<00:06, 23.05it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.31.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	26%\|███████████████████████████▉ \| 51/195 [00:05<00:06, 23.05it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.norm.weight[0m", shape: (4096,), dtype: float32
	26%\|███████████████████████████▉ \| 51/195 [00:05<00:06, 23.05it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/pytorch_model-00003-of-00003.bin
	26%\|███████████████████████████▉ \| 51/195 [00:05<00:06, 23.05it/s] [2024-01-30 00:33:49] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/pytorch_model-00001-of-00003.bin
	26%\|███████████████████████████▉ \| 51/195 [00:05<00:06, 23.05it/s] [2024-01-30 00:33:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.embed_tokens.q_weight[0m", shape: (32000, 512), dtype: uint32
	26%\|███████████████████████████▉ \| 51/195 [00:07<00:06, 23.05it/s] [2024-01-30 00:33:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.embed_tokens.q_scale[0m", shape: (32000, 128), dtype: float32
	26%\|███████████████████████████▉ \| 51/195 [00:07<00:06, 23.05it/s] 28%\|█████████████████████████████▋ \| 54/195 [00:07<00:28, 4.98it/s] [2024-01-30 00:33:51] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.0.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	28%\|█████████████████████████████▋ \| 54/195 [00:07<00:28, 4.98it/s] [2024-01-30 00:33:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	28%\|█████████████████████████████▋ \| 54/195 [00:07<00:28, 4.98it/s] [2024-01-30 00:33:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	28%\|█████████████████████████████▋ \| 54/195 [00:07<00:28, 4.98it/s] [2024-01-30 00:33:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	28%\|█████████████████████████████▋ \| 54/195 [00:07<00:28, 4.98it/s] [2024-01-30 00:33:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	28%\|█████████████████████████████▋ \| 54/195 [00:07<00:28, 4.98it/s] 29%\|███████████████████████████████▎ \| 57/195 [00:07<00:22, 6.18it/s] [2024-01-30 00:33:51] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.0.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	29%\|███████████████████████████████▎ \| 57/195 [00:07<00:22, 6.18it/s] [2024-01-30 00:33:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	29%\|███████████████████████████████▎ \| 57/195 [00:07<00:22, 6.18it/s] [2024-01-30 00:33:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	29%\|███████████████████████████████▎ \| 57/195 [00:07<00:22, 6.18it/s] [2024-01-30 00:33:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	29%\|███████████████████████████████▎ \| 57/195 [00:07<00:22, 6.18it/s] [2024-01-30 00:33:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	29%\|███████████████████████████████▎ \| 57/195 [00:07<00:22, 6.18it/s] [2024-01-30 00:33:51] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.1.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	29%\|███████████████████████████████▎ \| 57/195 [00:07<00:22, 6.18it/s] 31%\|█████████████████████████████████▍ \| 61/195 [00:07<00:15, 8.61it/s] [2024-01-30 00:33:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	31%\|█████████████████████████████████▍ \| 61/195 [00:07<00:15, 8.61it/s] [2024-01-30 00:33:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	31%\|█████████████████████████████████▍ \| 61/195 [00:07<00:15, 8.61it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	31%\|█████████████████████████████████▍ \| 61/195 [00:07<00:15, 8.61it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	31%\|█████████████████████████████████▍ \| 61/195 [00:07<00:15, 8.61it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.1.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	31%\|█████████████████████████████████▍ \| 61/195 [00:07<00:15, 8.61it/s] 33%\|███████████████████████████████████ \| 64/195 [00:07<00:12, 10.13it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	33%\|███████████████████████████████████ \| 64/195 [00:07<00:12, 10.13it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	33%\|███████████████████████████████████ \| 64/195 [00:07<00:12, 10.13it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	33%\|███████████████████████████████████ \| 64/195 [00:07<00:12, 10.13it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	33%\|███████████████████████████████████ \| 64/195 [00:07<00:12, 10.13it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.10.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	33%\|███████████████████████████████████ \| 64/195 [00:07<00:12, 10.13it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	33%\|███████████████████████████████████ \| 64/195 [00:07<00:12, 10.13it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	33%\|███████████████████████████████████ \| 64/195 [00:07<00:12, 10.13it/s] 35%\|█████████████████████████████████████▎ \| 68/195 [00:07<00:09, 13.17it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	35%\|█████████████████████████████████████▎ \| 68/195 [00:07<00:09, 13.17it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	35%\|█████████████████████████████████████▎ \| 68/195 [00:07<00:09, 13.17it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.10.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	35%\|█████████████████████████████████████▎ \| 68/195 [00:07<00:09, 13.17it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	35%\|█████████████████████████████████████▎ \| 68/195 [00:07<00:09, 13.17it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	35%\|█████████████████████████████████████▎ \| 68/195 [00:07<00:09, 13.17it/s] 36%\|██████████████████████████████████████▉ \| 71/195 [00:07<00:08, 13.92it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	36%\|██████████████████████████████████████▉ \| 71/195 [00:07<00:08, 13.92it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	36%\|██████████████████████████████████████▉ \| 71/195 [00:07<00:08, 13.92it/s] [2024-01-30 00:33:52] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/pytorch_model-00002-of-00003.bin
	36%\|██████████████████████████████████████▉ \| 71/195 [00:07<00:08, 13.92it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	36%\|██████████████████████████████████████▉ \| 71/195 [00:10<00:08, 13.92it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	36%\|██████████████████████████████████████▉ \| 71/195 [00:10<00:08, 13.92it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	36%\|██████████████████████████████████████▉ \| 71/195 [00:10<00:08, 13.92it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	36%\|██████████████████████████████████████▉ \| 71/195 [00:10<00:08, 13.92it/s] 38%\|████████████████████████████████████████▌ \| 74/195 [00:10<00:40, 2.99it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	38%\|████████████████████████████████████████▌ \| 74/195 [00:10<00:40, 2.99it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	38%\|████████████████████████████████████████▌ \| 74/195 [00:10<00:40, 2.99it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.2.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	38%\|████████████████████████████████████████▌ \| 74/195 [00:10<00:40, 2.99it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	38%\|████████████████████████████████████████▌ \| 74/195 [00:10<00:40, 2.99it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	38%\|████████████████████████████████████████▌ \| 74/195 [00:10<00:40, 2.99it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	38%\|████████████████████████████████████████▌ \| 74/195 [00:11<00:40, 2.99it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	38%\|████████████████████████████████████████▌ \| 74/195 [00:11<00:40, 2.99it/s] 40%\|██████████████████████████████████████████▊ \| 78/195 [00:11<00:27, 4.27it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.2.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	40%\|██████████████████████████████████████████▊ \| 78/195 [00:11<00:27, 4.27it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	40%\|██████████████████████████████████████████▊ \| 78/195 [00:11<00:27, 4.27it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	40%\|██████████████████████████████████████████▊ \| 78/195 [00:11<00:27, 4.27it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	40%\|██████████████████████████████████████████▊ \| 78/195 [00:11<00:27, 4.27it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	40%\|██████████████████████████████████████████▊ \| 78/195 [00:11<00:27, 4.27it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.3.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	40%\|██████████████████████████████████████████▊ \| 78/195 [00:11<00:27, 4.27it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	40%\|██████████████████████████████████████████▊ \| 78/195 [00:11<00:27, 4.27it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	40%\|██████████████████████████████████████████▊ \| 78/195 [00:11<00:27, 4.27it/s] 43%\|█████████████████████████████████████████████▌ \| 83/195 [00:11<00:17, 6.44it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	43%\|█████████████████████████████████████████████▌ \| 83/195 [00:11<00:17, 6.44it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	43%\|█████████████████████████████████████████████▌ \| 83/195 [00:11<00:17, 6.44it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.3.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	43%\|█████████████████████████████████████████████▌ \| 83/195 [00:11<00:17, 6.44it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	43%\|█████████████████████████████████████████████▌ \| 83/195 [00:11<00:17, 6.44it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	43%\|█████████████████████████████████████████████▌ \| 83/195 [00:11<00:17, 6.44it/s] 44%\|███████████████████████████████████████████████▏ \| 86/195 [00:11<00:14, 7.65it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	44%\|███████████████████████████████████████████████▏ \| 86/195 [00:11<00:14, 7.65it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	44%\|███████████████████████████████████████████████▏ \| 86/195 [00:11<00:14, 7.65it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.4.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	44%\|███████████████████████████████████████████████▏ \| 86/195 [00:11<00:14, 7.65it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	44%\|███████████████████████████████████████████████▏ \| 86/195 [00:11<00:14, 7.65it/s] [2024-01-30 00:33:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	44%\|███████████████████████████████████████████████▏ \| 86/195 [00:11<00:14, 7.65it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	44%\|███████████████████████████████████████████████▏ \| 86/195 [00:11<00:14, 7.65it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	44%\|███████████████████████████████████████████████▏ \| 86/195 [00:11<00:14, 7.65it/s] 46%\|█████████████████████████████████████████████████▍ \| 90/195 [00:11<00:10, 9.89it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.4.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	46%\|█████████████████████████████████████████████████▍ \| 90/195 [00:11<00:10, 9.89it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	46%\|█████████████████████████████████████████████████▍ \| 90/195 [00:11<00:10, 9.89it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	46%\|█████████████████████████████████████████████████▍ \| 90/195 [00:11<00:10, 9.89it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	46%\|█████████████████████████████████████████████████▍ \| 90/195 [00:11<00:10, 9.89it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	46%\|█████████████████████████████████████████████████▍ \| 90/195 [00:11<00:10, 9.89it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.5.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	46%\|█████████████████████████████████████████████████▍ \| 90/195 [00:11<00:10, 9.89it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	46%\|█████████████████████████████████████████████████▍ \| 90/195 [00:11<00:10, 9.89it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	46%\|█████████████████████████████████████████████████▍ \| 90/195 [00:11<00:10, 9.89it/s] 49%\|████████████████████████████████████████████████████▏ \| 95/195 [00:11<00:07, 13.51it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	49%\|████████████████████████████████████████████████████▏ \| 95/195 [00:11<00:07, 13.51it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	49%\|████████████████████████████████████████████████████▏ \| 95/195 [00:11<00:07, 13.51it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.5.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	49%\|████████████████████████████████████████████████████▏ \| 95/195 [00:11<00:07, 13.51it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	49%\|████████████████████████████████████████████████████▏ \| 95/195 [00:11<00:07, 13.51it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	49%\|████████████████████████████████████████████████████▏ \| 95/195 [00:11<00:07, 13.51it/s] 50%\|█████████████████████████████████████████████████████▊ \| 98/195 [00:11<00:06, 14.20it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	50%\|█████████████████████████████████████████████████████▊ \| 98/195 [00:11<00:06, 14.20it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	50%\|█████████████████████████████████████████████████████▊ \| 98/195 [00:11<00:06, 14.20it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.6.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	50%\|█████████████████████████████████████████████████████▊ \| 98/195 [00:11<00:06, 14.20it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	50%\|█████████████████████████████████████████████████████▊ \| 98/195 [00:11<00:06, 14.20it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	50%\|█████████████████████████████████████████████████████▊ \| 98/195 [00:11<00:06, 14.20it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	50%\|█████████████████████████████████████████████████████▊ \| 98/195 [00:11<00:06, 14.20it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	50%\|█████████████████████████████████████████████████████▊ \| 98/195 [00:11<00:06, 14.20it/s] 52%\|███████████████████████████████████████████████████████▍ \| 102/195 [00:11<00:05, 16.70it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.6.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	52%\|███████████████████████████████████████████████████████▍ \| 102/195 [00:11<00:05, 16.70it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	52%\|███████████████████████████████████████████████████████▍ \| 102/195 [00:12<00:05, 16.70it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	52%\|███████████████████████████████████████████████████████▍ \| 102/195 [00:12<00:05, 16.70it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	52%\|███████████████████████████████████████████████████████▍ \| 102/195 [00:12<00:05, 16.70it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	52%\|███████████████████████████████████████████████████████▍ \| 102/195 [00:12<00:05, 16.70it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.7.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	52%\|███████████████████████████████████████████████████████▍ \| 102/195 [00:12<00:05, 16.70it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	52%\|███████████████████████████████████████████████████████▍ \| 102/195 [00:12<00:05, 16.70it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	52%\|███████████████████████████████████████████████████████▍ \| 102/195 [00:12<00:05, 16.70it/s] 55%\|██████████████████████████████████████████████████████████▏ \| 107/195 [00:12<00:04, 20.88it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	55%\|██████████████████████████████████████████████████████████▏ \| 107/195 [00:12<00:04, 20.88it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	55%\|██████████████████████████████████████████████████████████▏ \| 107/195 [00:12<00:04, 20.88it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.7.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	55%\|██████████████████████████████████████████████████████████▏ \| 107/195 [00:12<00:04, 20.88it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	55%\|██████████████████████████████████████████████████████████▏ \| 107/195 [00:12<00:04, 20.88it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	55%\|██████████████████████████████████████████████████████████▏ \| 107/195 [00:12<00:04, 20.88it/s] 56%\|███████████████████████████████████████████████████████████▊ \| 110/195 [00:12<00:04, 19.92it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	56%\|███████████████████████████████████████████████████████████▊ \| 110/195 [00:12<00:04, 19.92it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	56%\|███████████████████████████████████████████████████████████▊ \| 110/195 [00:12<00:04, 19.92it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.8.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	56%\|███████████████████████████████████████████████████████████▊ \| 110/195 [00:12<00:04, 19.92it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	56%\|███████████████████████████████████████████████████████████▊ \| 110/195 [00:12<00:04, 19.92it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	56%\|███████████████████████████████████████████████████████████▊ \| 110/195 [00:12<00:04, 19.92it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	56%\|███████████████████████████████████████████████████████████▊ \| 110/195 [00:12<00:04, 19.92it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	56%\|███████████████████████████████████████████████████████████▊ \| 110/195 [00:12<00:04, 19.92it/s] 58%\|█████████████████████████████████████████████████████████████▉ \| 114/195 [00:12<00:03, 21.47it/s] [2024-01-30 00:33:56] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.8.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	58%\|█████████████████████████████████████████████████████████████▉ \| 114/195 [00:12<00:03, 21.47it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	58%\|█████████████████████████████████████████████████████████████▉ \| 114/195 [00:12<00:03, 21.47it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	58%\|█████████████████████████████████████████████████████████████▉ \| 114/195 [00:12<00:03, 21.47it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	58%\|█████████████████████████████████████████████████████████████▉ \| 114/195 [00:12<00:03, 21.47it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	58%\|█████████████████████████████████████████████████████████████▉ \| 114/195 [00:12<00:03, 21.47it/s] 60%\|███████████████████████████████████████████████████████████████▌ \| 117/195 [00:12<00:03, 23.01it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.9.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	60%\|███████████████████████████████████████████████████████████████▌ \| 117/195 [00:12<00:03, 23.01it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	60%\|███████████████████████████████████████████████████████████████▌ \| 117/195 [00:12<00:03, 23.01it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	60%\|███████████████████████████████████████████████████████████████▌ \| 117/195 [00:12<00:03, 23.01it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	60%\|███████████████████████████████████████████████████████████████▌ \| 117/195 [00:12<00:03, 23.01it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	60%\|███████████████████████████████████████████████████████████████▌ \| 117/195 [00:12<00:03, 23.01it/s] 62%\|█████████████████████████████████████████████████████████████████▏ \| 120/195 [00:12<00:03, 22.72it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.9.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	62%\|█████████████████████████████████████████████████████████████████▏ \| 120/195 [00:12<00:03, 22.72it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	62%\|█████████████████████████████████████████████████████████████████▏ \| 120/195 [00:12<00:03, 22.72it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	62%\|█████████████████████████████████████████████████████████████████▏ \| 120/195 [00:12<00:03, 22.72it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	62%\|█████████████████████████████████████████████████████████████████▏ \| 120/195 [00:12<00:03, 22.72it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	62%\|█████████████████████████████████████████████████████████████████▏ \| 120/195 [00:12<00:03, 22.72it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.11.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	62%\|█████████████████████████████████████████████████████████████████▏ \| 120/195 [00:12<00:03, 22.72it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	62%\|█████████████████████████████████████████████████████████████████▏ \| 120/195 [00:12<00:03, 22.72it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	62%\|█████████████████████████████████████████████████████████████████▏ \| 120/195 [00:12<00:03, 22.72it/s] 64%\|███████████████████████████████████████████████████████████████████▉ \| 125/195 [00:12<00:02, 26.92it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.11.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	64%\|███████████████████████████████████████████████████████████████████▉ \| 125/195 [00:12<00:02, 26.92it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.12.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	64%\|███████████████████████████████████████████████████████████████████▉ \| 125/195 [00:12<00:02, 26.92it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	64%\|███████████████████████████████████████████████████████████████████▉ \| 125/195 [00:12<00:02, 26.92it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	64%\|███████████████████████████████████████████████████████████████████▉ \| 125/195 [00:12<00:02, 26.92it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	64%\|███████████████████████████████████████████████████████████████████▉ \| 125/195 [00:12<00:02, 26.92it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	64%\|███████████████████████████████████████████████████████████████████▉ \| 125/195 [00:12<00:02, 26.92it/s] 66%\|██████████████████████████████████████████████████████████████████████ \| 129/195 [00:12<00:02, 27.99it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.12.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	66%\|██████████████████████████████████████████████████████████████████████ \| 129/195 [00:12<00:02, 27.99it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	66%\|██████████████████████████████████████████████████████████████████████ \| 129/195 [00:12<00:02, 27.99it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	66%\|██████████████████████████████████████████████████████████████████████ \| 129/195 [00:12<00:02, 27.99it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	66%\|██████████████████████████████████████████████████████████████████████ \| 129/195 [00:13<00:02, 27.99it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	66%\|██████████████████████████████████████████████████████████████████████ \| 129/195 [00:13<00:02, 27.99it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.13.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	66%\|██████████████████████████████████████████████████████████████████████ \| 129/195 [00:13<00:02, 27.99it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	66%\|██████████████████████████████████████████████████████████████████████ \| 129/195 [00:13<00:02, 27.99it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	66%\|██████████████████████████████████████████████████████████████████████ \| 129/195 [00:13<00:02, 27.99it/s] 69%\|████████████████████████████████████████████████████████████████████████▊ \| 134/195 [00:13<00:01, 30.89it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	69%\|████████████████████████████████████████████████████████████████████████▊ \| 134/195 [00:13<00:01, 30.89it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	69%\|████████████████████████████████████████████████████████████████████████▊ \| 134/195 [00:13<00:01, 30.89it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.13.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	69%\|████████████████████████████████████████████████████████████████████████▊ \| 134/195 [00:13<00:01, 30.89it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	69%\|████████████████████████████████████████████████████████████████████████▊ \| 134/195 [00:13<00:01, 30.89it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	69%\|████████████████████████████████████████████████████████████████████████▊ \| 134/195 [00:13<00:01, 30.89it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	69%\|████████████████████████████████████████████████████████████████████████▊ \| 134/195 [00:13<00:01, 30.89it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	69%\|████████████████████████████████████████████████████████████████████████▊ \| 134/195 [00:13<00:01, 30.89it/s] 71%\|███████████████████████████████████████████████████████████████████████████ \| 138/195 [00:13<00:02, 27.07it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.14.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	71%\|███████████████████████████████████████████████████████████████████████████ \| 138/195 [00:13<00:02, 27.07it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	71%\|███████████████████████████████████████████████████████████████████████████ \| 138/195 [00:13<00:02, 27.07it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	71%\|███████████████████████████████████████████████████████████████████████████ \| 138/195 [00:13<00:02, 27.07it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	71%\|███████████████████████████████████████████████████████████████████████████ \| 138/195 [00:13<00:02, 27.07it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	71%\|███████████████████████████████████████████████████████████████████████████ \| 138/195 [00:13<00:02, 27.07it/s] 72%\|████████████████████████████████████████████████████████████████████████████▋ \| 141/195 [00:13<00:02, 25.71it/s] [2024-01-30 00:33:57] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.14.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	72%\|████████████████████████████████████████████████████████████████████████████▋ \| 141/195 [00:13<00:02, 25.71it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	72%\|████████████████████████████████████████████████████████████████████████████▋ \| 141/195 [00:13<00:02, 25.71it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	72%\|████████████████████████████████████████████████████████████████████████████▋ \| 141/195 [00:13<00:02, 25.71it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	72%\|████████████████████████████████████████████████████████████████████████████▋ \| 141/195 [00:13<00:02, 25.71it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	72%\|████████████████████████████████████████████████████████████████████████████▋ \| 141/195 [00:13<00:02, 25.71it/s] 74%\|██████████████████████████████████████████████████████████████████████████████▎ \| 144/195 [00:13<00:01, 26.55it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.15.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	74%\|██████████████████████████████████████████████████████████████████████████████▎ \| 144/195 [00:13<00:01, 26.55it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	74%\|██████████████████████████████████████████████████████████████████████████████▎ \| 144/195 [00:13<00:01, 26.55it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	74%\|██████████████████████████████████████████████████████████████████████████████▎ \| 144/195 [00:13<00:01, 26.55it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	74%\|██████████████████████████████████████████████████████████████████████████████▎ \| 144/195 [00:13<00:01, 26.55it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	74%\|██████████████████████████████████████████████████████████████████████████████▎ \| 144/195 [00:13<00:01, 26.55it/s] 75%\|███████████████████████████████████████████████████████████████████████████████▉ \| 147/195 [00:13<00:01, 25.27it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.15.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	75%\|███████████████████████████████████████████████████████████████████████████████▉ \| 147/195 [00:13<00:01, 25.27it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	75%\|███████████████████████████████████████████████████████████████████████████████▉ \| 147/195 [00:13<00:01, 25.27it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	75%\|███████████████████████████████████████████████████████████████████████████████▉ \| 147/195 [00:13<00:01, 25.27it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	75%\|███████████████████████████████████████████████████████████████████████████████▉ \| 147/195 [00:13<00:01, 25.27it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	75%\|███████████████████████████████████████████████████████████████████████████████▉ \| 147/195 [00:13<00:01, 25.27it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.16.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	75%\|███████████████████████████████████████████████████████████████████████████████▉ \| 147/195 [00:13<00:01, 25.27it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	75%\|███████████████████████████████████████████████████████████████████████████████▉ \| 147/195 [00:13<00:01, 25.27it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	75%\|███████████████████████████████████████████████████████████████████████████████▉ \| 147/195 [00:13<00:01, 25.27it/s] 78%\|██████████████████████████████████████████████████████████████████████████████████▋ \| 152/195 [00:13<00:01, 28.90it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	78%\|██████████████████████████████████████████████████████████████████████████████████▋ \| 152/195 [00:13<00:01, 28.90it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	78%\|██████████████████████████████████████████████████████████████████████████████████▋ \| 152/195 [00:13<00:01, 28.90it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.16.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	78%\|██████████████████████████████████████████████████████████████████████████████████▋ \| 152/195 [00:13<00:01, 28.90it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	78%\|██████████████████████████████████████████████████████████████████████████████████▋ \| 152/195 [00:13<00:01, 28.90it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	78%\|██████████████████████████████████████████████████████████████████████████████████▋ \| 152/195 [00:13<00:01, 28.90it/s] 79%\|████████████████████████████████████████████████████████████████████████████████████▎ \| 155/195 [00:13<00:01, 24.28it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	79%\|████████████████████████████████████████████████████████████████████████████████████▎ \| 155/195 [00:13<00:01, 24.28it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	79%\|████████████████████████████████████████████████████████████████████████████████████▎ \| 155/195 [00:13<00:01, 24.28it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.17.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	79%\|████████████████████████████████████████████████████████████████████████████████████▎ \| 155/195 [00:13<00:01, 24.28it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	79%\|████████████████████████████████████████████████████████████████████████████████████▎ \| 155/195 [00:13<00:01, 24.28it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	79%\|████████████████████████████████████████████████████████████████████████████████████▎ \| 155/195 [00:13<00:01, 24.28it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	79%\|████████████████████████████████████████████████████████████████████████████████████▎ \| 155/195 [00:14<00:01, 24.28it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	79%\|████████████████████████████████████████████████████████████████████████████████████▎ \| 155/195 [00:14<00:01, 24.28it/s] 82%\|██████████████████████████████████████████████████████████████████████████████████████▍ \| 159/195 [00:14<00:01, 25.02it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.17.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	82%\|██████████████████████████████████████████████████████████████████████████████████████▍ \| 159/195 [00:14<00:01, 25.02it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	82%\|██████████████████████████████████████████████████████████████████████████████████████▍ \| 159/195 [00:14<00:01, 25.02it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	82%\|██████████████████████████████████████████████████████████████████████████████████████▍ \| 159/195 [00:14<00:01, 25.02it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	82%\|██████████████████████████████████████████████████████████████████████████████████████▍ \| 159/195 [00:14<00:01, 25.02it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	82%\|██████████████████████████████████████████████████████████████████████████████████████▍ \| 159/195 [00:14<00:01, 25.02it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.18.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	82%\|██████████████████████████████████████████████████████████████████████████████████████▍ \| 159/195 [00:14<00:01, 25.02it/s] 84%\|████████████████████████████████████████████████████████████████████████████████████████▌ \| 163/195 [00:14<00:01, 28.25it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	84%\|████████████████████████████████████████████████████████████████████████████████████████▌ \| 163/195 [00:14<00:01, 28.25it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	84%\|████████████████████████████████████████████████████████████████████████████████████████▌ \| 163/195 [00:14<00:01, 28.25it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	84%\|████████████████████████████████████████████████████████████████████████████████████████▌ \| 163/195 [00:14<00:01, 28.25it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	84%\|████████████████████████████████████████████████████████████████████████████████████████▌ \| 163/195 [00:14<00:01, 28.25it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.18.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	84%\|████████████████████████████████████████████████████████████████████████████████████████▌ \| 163/195 [00:14<00:01, 28.25it/s] 85%\|██████████████████████████████████████████████████████████████████████████████████████████▏ \| 166/195 [00:14<00:01, 25.86it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	85%\|██████████████████████████████████████████████████████████████████████████████████████████▏ \| 166/195 [00:14<00:01, 25.86it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	85%\|██████████████████████████████████████████████████████████████████████████████████████████▏ \| 166/195 [00:14<00:01, 25.86it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	85%\|██████████████████████████████████████████████████████████████████████████████████████████▏ \| 166/195 [00:14<00:01, 25.86it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	85%\|██████████████████████████████████████████████████████████████████████████████████████████▏ \| 166/195 [00:14<00:01, 25.86it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.19.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	85%\|██████████████████████████████████████████████████████████████████████████████████████████▏ \| 166/195 [00:14<00:01, 25.86it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	85%\|██████████████████████████████████████████████████████████████████████████████████████████▏ \| 166/195 [00:14<00:01, 25.86it/s] [2024-01-30 00:33:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	85%\|██████████████████████████████████████████████████████████████████████████████████████████▏ \| 166/195 [00:14<00:01, 25.86it/s] 87%\|████████████████████████████████████████████████████████████████████████████████████████████▍ \| 170/195 [00:14<00:00, 28.35it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	87%\|████████████████████████████████████████████████████████████████████████████████████████████▍ \| 170/195 [00:14<00:00, 28.35it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	87%\|████████████████████████████████████████████████████████████████████████████████████████████▍ \| 170/195 [00:14<00:00, 28.35it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.19.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	87%\|████████████████████████████████████████████████████████████████████████████████████████████▍ \| 170/195 [00:14<00:00, 28.35it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	87%\|████████████████████████████████████████████████████████████████████████████████████████████▍ \| 170/195 [00:14<00:00, 28.35it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	87%\|████████████████████████████████████████████████████████████████████████████████████████████▍ \| 170/195 [00:14<00:00, 28.35it/s] 89%\|██████████████████████████████████████████████████████████████████████████████████████████████ \| 173/195 [00:14<00:00, 24.16it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	89%\|██████████████████████████████████████████████████████████████████████████████████████████████ \| 173/195 [00:14<00:00, 24.16it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	89%\|██████████████████████████████████████████████████████████████████████████████████████████████ \| 173/195 [00:14<00:00, 24.16it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.20.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	89%\|██████████████████████████████████████████████████████████████████████████████████████████████ \| 173/195 [00:14<00:00, 24.16it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	89%\|██████████████████████████████████████████████████████████████████████████████████████████████ \| 173/195 [00:14<00:00, 24.16it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	89%\|██████████████████████████████████████████████████████████████████████████████████████████████ \| 173/195 [00:14<00:00, 24.16it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	89%\|██████████████████████████████████████████████████████████████████████████████████████████████ \| 173/195 [00:14<00:00, 24.16it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	89%\|██████████████████████████████████████████████████████████████████████████████████████████████ \| 173/195 [00:14<00:00, 24.16it/s] 91%\|████████████████████████████████████████████████████████████████████████████████████████████████▏ \| 177/195 [00:14<00:00, 24.87it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.20.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	91%\|████████████████████████████████████████████████████████████████████████████████████████████████▏ \| 177/195 [00:14<00:00, 24.87it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	91%\|████████████████████████████████████████████████████████████████████████████████████████████████▏ \| 177/195 [00:14<00:00, 24.87it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	91%\|████████████████████████████████████████████████████████████████████████████████████████████████▏ \| 177/195 [00:14<00:00, 24.87it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	91%\|████████████████████████████████████████████████████████████████████████████████████████████████▏ \| 177/195 [00:14<00:00, 24.87it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	91%\|████████████████████████████████████████████████████████████████████████████████████████████████▏ \| 177/195 [00:14<00:00, 24.87it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.21.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	91%\|████████████████████████████████████████████████████████████████████████████████████████████████▏ \| 177/195 [00:14<00:00, 24.87it/s] 93%\|██████████████████████████████████████████████████████████████████████████████████████████████████▍ \| 181/195 [00:14<00:00, 28.14it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	93%\|██████████████████████████████████████████████████████████████████████████████████████████████████▍ \| 181/195 [00:14<00:00, 28.14it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	93%\|██████████████████████████████████████████████████████████████████████████████████████████████████▍ \| 181/195 [00:14<00:00, 28.14it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	93%\|██████████████████████████████████████████████████████████████████████████████████████████████████▍ \| 181/195 [00:14<00:00, 28.14it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	93%\|██████████████████████████████████████████████████████████████████████████████████████████████████▍ \| 181/195 [00:15<00:00, 28.14it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.21.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	93%\|██████████████████████████████████████████████████████████████████████████████████████████████████▍ \| 181/195 [00:15<00:00, 28.14it/s] 94%\|████████████████████████████████████████████████████████████████████████████████████████████████████ \| 184/195 [00:15<00:00, 25.75it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	94%\|████████████████████████████████████████████████████████████████████████████████████████████████████ \| 184/195 [00:15<00:00, 25.75it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	94%\|████████████████████████████████████████████████████████████████████████████████████████████████████ \| 184/195 [00:15<00:00, 25.75it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	94%\|████████████████████████████████████████████████████████████████████████████████████████████████████ \| 184/195 [00:15<00:00, 25.75it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	94%\|████████████████████████████████████████████████████████████████████████████████████████████████████ \| 184/195 [00:15<00:00, 25.75it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.22.input_layernorm.weight[0m", shape: (4096,), dtype: float32
	94%\|████████████████████████████████████████████████████████████████████████████████████████████████████ \| 184/195 [00:15<00:00, 25.75it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.22.mlp.down_proj.q_weight[0m", shape: (4096, 1376), dtype: uint32
	94%\|████████████████████████████████████████████████████████████████████████████████████████████████████ \| 184/195 [00:15<00:00, 25.75it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.22.mlp.down_proj.q_scale[0m", shape: (4096, 344), dtype: float32
	94%\|████████████████████████████████████████████████████████████████████████████████████████████████████ \| 184/195 [00:15<00:00, 25.75it/s] 96%\|██████████████████████████████████████████████████████████████████████████████████████████████████████▏ \| 188/195 [00:15<00:00, 27.32it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.22.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	96%\|██████████████████████████████████████████████████████████████████████████████████████████████████████▏ \| 188/195 [00:15<00:00, 27.32it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.22.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	96%\|██████████████████████████████████████████████████████████████████████████████████████████████████████▏ \| 188/195 [00:15<00:00, 27.32it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.22.post_attention_layernorm.weight[0m", shape: (4096,), dtype: float32
	96%\|██████████████████████████████████████████████████████████████████████████████████████████████████████▏ \| 188/195 [00:15<00:00, 27.32it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	96%\|██████████████████████████████████████████████████████████████████████████████████████████████████████▏ \| 188/195 [00:15<00:00, 27.32it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	96%\|██████████████████████████████████████████████████████████████████████████████████████████████████████▏ \| 188/195 [00:15<00:00, 27.32it/s] 98%\|███████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 191/195 [00:15<00:00, 23.21it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	98%\|███████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 191/195 [00:15<00:00, 23.21it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	98%\|███████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 191/195 [00:15<00:00, 23.21it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.23.mlp.gate_up_proj.q_weight[0m", shape: (22016, 512), dtype: uint32
	98%\|███████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 191/195 [00:15<00:00, 23.21it/s] [2024-01-30 00:33:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.23.mlp.gate_up_proj.q_scale[0m", shape: (22016, 128), dtype: float32
	98%\|███████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 191/195 [00:15<00:00, 23.21it/s] [2024-01-30 00:34:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.qkv_proj.q_weight[0m", shape: (12288, 512), dtype: uint32
	98%\|███████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 191/195 [00:15<00:00, 23.21it/s] [2024-01-30 00:34:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.qkv_proj.q_scale[0m", shape: (12288, 128), dtype: float32
	98%\|███████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 191/195 [00:15<00:00, 23.21it/s] 99%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████▍\| 194/195 [00:15<00:00, 20.75it/s] [2024-01-30 00:34:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.o_proj.q_weight[0m", shape: (4096, 512), dtype: uint32
	99%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████▍\| 194/195 [00:15<00:00, 20.75it/s] [2024-01-30 00:34:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.o_proj.q_scale[0m", shape: (4096, 128), dtype: float32
	99%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████▍\| 194/195 [00:15<00:00, 20.75it/s] 100%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████\| 195/195 [00:15<00:00, 12.55it/s]
	[2024-01-30 00:34:00] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/pytorch_model-00001-of-00003.bin
	[2024-01-30 00:34:00] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/pytorch_model-00002-of-00003.bin
	[2024-01-30 00:34:00] INFO stats.py:76: [92mTime usage[0m: HF loading: 7.783 sec; Pre-quantization mapping: 3.646 sec; Quantization: 0.597 sec
	[2024-01-30 00:34:00] INFO stats.py:90: [92mRAM usage[0m: Peak RAM: 18.415 GB. Total bytes loaded from disk: 25.103 GB
	[2024-01-30 00:34:00] INFO convert_weight.py:121: [92mParameter size[0m after quantization: 3.923 GB
	[2024-01-30 00:34:00] INFO convert_weight.py:126: [92mTotal parameters[0m: 6,738,415,616
	[2024-01-30 00:34:00] INFO convert_weight.py:127: [92mBits per parameter[0m: 5.001
	Start storing to cache /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpewt38rmf
	[0001/0325] saving lm_head.q_weight [0002/0325] saving lm_head.q_scale [0003/0325] saving model.layers.23.input_layernorm.weight [0004/0325] saving model.layers.23.mlp.down_proj.q_weight [0005/0325] saving model.layers.23.mlp.down_proj.q_scale [0006/0325] saving model.layers.23.post_attention_layernorm.weight [0007/0325] saving model.layers.24.input_layernorm.weight [0008/0325] saving model.layers.24.mlp.down_proj.q_weight [0009/0325] saving model.layers.24.mlp.down_proj.q_scale [0010/0325] saving model.layers.24.mlp.gate_up_proj.q_weight [0011/0325] saving model.layers.24.mlp.gate_up_proj.q_scale [0012/0325] saving model.layers.24.post_attention_layernorm.weight [0013/0325] saving model.layers.24.self_attn.qkv_proj.q_weight [0014/0325] saving model.layers.24.self_attn.qkv_proj.q_scale [0015/0325] saving model.layers.24.self_attn.o_proj.q_weight [0016/0325] saving model.layers.24.self_attn.o_proj.q_scale [0017/0325] saving model.layers.25.input_layernorm.weight [0018/0325] saving model.layers.25.mlp.down_proj.q_weight [0019/0325] saving model.layers.25.mlp.down_proj.q_scale [0020/0325] saving model.layers.25.mlp.gate_up_proj.q_weight [0021/0325] saving model.layers.25.mlp.gate_up_proj.q_scale [0022/0325] saving model.layers.25.post_attention_layernorm.weight [0023/0325] saving model.layers.25.self_attn.qkv_proj.q_weight [0024/0325] saving model.layers.25.self_attn.qkv_proj.q_scale [0025/0325] saving model.layers.25.self_attn.o_proj.q_weight [0026/0325] saving model.layers.25.self_attn.o_proj.q_scale [0027/0325] saving model.layers.26.input_layernorm.weight [0028/0325] saving model.layers.26.mlp.down_proj.q_weight [0029/0325] saving model.layers.26.mlp.down_proj.q_scale [0030/0325] saving model.layers.26.mlp.gate_up_proj.q_weight [0031/0325] saving model.layers.26.mlp.gate_up_proj.q_scale [0032/0325] saving model.layers.26.post_attention_layernorm.weight [0033/0325] saving model.layers.26.self_attn.qkv_proj.q_weight [0034/0325] saving model.layers.26.self_attn.qkv_proj.q_scale [0035/0325] saving model.layers.26.self_attn.o_proj.q_weight [0036/0325] saving model.layers.26.self_attn.o_proj.q_scale [0037/0325] saving model.layers.27.input_layernorm.weight [0038/0325] saving model.layers.27.mlp.down_proj.q_weight [0039/0325] saving model.layers.27.mlp.down_proj.q_scale [0040/0325] saving model.layers.27.mlp.gate_up_proj.q_weight [0041/0325] saving model.layers.27.mlp.gate_up_proj.q_scale [0042/0325] saving model.layers.27.post_attention_layernorm.weight [0043/0325] saving model.layers.27.self_attn.qkv_proj.q_weight [0044/0325] saving model.layers.27.self_attn.qkv_proj.q_scale [0045/0325] saving model.layers.27.self_attn.o_proj.q_weight [0046/0325] saving model.layers.27.self_attn.o_proj.q_scale [0047/0325] saving model.layers.28.input_layernorm.weight [0048/0325] saving model.layers.28.mlp.down_proj.q_weight [0049/0325] saving model.layers.28.mlp.down_proj.q_scale [0050/0325] saving model.layers.28.mlp.gate_up_proj.q_weight [0051/0325] saving model.layers.28.mlp.gate_up_proj.q_scale [0052/0325] saving model.layers.28.post_attention_layernorm.weight [0053/0325] saving model.layers.28.self_attn.qkv_proj.q_weight [0054/0325] saving model.layers.28.self_attn.qkv_proj.q_scale [0055/0325] saving model.layers.28.self_attn.o_proj.q_weight [0056/0325] saving model.layers.28.self_attn.o_proj.q_scale [0057/0325] saving model.layers.29.input_layernorm.weight [0058/0325] saving model.layers.29.mlp.down_proj.q_weight [0059/0325] saving model.layers.29.mlp.down_proj.q_scale [0060/0325] saving model.layers.29.mlp.gate_up_proj.q_weight [0061/0325] saving model.layers.29.mlp.gate_up_proj.q_scale [0062/0325] saving model.layers.29.post_attention_layernorm.weight [0063/0325] saving model.layers.29.self_attn.qkv_proj.q_weight [0064/0325] saving model.layers.29.self_attn.qkv_proj.q_scale [0065/0325] saving model.layers.29.self_attn.o_proj.q_weight [0066/0325] saving model.layers.29.self_attn.o_proj.q_scale [0067/0325] saving model.layers.30.input_layernorm.weight [0068/0325] saving model.layers.30.mlp.down_proj.q_weight [0069/0325] saving model.layers.30.mlp.down_proj.q_scale [0070/0325] saving model.layers.30.mlp.gate_up_proj.q_weight [0071/0325] saving model.layers.30.mlp.gate_up_proj.q_scale [0072/0325] saving model.layers.30.post_attention_layernorm.weight [0073/0325] saving model.layers.30.self_attn.qkv_proj.q_weight [0074/0325] saving model.layers.30.self_attn.qkv_proj.q_scale [0075/0325] saving model.layers.30.self_attn.o_proj.q_weight [0076/0325] saving model.layers.30.self_attn.o_proj.q_scale [0077/0325] saving model.layers.31.input_layernorm.weight [0078/0325] saving model.layers.31.mlp.down_proj.q_weight [0079/0325] saving model.layers.31.mlp.down_proj.q_scale [0080/0325] saving model.layers.31.mlp.gate_up_proj.q_weight [0081/0325] saving model.layers.31.mlp.gate_up_proj.q_scale [0082/0325] saving model.layers.31.post_attention_layernorm.weight [0083/0325] saving model.layers.31.self_attn.qkv_proj.q_weight [0084/0325] saving model.layers.31.self_attn.qkv_proj.q_scale [0085/0325] saving model.layers.31.self_attn.o_proj.q_weight [0086/0325] saving model.layers.31.self_attn.o_proj.q_scale [0087/0325] saving model.norm.weight [0088/0325] saving model.embed_tokens.q_weight [0089/0325] saving model.embed_tokens.q_scale [0090/0325] saving model.layers.0.input_layernorm.weight [0091/0325] saving model.layers.0.mlp.down_proj.q_weight [0092/0325] saving model.layers.0.mlp.down_proj.q_scale [0093/0325] saving model.layers.0.mlp.gate_up_proj.q_weight [0094/0325] saving model.layers.0.mlp.gate_up_proj.q_scale [0095/0325] saving model.layers.0.post_attention_layernorm.weight [0096/0325] saving model.layers.0.self_attn.qkv_proj.q_weight [0097/0325] saving model.layers.0.self_attn.qkv_proj.q_scale [0098/0325] saving model.layers.0.self_attn.o_proj.q_weight [0099/0325] saving model.layers.0.self_attn.o_proj.q_scale [0100/0325] saving model.layers.1.input_layernorm.weight [0101/0325] saving model.layers.1.mlp.down_proj.q_weight [0102/0325] saving model.layers.1.mlp.down_proj.q_scale [0103/0325] saving model.layers.1.mlp.gate_up_proj.q_weight [0104/0325] saving model.layers.1.mlp.gate_up_proj.q_scale [0105/0325] saving model.layers.1.post_attention_layernorm.weight [0106/0325] saving model.layers.1.self_attn.qkv_proj.q_weight [0107/0325] saving model.layers.1.self_attn.qkv_proj.q_scale [0108/0325] saving model.layers.1.self_attn.o_proj.q_weight [0109/0325] saving model.layers.1.self_attn.o_proj.q_scale [0110/0325] saving model.layers.10.input_layernorm.weight [0111/0325] saving model.layers.10.mlp.down_proj.q_weight [0112/0325] saving model.layers.10.mlp.down_proj.q_scale [0113/0325] saving model.layers.10.mlp.gate_up_proj.q_weight [0114/0325] saving model.layers.10.mlp.gate_up_proj.q_scale [0115/0325] saving model.layers.10.post_attention_layernorm.weight [0116/0325] saving model.layers.10.self_attn.qkv_proj.q_weight [0117/0325] saving model.layers.10.self_attn.qkv_proj.q_scale [0118/0325] saving model.layers.10.self_attn.o_proj.q_weight [0119/0325] saving model.layers.10.self_attn.o_proj.q_scale [0120/0325] saving model.layers.11.mlp.gate_up_proj.q_weight [0121/0325] saving model.layers.11.mlp.gate_up_proj.q_scale [0122/0325] saving model.layers.11.self_attn.qkv_proj.q_weight [0123/0325] saving model.layers.11.self_attn.qkv_proj.q_scale [0124/0325] saving model.layers.11.self_attn.o_proj.q_weight [0125/0325] saving model.layers.11.self_attn.o_proj.q_scale [0126/0325] saving model.layers.2.input_layernorm.weight [0127/0325] saving model.layers.2.mlp.down_proj.q_weight [0128/0325] saving model.layers.2.mlp.down_proj.q_scale [0129/0325] saving model.layers.2.mlp.gate_up_proj.q_weight [0130/0325] saving model.layers.2.mlp.gate_up_proj.q_scale [0131/0325] saving model.layers.2.post_attention_layernorm.weight [0132/0325] saving model.layers.2.self_attn.qkv_proj.q_weight [0133/0325] saving model.layers.2.self_attn.qkv_proj.q_scale [0134/0325] saving model.layers.2.self_attn.o_proj.q_weight [0135/0325] saving model.layers.2.self_attn.o_proj.q_scale [0136/0325] saving model.layers.3.input_layernorm.weight [0137/0325] saving model.layers.3.mlp.down_proj.q_weight [0138/0325] saving model.layers.3.mlp.down_proj.q_scale [0139/0325] saving model.layers.3.mlp.gate_up_proj.q_weight [0140/0325] saving model.layers.3.mlp.gate_up_proj.q_scale [0141/0325] saving model.layers.3.post_attention_layernorm.weight [0142/0325] saving model.layers.3.self_attn.qkv_proj.q_weight [0143/0325] saving model.layers.3.self_attn.qkv_proj.q_scale [0144/0325] saving model.layers.3.self_attn.o_proj.q_weight [0145/0325] saving model.layers.3.self_attn.o_proj.q_scale [0146/0325] saving model.layers.4.input_layernorm.weight [0147/0325] saving model.layers.4.mlp.down_proj.q_weight [0148/0325] saving model.layers.4.mlp.down_proj.q_scale [0149/0325] saving model.layers.4.mlp.gate_up_proj.q_weight [0150/0325] saving model.layers.4.mlp.gate_up_proj.q_scale [0151/0325] saving model.layers.4.post_attention_layernorm.weight [0152/0325] saving model.layers.4.self_attn.qkv_proj.q_weight [0153/0325] saving model.layers.4.self_attn.qkv_proj.q_scale [0154/0325] saving model.layers.4.self_attn.o_proj.q_weight [0155/0325] saving model.layers.4.self_attn.o_proj.q_scale [0156/0325] saving model.layers.5.input_layernorm.weight [0157/0325] saving model.layers.5.mlp.down_proj.q_weight [0158/0325] saving model.layers.5.mlp.down_proj.q_scale [0159/0325] saving model.layers.5.mlp.gate_up_proj.q_weight [0160/0325] saving model.layers.5.mlp.gate_up_proj.q_scale [0161/0325] saving model.layers.5.post_attention_layernorm.weight [0162/0325] saving model.layers.5.self_attn.qkv_proj.q_weight [0163/0325] saving model.layers.5.self_attn.qkv_proj.q_scale [0164/0325] saving model.layers.5.self_attn.o_proj.q_weight [0165/0325] saving model.layers.5.self_attn.o_proj.q_scale [0166/0325] saving model.layers.6.input_layernorm.weight [0167/0325] saving model.layers.6.mlp.down_proj.q_weight [0168/0325] saving model.layers.6.mlp.down_proj.q_scale [0169/0325] saving model.layers.6.mlp.gate_up_proj.q_weight [0170/0325] saving model.layers.6.mlp.gate_up_proj.q_scale [0171/0325] saving model.layers.6.post_attention_layernorm.weight [0172/0325] saving model.layers.6.self_attn.qkv_proj.q_weight [0173/0325] saving model.layers.6.self_attn.qkv_proj.q_scale [0174/0325] saving model.layers.6.self_attn.o_proj.q_weight [0175/0325] saving model.layers.6.self_attn.o_proj.q_scale [0176/0325] saving model.layers.7.input_layernorm.weight [0177/0325] saving model.layers.7.mlp.down_proj.q_weight [0178/0325] saving model.layers.7.mlp.down_proj.q_scale [0179/0325] saving model.layers.7.mlp.gate_up_proj.q_weight [0180/0325] saving model.layers.7.mlp.gate_up_proj.q_scale [0181/0325] saving model.layers.7.post_attention_layernorm.weight [0182/0325] saving model.layers.7.self_attn.qkv_proj.q_weight [0183/0325] saving model.layers.7.self_attn.qkv_proj.q_scale [0184/0325] saving model.layers.7.self_attn.o_proj.q_weight [0185/0325] saving model.layers.7.self_attn.o_proj.q_scale [0186/0325] saving model.layers.8.input_layernorm.weight [0187/0325] saving model.layers.8.mlp.down_proj.q_weight [0188/0325] saving model.layers.8.mlp.down_proj.q_scale [0189/0325] saving model.layers.8.mlp.gate_up_proj.q_weight [0190/0325] saving model.layers.8.mlp.gate_up_proj.q_scale [0191/0325] saving model.layers.8.post_attention_layernorm.weight [0192/0325] saving model.layers.8.self_attn.qkv_proj.q_weight [0193/0325] saving model.layers.8.self_attn.qkv_proj.q_scale [0194/0325] saving model.layers.8.self_attn.o_proj.q_weight [0195/0325] saving model.layers.8.self_attn.o_proj.q_scale [0196/0325] saving model.layers.9.input_layernorm.weight [0197/0325] saving model.layers.9.mlp.down_proj.q_weight [0198/0325] saving model.layers.9.mlp.down_proj.q_scale [0199/0325] saving model.layers.9.mlp.gate_up_proj.q_weight [0200/0325] saving model.layers.9.mlp.gate_up_proj.q_scale [0201/0325] saving model.layers.9.post_attention_layernorm.weight [0202/0325] saving model.layers.9.self_attn.qkv_proj.q_weight [0203/0325] saving model.layers.9.self_attn.qkv_proj.q_scale [0204/0325] saving model.layers.9.self_attn.o_proj.q_weight [0205/0325] saving model.layers.9.self_attn.o_proj.q_scale [0206/0325] saving model.layers.11.input_layernorm.weight [0207/0325] saving model.layers.11.mlp.down_proj.q_weight [0208/0325] saving model.layers.11.mlp.down_proj.q_scale [0209/0325] saving model.layers.11.post_attention_layernorm.weight [0210/0325] saving model.layers.12.input_layernorm.weight [0211/0325] saving model.layers.12.mlp.down_proj.q_weight [0212/0325] saving model.layers.12.mlp.down_proj.q_scale [0213/0325] saving model.layers.12.mlp.gate_up_proj.q_weight [0214/0325] saving model.layers.12.mlp.gate_up_proj.q_scale [0215/0325] saving model.layers.12.post_attention_layernorm.weight [0216/0325] saving model.layers.12.self_attn.qkv_proj.q_weight [0217/0325] saving model.layers.12.self_attn.qkv_proj.q_scale [0218/0325] saving model.layers.12.self_attn.o_proj.q_weight [0219/0325] saving model.layers.12.self_attn.o_proj.q_scale [0220/0325] saving model.layers.13.input_layernorm.weight [0221/0325] saving model.layers.13.mlp.down_proj.q_weight [0222/0325] saving model.layers.13.mlp.down_proj.q_scale [0223/0325] saving model.layers.13.mlp.gate_up_proj.q_weight [0224/0325] saving model.layers.13.mlp.gate_up_proj.q_scale [0225/0325] saving model.layers.13.post_attention_layernorm.weight [0226/0325] saving model.layers.13.self_attn.qkv_proj.q_weight [0227/0325] saving model.layers.13.self_attn.qkv_proj.q_scale [0228/0325] saving model.layers.13.self_attn.o_proj.q_weight [0229/0325] saving model.layers.13.self_attn.o_proj.q_scale [0230/0325] saving model.layers.14.input_layernorm.weight [0231/0325] saving model.layers.14.mlp.down_proj.q_weight [0232/0325] saving model.layers.14.mlp.down_proj.q_scale [0233/0325] saving model.layers.14.mlp.gate_up_proj.q_weight [0234/0325] saving model.layers.14.mlp.gate_up_proj.q_scale [0235/0325] saving model.layers.14.post_attention_layernorm.weight [0236/0325] saving model.layers.14.self_attn.qkv_proj.q_weight [0237/0325] saving model.layers.14.self_attn.qkv_proj.q_scale [0238/0325] saving model.layers.14.self_attn.o_proj.q_weight [0239/0325] saving model.layers.14.self_attn.o_proj.q_scale [0240/0325] saving model.layers.15.input_layernorm.weight [0241/0325] saving model.layers.15.mlp.down_proj.q_weight [0242/0325] saving model.layers.15.mlp.down_proj.q_scale [0243/0325] saving model.layers.15.mlp.gate_up_proj.q_weight [0244/0325] saving model.layers.15.mlp.gate_up_proj.q_scale [0245/0325] saving model.layers.15.post_attention_layernorm.weight [0246/0325] saving model.layers.15.self_attn.qkv_proj.q_weight [0247/0325] saving model.layers.15.self_attn.qkv_proj.q_scale [0248/0325] saving model.layers.15.self_attn.o_proj.q_weight [0249/0325] saving model.layers.15.self_attn.o_proj.q_scale [0250/0325] saving model.layers.16.input_layernorm.weight [0251/0325] saving model.layers.16.mlp.down_proj.q_weight [0252/0325] saving model.layers.16.mlp.down_proj.q_scale [0253/0325] saving model.layers.16.mlp.gate_up_proj.q_weight [0254/0325] saving model.layers.16.mlp.gate_up_proj.q_scale [0255/0325] saving model.layers.16.post_attention_layernorm.weight [0256/0325] saving model.layers.16.self_attn.qkv_proj.q_weight [0257/0325] saving model.layers.16.self_attn.qkv_proj.q_scale [0258/0325] saving model.layers.16.self_attn.o_proj.q_weight [0259/0325] saving model.layers.16.self_attn.o_proj.q_scale [0260/0325] saving model.layers.17.input_layernorm.weight [0261/0325] saving model.layers.17.mlp.down_proj.q_weight [0262/0325] saving model.layers.17.mlp.down_proj.q_scale [0263/0325] saving model.layers.17.mlp.gate_up_proj.q_weight [0264/0325] saving model.layers.17.mlp.gate_up_proj.q_scale [0265/0325] saving model.layers.17.post_attention_layernorm.weight [0266/0325] saving model.layers.17.self_attn.qkv_proj.q_weight [0267/0325] saving model.layers.17.self_attn.qkv_proj.q_scale [0268/0325] saving model.layers.17.self_attn.o_proj.q_weight [0269/0325] saving model.layers.17.self_attn.o_proj.q_scale [0270/0325] saving model.layers.18.input_layernorm.weight [0271/0325] saving model.layers.18.mlp.down_proj.q_weight [0272/0325] saving model.layers.18.mlp.down_proj.q_scale [0273/0325] saving model.layers.18.mlp.gate_up_proj.q_weight [0274/0325] saving model.layers.18.mlp.gate_up_proj.q_scale [0275/0325] saving model.layers.18.post_attention_layernorm.weight [0276/0325] saving model.layers.18.self_attn.qkv_proj.q_weight [0277/0325] saving model.layers.18.self_attn.qkv_proj.q_scale [0278/0325] saving model.layers.18.self_attn.o_proj.q_weight [0279/0325] saving model.layers.18.self_attn.o_proj.q_scale [0280/0325] saving model.layers.19.input_layernorm.weight [0281/0325] saving model.layers.19.mlp.down_proj.q_weight [0282/0325] saving model.layers.19.mlp.down_proj.q_scale [0283/0325] saving model.layers.19.mlp.gate_up_proj.q_weight [0284/0325] saving model.layers.19.mlp.gate_up_proj.q_scale [0285/0325] saving model.layers.19.post_attention_layernorm.weight [0286/0325] saving model.layers.19.self_attn.qkv_proj.q_weight [0287/0325] saving model.layers.19.self_attn.qkv_proj.q_scale [0288/0325] saving model.layers.19.self_attn.o_proj.q_weight [0289/0325] saving model.layers.19.self_attn.o_proj.q_scale [0290/0325] saving model.layers.20.input_layernorm.weight [0291/0325] saving model.layers.20.mlp.down_proj.q_weight [0292/0325] saving model.layers.20.mlp.down_proj.q_scale [0293/0325] saving model.layers.20.mlp.gate_up_proj.q_weight [0294/0325] saving model.layers.20.mlp.gate_up_proj.q_scale [0295/0325] saving model.layers.20.post_attention_layernorm.weight [0296/0325] saving model.layers.20.self_attn.qkv_proj.q_weight [0297/0325] saving model.layers.20.self_attn.qkv_proj.q_scale [0298/0325] saving model.layers.20.self_attn.o_proj.q_weight [0299/0325] saving model.layers.20.self_attn.o_proj.q_scale [0300/0325] saving model.layers.21.input_layernorm.weight [0301/0325] saving model.layers.21.mlp.down_proj.q_weight [0302/0325] saving model.layers.21.mlp.down_proj.q_scale [0303/0325] saving model.layers.21.mlp.gate_up_proj.q_weight [0304/0325] saving model.layers.21.mlp.gate_up_proj.q_scale [0305/0325] saving model.layers.21.post_attention_layernorm.weight [0306/0325] saving model.layers.21.self_attn.qkv_proj.q_weight [0307/0325] saving model.layers.21.self_attn.qkv_proj.q_scale [0308/0325] saving model.layers.21.self_attn.o_proj.q_weight [0309/0325] saving model.layers.21.self_attn.o_proj.q_scale [0310/0325] saving model.layers.22.input_layernorm.weight [0311/0325] saving model.layers.22.mlp.down_proj.q_weight [0312/0325] saving model.layers.22.mlp.down_proj.q_scale [0313/0325] saving model.layers.22.mlp.gate_up_proj.q_weight [0314/0325] saving model.layers.22.mlp.gate_up_proj.q_scale [0315/0325] saving model.layers.22.post_attention_layernorm.weight [0316/0325] saving model.layers.22.self_attn.qkv_proj.q_weight [0317/0325] saving model.layers.22.self_attn.qkv_proj.q_scale [0318/0325] saving model.layers.22.self_attn.o_proj.q_weight [0319/0325] saving model.layers.22.self_attn.o_proj.q_scale [0320/0325] saving model.layers.23.mlp.gate_up_proj.q_weight [0321/0325] saving model.layers.23.mlp.gate_up_proj.q_scale[2024-01-30 00:34:07] INFO convert_weight.py:143: Saved to directory: [1m/var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpewt38rmf[0m
	[0322/0325] saving model.layers.23.self_attn.qkv_proj.q_weight [0323/0325] saving model.layers.23.self_attn.qkv_proj.q_scale [0324/0325] saving model.layers.23.self_attn.o_proj.q_weight [0325/0325] saving model.layers.23.self_attn.o_proj.q_scale
	All finished, 114 total shards committed, record saved to /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpewt38rmf/ndarray-cache.json
	Also saved a bf16 record to /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpewt38rmf/ndarray-cache-b16.json