diff --git "a/logs.txt" "b/logs.txt"
new file mode 100644--- /dev/null
+++ "b/logs.txt"
@@ -0,0 +1,393 @@
+/Users/cfruan/miniconda3/envs/mlc-chat-venv/bin/python -m mlc_chat gen_config /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo --quantization q4f16_1 --conv-template codellama_instruct --output /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpw9em1i59 --context-window-size 16384
+[2024-01-30 00:31:10] INFO auto_config.py:115: Found model configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/config.json
+[2024-01-30 00:31:10] INFO auto_config.py:153: Found model type: llama. Use `--model-type` to override.
+[2024-01-30 00:31:10] INFO llama_model.py:51: context_window_size not found in config.json. Falling back to max_position_embeddings (16384)
+[2024-01-30 00:31:10] INFO llama_model.py:71: prefill_chunk_size defaults to context_window_size (16384)
+[2024-01-30 00:31:10] INFO config.py:106: Overriding context_window_size from 16384 to 16384
+[2024-01-30 00:31:10] INFO config.py:106: Overriding max_batch_size from 1 to 80
+[2024-01-30 00:31:10] INFO gen_config.py:116: [generation_config.json] Setting bos_token_id: 1
+[2024-01-30 00:31:10] INFO gen_config.py:116: [generation_config.json] Setting eos_token_id: 2
+[2024-01-30 00:31:10] INFO gen_config.py:128: Found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/tokenizer.model. Copying to /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpw9em1i59/tokenizer.model
+[2024-01-30 00:31:10] INFO gen_config.py:128: Found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/tokenizer.json. Copying to /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpw9em1i59/tokenizer.json
+[2024-01-30 00:31:10] INFO gen_config.py:130: Not found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/vocab.json
+[2024-01-30 00:31:10] INFO gen_config.py:130: Not found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/merges.txt
+[2024-01-30 00:31:10] INFO gen_config.py:130: Not found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/added_tokens.json
+[2024-01-30 00:31:10] INFO gen_config.py:128: Found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/tokenizer_config.json. Copying to /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpw9em1i59/tokenizer_config.json
+[2024-01-30 00:31:10] INFO gen_config.py:69: [System default] Setting pad_token_id: 0
+[2024-01-30 00:31:10] INFO gen_config.py:69: [System default] Setting temperature: 0.7
+[2024-01-30 00:31:10] INFO gen_config.py:69: [System default] Setting repetition_penalty: 1.0
+[2024-01-30 00:31:10] INFO gen_config.py:69: [System default] Setting top_p: 0.95
+[2024-01-30 00:31:10] INFO gen_config.py:69: [System default] Setting mean_gen_len: 128
+[2024-01-30 00:31:10] INFO gen_config.py:69: [System default] Setting max_gen_len: 512
+[2024-01-30 00:31:10] INFO gen_config.py:69: [System default] Setting shift_fill_factor: 0.3
+[2024-01-30 00:31:10] INFO gen_config.py:158: Dumping configuration file to: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpw9em1i59/mlc-chat-config.json
+/Users/cfruan/miniconda3/envs/mlc-chat-venv/bin/python -m mlc_chat convert_weight /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo --quantization q4f16_1 --source-format auto --output /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpw9em1i59
+[2024-01-30 00:31:11] INFO auto_config.py:115: Found model configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/config.json
+[2024-01-30 00:31:11] INFO auto_device.py:85: Not found device: cuda:0
+[2024-01-30 00:31:11] INFO auto_device.py:85: Not found device: rocm:0
+[2024-01-30 00:31:12] INFO auto_device.py:76: Found device: metal:0
+[2024-01-30 00:31:12] INFO auto_device.py:85: Not found device: vulkan:0
+[2024-01-30 00:31:12] INFO auto_device.py:85: Not found device: opencl:0
+[2024-01-30 00:31:12] INFO auto_device.py:33: Using device: metal:0
+[2024-01-30 00:31:12] INFO auto_weight.py:70: Finding weights in: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo
+[2024-01-30 00:31:12] INFO auto_weight.py:120: Found source weight format: huggingface-torch. Source configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/pytorch_model.bin.index.json
+[2024-01-30 00:31:12] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/model.safetensors.index.json
+[2024-01-30 00:31:12] INFO auto_weight.py:106: Using source weight configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/pytorch_model.bin.index.json. Use `--source` to override.
+[2024-01-30 00:31:12] INFO auto_weight.py:110: Using source weight format: huggingface-torch. Use `--source-format` to override.
+[2024-01-30 00:31:12] INFO auto_config.py:153: Found model type: llama. Use `--model-type` to override.
+[2024-01-30 00:31:12] INFO llama_model.py:51: context_window_size not found in config.json. Falling back to max_position_embeddings (16384)
+[2024-01-30 00:31:12] INFO llama_model.py:71: prefill_chunk_size defaults to context_window_size (16384)
+Weight conversion with arguments:
+  --config          /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/config.json
+  --quantization    GroupQuantize(name='q4f16_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float16', linear_weight_layout='NK', num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7)
+  --model-type      llama
+  --device          metal:0
+  --source          /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/pytorch_model.bin.index.json
+  --source-format   huggingface-torch
+  --output          /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpw9em1i59
+
  0%|                                                                                                                    | 0/195 [00:00<?, ?it/s]
                                                                                                                                                 
[2024-01-30 00:31:16] 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 00:31:19] INFO group_quantization.py:227: Compiling quantize function for key: ((32000, 4096), float16, metal, axis=1, output_transpose=False)
+
  0%|                                                                                                                    | 0/195 [00:03<?, ?it/s]
                                                                                                                                                 
[2024-01-30 00:31:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "lm_head.q_weight", shape: (32000, 512), dtype: uint32
+
  0%|                                                                                                                    | 0/195 [00:03<?, ?it/s]
                                                                                                                                                 
[2024-01-30 00:31:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "lm_head.q_scale", shape: (32000, 128), dtype: float16
+
  0%|                                                                                                                    | 0/195 [00:03<?, ?it/s]
  1%|▌                                                                                                           | 1/195 [00:03<10:47,  3.34s/it]
                                                                                                                                                 
[2024-01-30 00:31:19] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (4096,), dtype: float16
+
  1%|▌                                                                                                           | 1/195 [00:03<10:47,  3.34s/it]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO group_quantization.py:227: Compiling quantize function for key: ((4096, 11008), float16, metal, axis=1, output_transpose=False)
+
  1%|▌                                                                                                           | 1/195 [00:03<10:47,  3.34s/it]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
  1%|▌                                                                                                           | 1/195 [00:03<10:47,  3.34s/it]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
  1%|▌                                                                                                           | 1/195 [00:03<10:47,  3.34s/it]
  2%|█▋                                                                                                          | 3/195 [00:03<02:59,  1.07it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
  2%|█▋                                                                                                          | 3/195 [00:03<02:59,  1.07it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (4096,), dtype: float16
+
  2%|█▋                                                                                                          | 3/195 [00:03<02:59,  1.07it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
  2%|█▋                                                                                                          | 3/195 [00:03<02:59,  1.07it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
  2%|█▋                                                                                                          | 3/195 [00:03<02:59,  1.07it/s]
  3%|███▎                                                                                                        | 6/195 [00:03<01:12,  2.59it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO group_quantization.py:227: Compiling quantize function for key: ((22016, 4096), float16, metal, axis=1, output_transpose=False)
+
  3%|███▎                                                                                                        | 6/195 [00:03<01:12,  2.59it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
  3%|███▎                                                                                                        | 6/195 [00:03<01:12,  2.59it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
  3%|███▎                                                                                                        | 6/195 [00:03<01:12,  2.59it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
  3%|███▎                                                                                                        | 6/195 [00:03<01:12,  2.59it/s]
  4%|████▍                                                                                                       | 8/195 [00:03<00:57,  3.26it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO group_quantization.py:227: Compiling quantize function for key: ((12288, 4096), float16, metal, axis=1, output_transpose=False)
+
  4%|████▍                                                                                                       | 8/195 [00:04<00:57,  3.26it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
  4%|████▍                                                                                                       | 8/195 [00:04<00:57,  3.26it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
  4%|████▍                                                                                                       | 8/195 [00:04<00:57,  3.26it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO group_quantization.py:227: Compiling quantize function for key: ((4096, 4096), float16, metal, axis=1, output_transpose=False)
+
  4%|████▍                                                                                                       | 8/195 [00:04<00:57,  3.26it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
  4%|████▍                                                                                                       | 8/195 [00:04<00:57,  3.26it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
  4%|████▍                                                                                                       | 8/195 [00:04<00:57,  3.26it/s]
  5%|█████▍                                                                                                     | 10/195 [00:04<00:47,  3.93it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (4096,), dtype: float16
+
  5%|█████▍                                                                                                     | 10/195 [00:04<00:47,  3.93it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
  5%|█████▍                                                                                                     | 10/195 [00:04<00:47,  3.93it/s]
                                                                                                                                                 
[2024-01-30 00:31:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
  5%|█████▍                                                                                                     | 10/195 [00:04<00:47,  3.93it/s]
  6%|██████▌                                                                                                    | 12/195 [00:04<00:34,  5.24it/s]
                                                                                                                                                 
[2024-01-30 00:31:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
  6%|██████▌                                                                                                    | 12/195 [00:04<00:34,  5.24it/s]
                                                                                                                                                 
[2024-01-30 00:31:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
  6%|██████▌                                                                                                    | 12/195 [00:04<00:34,  5.24it/s]
                                                                                                                                                 
[2024-01-30 00:31:21] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
  6%|██████▌                                                                                                    | 12/195 [00:04<00:34,  5.24it/s]
  7%|███████▋                                                                                                   | 14/195 [00:04<00:31,  5.71it/s]
                                                                                                                                                 
[2024-01-30 00:31:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
  7%|███████▋                                                                                                   | 14/195 [00:04<00:31,  5.71it/s]
                                                                                                                                                 
[2024-01-30 00:31:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
  7%|███████▋                                                                                                   | 14/195 [00:04<00:31,  5.71it/s]
                                                                                                                                                 
[2024-01-30 00:31:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
  7%|███████▋                                                                                                   | 14/195 [00:04<00:31,  5.71it/s]
                                                                                                                                                 
[2024-01-30 00:31:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
  7%|███████▋                                                                                                   | 14/195 [00:04<00:31,  5.71it/s]
  8%|████████▊                                                                                                  | 16/195 [00:04<00:27,  6.53it/s]
                                                                                                                                                 
[2024-01-30 00:31:21] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (4096,), dtype: float16
+
  8%|████████▊                                                                                                  | 16/195 [00:04<00:27,  6.53it/s]
                                                                                                                                                 
[2024-01-30 00:31:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
  8%|████████▊                                                                                                  | 16/195 [00:05<00:27,  6.53it/s]
                                                                                                                                                 
[2024-01-30 00:31:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
  8%|████████▊                                                                                                  | 16/195 [00:05<00:27,  6.53it/s]
  9%|█████████▉                                                                                                 | 18/195 [00:05<00:22,  8.01it/s]
                                                                                                                                                 
[2024-01-30 00:31:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
  9%|█████████▉                                                                                                 | 18/195 [00:05<00:22,  8.01it/s]
                                                                                                                                                 
[2024-01-30 00:31:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
  9%|█████████▉                                                                                                 | 18/195 [00:05<00:22,  8.01it/s]
                                                                                                                                                 
[2024-01-30 00:31:21] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
  9%|█████████▉                                                                                                 | 18/195 [00:05<00:22,  8.01it/s]
 10%|██████████▉                                                                                                | 20/195 [00:05<00:22,  7.71it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 10%|██████████▉                                                                                                | 20/195 [00:05<00:22,  7.71it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 10%|██████████▉                                                                                                | 20/195 [00:05<00:22,  7.71it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 10%|██████████▉                                                                                                | 20/195 [00:05<00:22,  7.71it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 10%|██████████▉                                                                                                | 20/195 [00:05<00:22,  7.71it/s]
 11%|████████████                                                                                               | 22/195 [00:05<00:20,  8.26it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (4096,), dtype: float16
+
 11%|████████████                                                                                               | 22/195 [00:05<00:20,  8.26it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 11%|████████████                                                                                               | 22/195 [00:05<00:20,  8.26it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 11%|████████████                                                                                               | 22/195 [00:05<00:20,  8.26it/s]
 12%|█████████████▏                                                                                             | 24/195 [00:05<00:17,  9.70it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 12%|█████████████▏                                                                                             | 24/195 [00:05<00:17,  9.70it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 12%|█████████████▏                                                                                             | 24/195 [00:05<00:17,  9.70it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 12%|█████████████▏                                                                                             | 24/195 [00:05<00:17,  9.70it/s]
 13%|██████████████▎                                                                                            | 26/195 [00:05<00:19,  8.70it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 13%|██████████████▎                                                                                            | 26/195 [00:06<00:19,  8.70it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 13%|██████████████▎                                                                                            | 26/195 [00:06<00:19,  8.70it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 13%|██████████████▎                                                                                            | 26/195 [00:06<00:19,  8.70it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 13%|██████████████▎                                                                                            | 26/195 [00:06<00:19,  8.70it/s]
 14%|███████████████▎                                                                                           | 28/195 [00:06<00:18,  9.00it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.28.input_layernorm.weight", shape: (4096,), dtype: float16
+
 14%|███████████████▎                                                                                           | 28/195 [00:06<00:18,  9.00it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 14%|███████████████▎                                                                                           | 28/195 [00:06<00:18,  9.00it/s]
                                                                                                                                                 
[2024-01-30 00:31:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 14%|███████████████▎                                                                                           | 28/195 [00:06<00:18,  9.00it/s]
 15%|████████████████▍                                                                                          | 30/195 [00:06<00:15, 10.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 15%|████████████████▍                                                                                          | 30/195 [00:06<00:15, 10.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 15%|████████████████▍                                                                                          | 30/195 [00:06<00:15, 10.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.28.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 15%|████████████████▍                                                                                          | 30/195 [00:06<00:15, 10.41it/s]
 16%|█████████████████▌                                                                                         | 32/195 [00:06<00:17,  9.16it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 16%|█████████████████▌                                                                                         | 32/195 [00:06<00:17,  9.16it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 16%|█████████████████▌                                                                                         | 32/195 [00:06<00:17,  9.16it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 16%|█████████████████▌                                                                                         | 32/195 [00:06<00:17,  9.16it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 16%|█████████████████▌                                                                                         | 32/195 [00:06<00:17,  9.16it/s]
 17%|██████████████████▋                                                                                        | 34/195 [00:06<00:17,  9.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.29.input_layernorm.weight", shape: (4096,), dtype: float16
+
 17%|██████████████████▋                                                                                        | 34/195 [00:06<00:17,  9.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 17%|██████████████████▋                                                                                        | 34/195 [00:06<00:17,  9.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 17%|██████████████████▋                                                                                        | 34/195 [00:06<00:17,  9.41it/s]
 18%|███████████████████▊                                                                                       | 36/195 [00:06<00:14, 10.77it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 18%|███████████████████▊                                                                                       | 36/195 [00:07<00:14, 10.77it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 18%|███████████████████▊                                                                                       | 36/195 [00:07<00:14, 10.77it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.29.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 18%|███████████████████▊                                                                                       | 36/195 [00:07<00:14, 10.77it/s]
 19%|████████████████████▊                                                                                      | 38/195 [00:07<00:16,  9.26it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 19%|████████████████████▊                                                                                      | 38/195 [00:07<00:16,  9.26it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 19%|████████████████████▊                                                                                      | 38/195 [00:07<00:16,  9.26it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 19%|████████████████████▊                                                                                      | 38/195 [00:07<00:16,  9.26it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 19%|████████████████████▊                                                                                      | 38/195 [00:07<00:16,  9.26it/s]
 21%|█████████████████████▉                                                                                     | 40/195 [00:07<00:16,  9.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:23] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.30.input_layernorm.weight", shape: (4096,), dtype: float16
+
 21%|█████████████████████▉                                                                                     | 40/195 [00:07<00:16,  9.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 21%|█████████████████████▉                                                                                     | 40/195 [00:07<00:16,  9.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 21%|█████████████████████▉                                                                                     | 40/195 [00:07<00:16,  9.41it/s]
 22%|███████████████████████                                                                                    | 42/195 [00:07<00:14, 10.72it/s]
                                                                                                                                                 
[2024-01-30 00:31:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 22%|███████████████████████                                                                                    | 42/195 [00:07<00:14, 10.72it/s]
                                                                                                                                                 
[2024-01-30 00:31:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 22%|███████████████████████                                                                                    | 42/195 [00:07<00:14, 10.72it/s]
                                                                                                                                                 
[2024-01-30 00:31:24] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.30.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 22%|███████████████████████                                                                                    | 42/195 [00:07<00:14, 10.72it/s]
 23%|████████████████████████▏                                                                                  | 44/195 [00:07<00:16,  9.30it/s]
                                                                                                                                                 
[2024-01-30 00:31:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 23%|████████████████████████▏                                                                                  | 44/195 [00:07<00:16,  9.30it/s]
                                                                                                                                                 
[2024-01-30 00:31:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 23%|████████████████████████▏                                                                                  | 44/195 [00:07<00:16,  9.30it/s]
                                                                                                                                                 
[2024-01-30 00:31:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 23%|████████████████████████▏                                                                                  | 44/195 [00:07<00:16,  9.30it/s]
                                                                                                                                                 
[2024-01-30 00:31:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 23%|████████████████████████▏                                                                                  | 44/195 [00:07<00:16,  9.30it/s]
 24%|█████████████████████████▏                                                                                 | 46/195 [00:07<00:15,  9.46it/s]
                                                                                                                                                 
[2024-01-30 00:31:24] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.31.input_layernorm.weight", shape: (4096,), dtype: float16
+
 24%|█████████████████████████▏                                                                                 | 46/195 [00:07<00:15,  9.46it/s]
                                                                                                                                                 
[2024-01-30 00:31:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 24%|█████████████████████████▏                                                                                 | 46/195 [00:08<00:15,  9.46it/s]
                                                                                                                                                 
[2024-01-30 00:31:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 24%|█████████████████████████▏                                                                                 | 46/195 [00:08<00:15,  9.46it/s]
 25%|██████████████████████████▎                                                                                | 48/195 [00:08<00:13, 10.78it/s]
                                                                                                                                                 
[2024-01-30 00:31:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 25%|██████████████████████████▎                                                                                | 48/195 [00:08<00:13, 10.78it/s]
                                                                                                                                                 
[2024-01-30 00:31:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 25%|██████████████████████████▎                                                                                | 48/195 [00:08<00:13, 10.78it/s]
                                                                                                                                                 
[2024-01-30 00:31:24] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.31.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 25%|██████████████████████████▎                                                                                | 48/195 [00:08<00:13, 10.78it/s]
 26%|███████████████████████████▍                                                                               | 50/195 [00:08<00:15,  9.31it/s]
                                                                                                                                                 
[2024-01-30 00:31:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 26%|███████████████████████████▍                                                                               | 50/195 [00:08<00:15,  9.31it/s]
                                                                                                                                                 
[2024-01-30 00:31:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 26%|███████████████████████████▍                                                                               | 50/195 [00:08<00:15,  9.31it/s]
                                                                                                                                                 
[2024-01-30 00:31:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 26%|███████████████████████████▍                                                                               | 50/195 [00:08<00:15,  9.31it/s]
                                                                                                                                                 
[2024-01-30 00:31:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 26%|███████████████████████████▍                                                                               | 50/195 [00:08<00:15,  9.31it/s]
 27%|████████████████████████████▌                                                                              | 52/195 [00:08<00:15,  9.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:25] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.norm.weight", shape: (4096,), dtype: float16
+
 27%|████████████████████████████▌                                                                              | 52/195 [00:08<00:15,  9.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:25] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/pytorch_model-00003-of-00003.bin
+
 27%|████████████████████████████▌                                                                              | 52/195 [00:08<00:15,  9.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:25] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/pytorch_model-00001-of-00003.bin
+
 27%|████████████████████████████▌                                                                              | 52/195 [00:08<00:15,  9.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (32000, 512), dtype: uint32
+
 27%|████████████████████████████▌                                                                              | 52/195 [00:10<00:15,  9.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (32000, 128), dtype: float16
+
 27%|████████████████████████████▌                                                                              | 52/195 [00:10<00:15,  9.41it/s]
 28%|█████████████████████████████▋                                                                             | 54/195 [00:10<00:57,  2.46it/s]
                                                                                                                                                 
[2024-01-30 00:31:27] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (4096,), dtype: float16
+
 28%|█████████████████████████████▋                                                                             | 54/195 [00:10<00:57,  2.46it/s]
                                                                                                                                                 
[2024-01-30 00:31:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 28%|█████████████████████████████▋                                                                             | 54/195 [00:10<00:57,  2.46it/s]
                                                                                                                                                 
[2024-01-30 00:31:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 28%|█████████████████████████████▋                                                                             | 54/195 [00:10<00:57,  2.46it/s]
 29%|██████████████████████████████▋                                                                            | 56/195 [00:10<00:42,  3.28it/s]
                                                                                                                                                 
[2024-01-30 00:31:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 29%|██████████████████████████████▋                                                                            | 56/195 [00:11<00:42,  3.28it/s]
                                                                                                                                                 
[2024-01-30 00:31:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 29%|██████████████████████████████▋                                                                            | 56/195 [00:11<00:42,  3.28it/s]
 29%|███████████████████████████████▎                                                                           | 57/195 [00:11<00:41,  3.32it/s]
                                                                                                                                                 
[2024-01-30 00:31:27] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 29%|███████████████████████████████▎                                                                           | 57/195 [00:11<00:41,  3.32it/s]
                                                                                                                                                 
[2024-01-30 00:31:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 29%|███████████████████████████████▎                                                                           | 57/195 [00:11<00:41,  3.32it/s]
                                                                                                                                                 
[2024-01-30 00:31:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 29%|███████████████████████████████▎                                                                           | 57/195 [00:11<00:41,  3.32it/s]
 30%|████████████████████████████████▎                                                                          | 59/195 [00:11<00:30,  4.39it/s]
                                                                                                                                                 
[2024-01-30 00:31:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 30%|████████████████████████████████▎                                                                          | 59/195 [00:11<00:30,  4.39it/s]
                                                                                                                                                 
[2024-01-30 00:31:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 30%|████████████████████████████████▎                                                                          | 59/195 [00:11<00:30,  4.39it/s]
                                                                                                                                                 
[2024-01-30 00:31:27] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (4096,), dtype: float16
+
 30%|████████████████████████████████▎                                                                          | 59/195 [00:11<00:30,  4.39it/s]
                                                                                                                                                 
[2024-01-30 00:31:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 30%|████████████████████████████████▎                                                                          | 59/195 [00:11<00:30,  4.39it/s]
                                                                                                                                                 
[2024-01-30 00:31:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 30%|████████████████████████████████▎                                                                          | 59/195 [00:11<00:30,  4.39it/s]
 32%|██████████████████████████████████                                                                         | 62/195 [00:11<00:20,  6.39it/s]
                                                                                                                                                 
[2024-01-30 00:31:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 32%|██████████████████████████████████                                                                         | 62/195 [00:11<00:20,  6.39it/s]
                                                                                                                                                 
[2024-01-30 00:31:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 32%|██████████████████████████████████                                                                         | 62/195 [00:11<00:20,  6.39it/s]
                                                                                                                                                 
[2024-01-30 00:31:28] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 32%|██████████████████████████████████                                                                         | 62/195 [00:11<00:20,  6.39it/s]
 33%|███████████████████████████████████                                                                        | 64/195 [00:11<00:19,  6.59it/s]
                                                                                                                                                 
[2024-01-30 00:31:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 33%|███████████████████████████████████                                                                        | 64/195 [00:11<00:19,  6.59it/s]
                                                                                                                                                 
[2024-01-30 00:31:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 33%|███████████████████████████████████                                                                        | 64/195 [00:11<00:19,  6.59it/s]
                                                                                                                                                 
[2024-01-30 00:31:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 33%|███████████████████████████████████                                                                        | 64/195 [00:12<00:19,  6.59it/s]
                                                                                                                                                 
[2024-01-30 00:31:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 33%|███████████████████████████████████                                                                        | 64/195 [00:12<00:19,  6.59it/s]
 34%|████████████████████████████████████▏                                                                      | 66/195 [00:12<00:17,  7.29it/s]
                                                                                                                                                 
[2024-01-30 00:31:28] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (4096,), dtype: float16
+
 34%|████████████████████████████████████▏                                                                      | 66/195 [00:12<00:17,  7.29it/s]
                                                                                                                                                 
[2024-01-30 00:31:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 34%|████████████████████████████████████▏                                                                      | 66/195 [00:12<00:17,  7.29it/s]
                                                                                                                                                 
[2024-01-30 00:31:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 34%|█████████████████��██████████████████▏                                                                      | 66/195 [00:12<00:17,  7.29it/s]
 35%|█████████████████████████████████████▎                                                                     | 68/195 [00:12<00:14,  8.68it/s]
                                                                                                                                                 
[2024-01-30 00:31:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 35%|█████████████████████████████████████▎                                                                     | 68/195 [00:12<00:14,  8.68it/s]
                                                                                                                                                 
[2024-01-30 00:31:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 35%|█████████████████████████████████████▎                                                                     | 68/195 [00:12<00:14,  8.68it/s]
                                                                                                                                                 
[2024-01-30 00:31:28] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 35%|█████████████████████████████████████▎                                                                     | 68/195 [00:12<00:14,  8.68it/s]
 36%|██████████████████████████████████████▍                                                                    | 70/195 [00:12<00:15,  8.14it/s]
                                                                                                                                                 
[2024-01-30 00:31:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 36%|██████████████████████████████████████▍                                                                    | 70/195 [00:12<00:15,  8.14it/s]
                                                                                                                                                 
[2024-01-30 00:31:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 36%|██████████████████████████████████████▍                                                                    | 70/195 [00:12<00:15,  8.14it/s]
                                                                                                                                                 
[2024-01-30 00:31:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 36%|██████████████████████████████████████▍                                                                    | 70/195 [00:12<00:15,  8.14it/s]
                                                                                                                                                 
[2024-01-30 00:31:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 36%|██████████████████████████████████████▍                                                                    | 70/195 [00:12<00:15,  8.14it/s]
 37%|███████████████████████████████████████▌                                                                   | 72/195 [00:12<00:14,  8.60it/s]
                                                                                                                                                 
[2024-01-30 00:31:29] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp3q4o77js/repo/pytorch_model-00002-of-00003.bin
+
 37%|███████████████████████████████████████▌                                                                   | 72/195 [00:12<00:14,  8.60it/s]
                                                                                                                                                 
[2024-01-30 00:31:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 37%|███████████████████████████████████████▌                                                                   | 72/195 [00:15<00:14,  8.60it/s]
                                                                                                                                                 
[2024-01-30 00:31:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 37%|███████████████████████████████████████▌                                                                   | 72/195 [00:15<00:14,  8.60it/s]
                                                                                                                                                 
[2024-01-30 00:31:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 37%|███████████████████████████████████████▌                                                                   | 72/195 [00:15<00:14,  8.60it/s]
                                                                                                                                                 
[2024-01-30 00:31:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 37%|███████████████████████████████████████▌                                                                   | 72/195 [00:15<00:14,  8.60it/s]
 38%|████████████████████████████████████████▌                                                                  | 74/195 [00:15<01:09,  1.73it/s]
                                                                                                                                                 
[2024-01-30 00:31:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 38%|████████████████████████████████████████▌                                                                  | 74/195 [00:16<01:09,  1.73it/s]
                                                                                                                                                 
[2024-01-30 00:31:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 38%|████████████████████████████████████████▌                                                                  | 74/195 [00:16<01:09,  1.73it/s]
                                                                                                                                                 
[2024-01-30 00:31:32] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (4096,), dtype: float16
+
 38%|████████████████████████████████████████▌                                                                  | 74/195 [00:16<01:09,  1.73it/s]
                                                                                                                                                 
[2024-01-30 00:31:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 38%|████████████████████████████████████████▌                                                                  | 74/195 [00:16<01:09,  1.73it/s]
                                                                                                                                                 
[2024-01-30 00:31:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 38%|████████████████████████████████████████▌                                                                  | 74/195 [00:16<01:09,  1.73it/s]
 39%|██���███████████████████████████████████████▎                                                                | 77/195 [00:16<00:44,  2.67it/s]
                                                                                                                                                 
[2024-01-30 00:31:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 39%|██████████████████████████████████████████▎                                                                | 77/195 [00:16<00:44,  2.67it/s]
                                                                                                                                                 
[2024-01-30 00:31:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 39%|██████████████████████████████████████████▎                                                                | 77/195 [00:16<00:44,  2.67it/s]
                                                                                                                                                 
[2024-01-30 00:31:32] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 39%|██████████████████████████████████████████▎                                                                | 77/195 [00:16<00:44,  2.67it/s]
 41%|███████████████████████████████████████████▎                                                               | 79/195 [00:16<00:36,  3.21it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 41%|███████████████████████████████████████████▎                                                               | 79/195 [00:16<00:36,  3.21it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 41%|███████████████████████████████████████████▎                                                               | 79/195 [00:16<00:36,  3.21it/s]
 41%|███████████████████████████████████████████▉                                                               | 80/195 [00:16<00:32,  3.49it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 41%|███████████████████████████████████████████▉                                                               | 80/195 [00:16<00:32,  3.49it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 41%|███████████████████████████████████████████▉                                                               | 80/195 [00:16<00:32,  3.49it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (4096,), dtype: float16
+
 41%|███████████████████████████████████████████▉                                                               | 80/195 [00:16<00:32,  3.49it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 41%|███████████████████████████████████████████▉                                                               | 80/195 [00:16<00:32,  3.49it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 41%|███████████████████████████████████████████▉                                                               | 80/195 [00:16<00:32,  3.49it/s]
 43%|█████████████████████████████████████████████▌                                                             | 83/195 [00:16<00:21,  5.19it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 43%|█████████████████████████████████████████████▌                                                             | 83/195 [00:17<00:21,  5.19it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 43%|█████████████████████████████████████████████▌                                                             | 83/195 [00:17<00:21,  5.19it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 43%|█████████████████████████████████████████████▌                                                             | 83/195 [00:17<00:21,  5.19it/s]
 44%|██████████████████████████████████████████████▋                                                            | 85/195 [00:17<00:19,  5.63it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 44%|██████████████████████████████████████████████▋                                                            | 85/195 [00:17<00:19,  5.63it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 44%|██████████████████████████████████████████████▋                                                            | 85/195 [00:17<00:19,  5.63it/s]
 44%|███████████████████████████████████████████████▏                                                           | 86/195 [00:17<00:18,  5.75it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 44%|███████████████████████████████████████████████▏                                                           | 86/195 [00:17<00:18,  5.75it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 44%|███████████████████████████████████████████████▏                                                           | 86/195 [00:17<00:18,  5.75it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (4096,), dtype: float16
+
 44%|███████████████████████████████████████████████▏                                                           | 86/195 [00:17<00:18,  5.75it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 44%|███████████████████████████████████████████████▏                                                           | 86/195 [00:17<00:18,  5.75it/s]
                                                                                                                                                 
[2024-01-30 00:31:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 44%|███████████████████████████████████████████████▏                                                           | 86/195 [00:17<00:18,  5.75it/s]
 46%|████████████████████████████████████████████████▊                                                          | 89/195 [00:17<00:13,  7.97it/s]
                                                                                                                                                 
[2024-01-30 00:31:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 46%|████████████████████████████████████████████████▊                                                          | 89/195 [00:17<00:13,  7.97it/s]
                                                                                                                                                 
[2024-01-30 00:31:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 46%|████████████████████████████████████████████████▊                                                          | 89/195 [00:17<00:13,  7.97it/s]
                                                                                                                                                 
[2024-01-30 00:31:34] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 46%|████████████████████████████████████████████████▊                                                          | 89/195 [00:17<00:13,  7.97it/s]
 47%|█████████████████████████████████████████████████▉                                                         | 91/195 [00:17<00:13,  7.69it/s]
                                                                                                                                                 
[2024-01-30 00:31:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 47%|█████████████████████████████████████████████████▉                                                         | 91/195 [00:17<00:13,  7.69it/s]
                                                                                                                                                 
[2024-01-30 00:31:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 47%|█████████████████████████████████████████████████▉                                                         | 91/195 [00:17<00:13,  7.69it/s]
                                                                                                                                                 
[2024-01-30 00:31:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 47%|█████████████████████████████████████████████████▉                                                         | 91/195 [00:17<00:13,  7.69it/s]
                                                                                                                                                 
[2024-01-30 00:31:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 47%|█████████████████████████████████████████████████▉                                                         | 91/195 [00:17<00:13,  7.69it/s]
 48%|███████████████████████████████████████████████████                                                        | 93/195 [00:17<00:12,  8.13it/s]
                                                                                                                                                 
[2024-01-30 00:31:34] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (4096,), dtype: float16
+
 48%|███████████████████████████████████████████████████                                                        | 93/195 [00:17<00:12,  8.13it/s]
                                                                                                                                                 
[2024-01-30 00:31:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 48%|███████████████████████████████████████████████████                                                        | 93/195 [00:17<00:12,  8.13it/s]
                                                                                                                                                 
[2024-01-30 00:31:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 48%|███████████████████████████████████████████████████                                                        | 93/195 [00:17<00:12,  8.13it/s]
 49%|████████████████████████████████████████████████████▏                                                      | 95/195 [00:17<00:10,  9.49it/s]
                                                                                                                                                 
[2024-01-30 00:31:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 49%|████████████████████████████████████████████████████▏                                                      | 95/195 [00:18<00:10,  9.49it/s]
                                                                                                                                                 
[2024-01-30 00:31:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 49%|████████████████████████████████████████████████████▏                                                      | 95/195 [00:18<00:10,  9.49it/s]
                                                                                                                                                 
[2024-01-30 00:31:34] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 49%|██████████████████████████���█████████████████████████▏                                                      | 95/195 [00:18<00:10,  9.49it/s]
 50%|█████████████████████████████████████████████████████▏                                                     | 97/195 [00:18<00:11,  8.59it/s]
                                                                                                                                                 
[2024-01-30 00:31:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 50%|█████████████████████████████████████████████████████▏                                                     | 97/195 [00:18<00:11,  8.59it/s]
                                                                                                                                                 
[2024-01-30 00:31:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 50%|█████████████████████████████████████████████████████▏                                                     | 97/195 [00:18<00:11,  8.59it/s]
                                                                                                                                                 
[2024-01-30 00:31:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 50%|█████████████████████████████████████████████████████▏                                                     | 97/195 [00:18<00:11,  8.59it/s]
                                                                                                                                                 
[2024-01-30 00:31:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 50%|█████████████████████████████████████████████████████▏                                                     | 97/195 [00:18<00:11,  8.59it/s]
 51%|██████████████████████████████████████████████████████▎                                                    | 99/195 [00:18<00:10,  8.96it/s]
                                                                                                                                                 
[2024-01-30 00:31:35] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (4096,), dtype: float16
+
 51%|██████████████████████████████████████████████████████▎                                                    | 99/195 [00:18<00:10,  8.96it/s]
                                                                                                                                                 
[2024-01-30 00:31:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 51%|██████████████████████████████████████████████████████▎                                                    | 99/195 [00:18<00:10,  8.96it/s]
                                                                                                                                                 
[2024-01-30 00:31:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 51%|██████████████████████████████████████████████████████▎                                                    | 99/195 [00:18<00:10,  8.96it/s]
 52%|██████████████████████████████████████████████████████▉                                                   | 101/195 [00:18<00:09, 10.34it/s]
                                                                                                                                                 
[2024-01-30 00:31:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 52%|██████████████████████████████████████████████████████▉                                                   | 101/195 [00:18<00:09, 10.34it/s]
                                                                                                                                                 
[2024-01-30 00:31:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 52%|██████████████████████████████████████████████████████▉                                                   | 101/195 [00:18<00:09, 10.34it/s]
                                                                                                                                                 
[2024-01-30 00:31:35] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 52%|██████████████████████████████████████████████████████▉                                                   | 101/195 [00:18<00:09, 10.34it/s]
 53%|███████████████████████████████████████████████████████▉                                                  | 103/195 [00:18<00:10,  9.03it/s]
                                                                                                                                                 
[2024-01-30 00:31:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 53%|███████████████████████████████████████████████████████▉                                                  | 103/195 [00:19<00:10,  9.03it/s]
                                                                                                                                                 
[2024-01-30 00:31:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 53%|███████████████████████████████████████████████████████▉                                                  | 103/195 [00:19<00:10,  9.03it/s]
                                                                                                                                                 
[2024-01-30 00:31:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 53%|███████████████████████████████████████████████████████▉                                                  | 103/195 [00:19<00:10,  9.03it/s]
                                                                                                                                                 
[2024-01-30 00:31:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 53%|███████████████████████████████████████████████████████▉                                                  | 103/195 [00:19<00:10,  9.03it/s]
 54%|█████████████████████████████████████████████████████████                                                 | 105/195 [00:19<00:09,  9.20it/s]
                                                                                                                                                 
[2024-01-30 00:31:35] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (4096,), dtype: float16
+
 54%|█████████████████████████████████████████████████████████                                                 | 105/195 [00:19<00:09,  9.20it/s]
                                                                                                                                                 
[2024-01-30 00:31:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 54%|█████████████████████████████████████████████████████████                                                 | 105/195 [00:19<00:09,  9.20it/s]
                                                                                                                                                 
[2024-01-30 00:31:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 54%|█████████████████████████████████████████████████████████                                                 | 105/195 [00:19<00:09,  9.20it/s]
 55%|██████████████████████████████████████████████████████████▏                                               | 107/195 [00:19<00:08, 10.58it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 55%|██████████████████████████████████████████████████████████▏                                               | 107/195 [00:19<00:08, 10.58it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 55%|██████████████████████████████████████████████████████████▏                                               | 107/195 [00:19<00:08, 10.58it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 55%|██████████████████████████████████████████████████████████▏                                               | 107/195 [00:19<00:08, 10.58it/s]
 56%|███████████████████████████████████████████████████████████▎                                              | 109/195 [00:19<00:09,  9.18it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 56%|███████████████████████████████████████████████████████████▎                                              | 109/195 [00:19<00:09,  9.18it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 56%|███████████████████████████████████████████████████████████▎                                              | 109/195 [00:19<00:09,  9.18it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 56%|███████████████████████████████████████████████████████████▎                                              | 109/195 [00:19<00:09,  9.18it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 56%|███████████████████████████████████████████████████████████▎                                              | 109/195 [00:19<00:09,  9.18it/s]
 57%|████████████████████████████████████████████████████████████▎                                             | 111/195 [00:19<00:08,  9.35it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (4096,), dtype: float16
+
 57%|████████████████████████████████████████████████████████████▎                                             | 111/195 [00:19<00:08,  9.35it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 57%|████████████████████████████████████████████████████████████▎                                             | 111/195 [00:19<00:08,  9.35it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 57%|████████████████████████████████████████████████████████████▎                                             | 111/195 [00:19<00:08,  9.35it/s]
 58%|█████████████████████████████████████████████████████████████▍                                            | 113/195 [00:19<00:07, 10.69it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 58%|█████████████████████████████████████████████████████████████▍                                            | 113/195 [00:20<00:07, 10.69it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 58%|█████████████████████████████████████████████████████████████▍                                            | 113/195 [00:20<00:07, 10.69it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 58%|█████████████████████████████████████████████████████████████▍                                            | 113/195 [00:20<00:07, 10.69it/s]
 59%|██████████████████████████████████████████████████████████████▌                                           | 115/195 [00:20<00:08,  9.27it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 59%|████████████████████████████████████████████████████████████���█▌                                           | 115/195 [00:20<00:08,  9.27it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 59%|██████████████████████████████████████████████████████████████▌                                           | 115/195 [00:20<00:08,  9.27it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 59%|██████████████████████████████████████████████████████████████▌                                           | 115/195 [00:20<00:08,  9.27it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 59%|██████████████████████████████████████████████████████████████▌                                           | 115/195 [00:20<00:08,  9.27it/s]
 60%|███████████████████████████████████████████████████████████████▌                                          | 117/195 [00:20<00:08,  9.35it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (4096,), dtype: float16
+
 60%|███████████████████████████████████████████████████████████████▌                                          | 117/195 [00:20<00:08,  9.35it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 60%|███████████████████████████████████████████████████████████████▌                                          | 117/195 [00:20<00:08,  9.35it/s]
                                                                                                                                                 
[2024-01-30 00:31:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 60%|███████████████████████████████████████████████████████████████▌                                          | 117/195 [00:20<00:08,  9.35it/s]
 61%|████████████████████████████████████████████████████████████████▋                                         | 119/195 [00:20<00:07, 10.72it/s]
                                                                                                                                                 
[2024-01-30 00:31:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 61%|████████████████████████████████████████████████████████████████▋                                         | 119/195 [00:20<00:07, 10.72it/s]
                                                                                                                                                 
[2024-01-30 00:31:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 61%|██████████████████████████���█████████████████████████████████████▋                                         | 119/195 [00:20<00:07, 10.72it/s]
                                                                                                                                                 
[2024-01-30 00:31:37] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 61%|████████████████████████████████████████████████████████████████▋                                         | 119/195 [00:20<00:07, 10.72it/s]
 62%|█████████████████████████████████████████████████████████████████▊                                        | 121/195 [00:20<00:08,  9.22it/s]
                                                                                                                                                 
[2024-01-30 00:31:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 62%|█████████████████████████████████████████████████████████████████▊                                        | 121/195 [00:20<00:08,  9.22it/s]
                                                                                                                                                 
[2024-01-30 00:31:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 62%|█████████████████████████████████████████████████████████████████▊                                        | 121/195 [00:20<00:08,  9.22it/s]
                                                                                                                                                 
[2024-01-30 00:31:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 62%|█████████████████████████████████████████████████████████████████▊                                        | 121/195 [00:20<00:08,  9.22it/s]
                                                                                                                                                 
[2024-01-30 00:31:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 62%|█████████████████████████████████████████████████████████████████▊                                        | 121/195 [00:20<00:08,  9.22it/s]
 63%|██████████████████████████████████████████████████████████████████▊                                       | 123/195 [00:20<00:07,  9.37it/s]
                                                                                                                                                 
[2024-01-30 00:31:37] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (4096,), dtype: float16
+
 63%|██████████████████████████████████████████████████████████████████▊                                       | 123/195 [00:20<00:07,  9.37it/s]
                                                                                                                                                 
[2024-01-30 00:31:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 63%|██████████████████████████████████████████████████████████████████▊                                       | 123/195 [00:21<00:07,  9.37it/s]
                                                                                                                                                 
[2024-01-30 00:31:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 63%|██████████████████████████████████████████████████████████████████▊                                       | 123/195 [00:21<00:07,  9.37it/s]
 64%|███████████████████████████████████████████████████████████████████▉                                      | 125/195 [00:21<00:06, 10.70it/s]
                                                                                                                                                 
[2024-01-30 00:31:37] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 64%|███████████████████████████████████████████████████████████████████▉                                      | 125/195 [00:21<00:06, 10.70it/s]
                                                                                                                                                 
[2024-01-30 00:31:37] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (4096,), dtype: float16
+
 64%|███████████████████████████████████████████████████████████████████▉                                      | 125/195 [00:21<00:06, 10.70it/s]
                                                                                                                                                 
[2024-01-30 00:31:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 64%|███████████████████████████████████████████████████████████████████▉                                      | 125/195 [00:21<00:06, 10.70it/s]
                                                                                                                                                 
[2024-01-30 00:31:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 64%|███████████████████████████████████████████████████████████████████▉                                      | 125/195 [00:21<00:06, 10.70it/s]
 66%|█████████████████████████████████████████████████████████████████████▌                                    | 128/195 [00:21<00:04, 13.65it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 66%|█████████████████████████████████████████████████████████████████████▌                                    | 128/195 [00:21<00:04, 13.65it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 66%|█████████████████████████████████████████████████████████████████████▌                                    | 128/195 [00:21<00:04, 13.65it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 66%|█████████████████████████████████████████████████████████████████████▌                                    | 128/195 [00:21<00:04, 13.65it/s]
 67%|████���█████████████████████████████████████████████████████████████████▋                                   | 130/195 [00:21<00:05, 10.86it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 67%|██████████████████████████████████████████████████████████████████████▋                                   | 130/195 [00:21<00:05, 10.86it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 67%|██████████████████████████████████████████████████████████████████████▋                                   | 130/195 [00:21<00:05, 10.86it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 67%|██████████████████████████████████████████████████████████████████████▋                                   | 130/195 [00:21<00:05, 10.86it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 67%|██████████████████████████████████████████████████████████████████████▋                                   | 130/195 [00:21<00:05, 10.86it/s]
 68%|███████████████████████████████████████████████████████████████████████▊                                  | 132/195 [00:21<00:06, 10.46it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (4096,), dtype: float16
+
 68%|███████████████████████████████████████████████████████████████████████▊                                  | 132/195 [00:21<00:06, 10.46it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 68%|███████████████████████████████████████████████████████████████████████▊                                  | 132/195 [00:21<00:06, 10.46it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 68%|███████████████████████████████████████████████████████████████████████▊                                  | 132/195 [00:21<00:06, 10.46it/s]
 69%|████████████████████████████████████████████████████████████████████████▊                                 | 134/195 [00:21<00:05, 11.65it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 69%|████████████████████████████████████████████████████████████████████████▊                                 | 134/195 [00:22<00:05, 11.65it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 69%|████████████████████████████████████████████████████████████████████████▊                                 | 134/195 [00:22<00:05, 11.65it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 69%|████████████████████████████████████████████████████████████████████████▊                                 | 134/195 [00:22<00:05, 11.65it/s]
 70%|█████████████████████████████████████████████████████████████████████████▉                                | 136/195 [00:22<00:05,  9.85it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 70%|█████████████████████████████████████████████████████████████████████████▉                                | 136/195 [00:22<00:05,  9.85it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 70%|█████████████████████████████████████████████████████████████████████████▉                                | 136/195 [00:22<00:05,  9.85it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 70%|█████████████████████████████████████████████████████████████████████████▉                                | 136/195 [00:22<00:05,  9.85it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 70%|█████████████████████████████████████████████████████████████████████████▉                                | 136/195 [00:22<00:05,  9.85it/s]
 71%|███████████████████████████████████████████████████████████████████████████                               | 138/195 [00:22<00:05,  9.87it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (4096,), dtype: float16
+
 71%|███████████████████████████████████████████████████████████████████████████                               | 138/195 [00:22<00:05,  9.87it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 71%|███████████████████████████████████████████████████████████████████████████                               | 138/195 [00:22<00:05,  9.87it/s]
                                                                                                                                                 
[2024-01-30 00:31:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 71%|███████████████████████████████████████████████████████████████████████████                               | 138/195 [00:22<00:05,  9.87it/s]
 72%|████████████████████████████████████████████████████████████████████████████                              | 140/195 [00:22<00:04, 11.20it/s]
                                                                                                                                                 
[2024-01-30 00:31:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 72%|████████████████████████████████████████████████████████████████████████████                              | 140/195 [00:22<00:04, 11.20it/s]
                                                                                                                                                 
[2024-01-30 00:31:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 72%|████████████████████████████████████████████████████████████████████████████                              | 140/195 [00:22<00:04, 11.20it/s]
                                                                                                                                                 
[2024-01-30 00:31:39] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 72%|████████████████████████████████████████████████████████████████████████████                              | 140/195 [00:22<00:04, 11.20it/s]
 73%|█████████████████████████████████████████████████████████████████████████████▏                            | 142/195 [00:22<00:05,  9.60it/s]
                                                                                                                                                 
[2024-01-30 00:31:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 73%|█████████████████████████████████████████████████████████████████████████████▏                            | 142/195 [00:22<00:05,  9.60it/s]
                                                                                                                                                 
[2024-01-30 00:31:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 73%|█████████████████████████████████████████████████████████████████████████████▏                            | 142/195 [00:22<00:05,  9.60it/s]
                                                                                                                                                 
[2024-01-30 00:31:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 73%|█████████████████████████████████████████████████████████████████████████████▏                            | 142/195 [00:22<00:05,  9.60it/s]
                                                                                                                                                 
[2024-01-30 00:31:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 73%|█████████████████████████████████████████████████████████████████████████████▏                            | 142/195 [00:22<00:05,  9.60it/s]
 74%|██████████████████████████████████████████████████████████████████████████████▎                           | 144/195 [00:22<00:05,  9.60it/s]
                                                                                                                                                 
[2024-01-30 00:31:39] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (4096,), dtype: float16
+
 74%|██████████████████████████████████████████████████████████████████████████████▎                           | 144/195 [00:22<00:05,  9.60it/s]
                                                                                                                                                 
[2024-01-30 00:31:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 74%|██████████████████████████████████████████████████████████████████████████████▎                           | 144/195 [00:23<00:05,  9.60it/s]
                                                                                                                                                 
[2024-01-30 00:31:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 74%|██████████████████████████████████████████████████████████████████████████████▎                           | 144/195 [00:23<00:05,  9.60it/s]
 75%|███████████████████████████████████████████████████████████████████████████████▎                          | 146/195 [00:23<00:04, 10.93it/s]
                                                                                                                                                 
[2024-01-30 00:31:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 75%|███████████████████████████████████████████████████████████████████████████████▎                          | 146/195 [00:23<00:04, 10.93it/s]
                                                                                                                                                 
[2024-01-30 00:31:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 75%|███████████████████████████████████████████████████████████████████████████████▎                          | 146/195 [00:23<00:04, 10.93it/s]
                                                                                                                                                 
[2024-01-30 00:31:39] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 75%|███████████████████████████████████████████████████████████████████████████████▎                          | 146/195 [00:23<00:04, 10.93it/s]
 76%|████████████████████████████████████████████████████████████████████████████████▍                         | 148/195 [00:23<00:05,  9.36it/s]
                                                                                                                                                 
[2024-01-30 00:31:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 76%|████████████████████████████████████████████████████████████████████████████████▍                         | 148/195 [00:23<00:05,  9.36it/s]
                                                                                                                                                 
[2024-01-30 00:31:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 76%|████████████████████████████████████████████████████████████████████████████████▍                         | 148/195 [00:23<00:05,  9.36it/s]
                                                                                                                                                 
[2024-01-30 00:31:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 76%|████████████████████████████████████████████████████████████████████████████████▍                         | 148/195 [00:23<00:05,  9.36it/s]
                                                                                                                                                 
[2024-01-30 00:31:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 76%|████████████████████████████████████████████████████████████████████████████████▍                         | 148/195 [00:23<00:05,  9.36it/s]
 77%|█████████████████████████████████████████████████████████████████████████████████▌                        | 150/195 [00:23<00:04,  9.46it/s]
                                                                                                                                                 
[2024-01-30 00:31:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (4096,), dtype: float16
+
 77%|█████████████████████████████████████████████████████████████████████████████████▌                        | 150/195 [00:23<00:04,  9.46it/s]
                                                                                                                                                 
[2024-01-30 00:31:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 77%|█████████████████████████████████████████████████████████████████████████████████▌                        | 150/195 [00:23<00:04,  9.46it/s]
                                                                                                                                                 
[2024-01-30 00:31:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 77%|█████████████████████████████████████████████████████████████████████████████████▌                        | 150/195 [00:23<00:04,  9.46it/s]
 78%|██████████████████████████████████████████████████████████████████████████████████▋                       | 152/195 [00:23<00:03, 10.81it/s]
                                                                                                                                                 
[2024-01-30 00:31:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 78%|██████████████████████████████████████████████████████████████████████████████████▋                       | 152/195 [00:23<00:03, 10.81it/s]
                                                                                                                                                 
[2024-01-30 00:31:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 78%|██████████████████████████████████████████████████████████████████████████████████▋                       | 152/195 [00:23<00:03, 10.81it/s]
                                                                                                                                                 
[2024-01-30 00:31:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 78%|██████████████████████████████████████████████████████████████████████████████████▋                       | 152/195 [00:23<00:03, 10.81it/s]
 79%|███████████████████████████████████████████████████████████████████████████████████▋                      | 154/195 [00:23<00:04,  9.28it/s]
                                                                                                                                                 
[2024-01-30 00:31:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 79%|███████████████████████████████████████████████████████████████████████████████████▋                      | 154/195 [00:24<00:04,  9.28it/s]
                                                                                                                                                 
[2024-01-30 00:31:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 79%|███████████████████████████████████████████████████████████████████████████████████▋                      | 154/195 [00:24<00:04,  9.28it/s]
                                                                                                                                                 
[2024-01-30 00:31:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 79%|███████████████████████████████████████████████████████████████████████████████████▋                      | 154/195 [00:24<00:04,  9.28it/s]
                                                                                                                                                 
[2024-01-30 00:31:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 79%|███████████████████████████████████████��███████████████████████████████████████████▋                      | 154/195 [00:24<00:04,  9.28it/s]
 80%|████████████████████████████████████████████████████████████████████████████████████▊                     | 156/195 [00:24<00:04,  9.37it/s]
                                                                                                                                                 
[2024-01-30 00:31:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (4096,), dtype: float16
+
 80%|████████████████████████████████████████████████████████████████████████████████████▊                     | 156/195 [00:24<00:04,  9.37it/s]
                                                                                                                                                 
[2024-01-30 00:31:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 80%|████████████████████████████████████████████████████████████████████████████████████▊                     | 156/195 [00:24<00:04,  9.37it/s]
                                                                                                                                                 
[2024-01-30 00:31:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 80%|████████████████████████████████████████████████████████████████████████████████████▊                     | 156/195 [00:24<00:04,  9.37it/s]
 81%|█████████████████████████████████████████████████████████████████████████████████████▉                    | 158/195 [00:24<00:03, 10.74it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 81%|█████████████████████████████████████████████████████████████████████████████████████▉                    | 158/195 [00:24<00:03, 10.74it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 81%|█████████████████████████████████████████████████████████████████████████████████████▉                    | 158/195 [00:24<00:03, 10.74it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 81%|█████████████████████████████████████████████████████████████████████████████████████▉                    | 158/195 [00:24<00:03, 10.74it/s]
 82%|██████████████████████████████████████████████████████████████████████████████████████▉                   | 160/195 [00:24<00:03,  9.30it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 82%|██████████████████████████████████████████████████████████████████████████████████████▉                   | 160/195 [00:24<00:03,  9.30it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 82%|██████████████████████████████████████████████████████████████████████████████████████▉                   | 160/195 [00:24<00:03,  9.30it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 82%|██████████████████████████████████████████████████████████████████████████████████████▉                   | 160/195 [00:24<00:03,  9.30it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 82%|██████████████████████████████████████████████████████████████████████████████████████▉                   | 160/195 [00:24<00:03,  9.30it/s]
 83%|████████████████████████████████████████████████████████████████████████████████████████                  | 162/195 [00:24<00:03,  9.45it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (4096,), dtype: float16
+
 83%|████████████████████████████████████████████████████████████████████████████████████████                  | 162/195 [00:24<00:03,  9.45it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 83%|████████████████████████████████████████████████████████████████████████████████████████                  | 162/195 [00:24<00:03,  9.45it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 83%|████████████████████████████████████████████████████████████████████████████████████████                  | 162/195 [00:24<00:03,  9.45it/s]
 84%|█████████████████████████████████████████████████████████████████████████████████████████▏                | 164/195 [00:24<00:02, 10.77it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 84%|█████████████████████████████████████████████████████████████████████████████████████████▏                | 164/195 [00:25<00:02, 10.77it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 84%|█████████████████████████████████████████████████████████████████████████████████████████▏                | 164/195 [00:25<00:02, 10.77it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 84%|█████████████████████████████████████████████████████████████████████████████████████████▏                | 164/195 [00:25<00:02, 10.77it/s]
 85%|██████████████████████████████████████████████████████████████████████████████████████████▏               | 166/195 [00:25<00:03,  9.31it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 85%|██████████████████████████████████████████████████████████████████████████████████████████▏               | 166/195 [00:25<00:03,  9.31it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 85%|██████████████████████████████████████████████████████████████████████████████████████████▏               | 166/195 [00:25<00:03,  9.31it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 85%|██████████████████████████████████████████████████████████████████████████████████████████▏               | 166/195 [00:25<00:03,  9.31it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 85%|██████████████████████████████████████████████████████████████████████████████████████████▏               | 166/195 [00:25<00:03,  9.31it/s]
 86%|███████████████████████████████████████████████████████████████████████████████████████████▎              | 168/195 [00:25<00:02,  9.43it/s]
                                                                                                                                                 
[2024-01-30 00:31:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (4096,), dtype: float16
+
 86%|███████████████████████████████████████████████████████████████████████████████████████████▎              | 168/195 [00:25<00:02,  9.43it/s]
                                                                                                                                                 
[2024-01-30 00:31:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 86%|███████████████████████████████████████████████████████████████████████████████████████████▎              | 168/195 [00:25<00:02,  9.43it/s]
                                                                                                                                                 
[2024-01-30 00:31:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 86%|███████████████████████████████████████████████████████████████████████████████████████████▎              | 168/195 [00:25<00:02,  9.43it/s]
 87%|████████████████████████████████████████████████████████████████████████████████████████████▍             | 170/195 [00:25<00:02, 10.79it/s]
                                                                                                                                                 
[2024-01-30 00:31:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 87%|████████████████████████████████████████████████████████████████████████████████████████████▍             | 170/195 [00:25<00:02, 10.79it/s]
                                                                                                                                                 
[2024-01-30 00:31:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 87%|████████████████████████████████████████████████████████████████████████████████████████████▍             | 170/195 [00:25<00:02, 10.79it/s]
                                                                                                                                                 
[2024-01-30 00:31:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 87%|████████████████████████████████████████████████████████████████████████████████████████████▍             | 170/195 [00:25<00:02, 10.79it/s]
 88%|█████████████████████████████████████████████████████████████████████████████████████████████▍            | 172/195 [00:25<00:02,  9.27it/s]
                                                                                                                                                 
[2024-01-30 00:31:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 88%|█████████████████████████████████████████████████████████████████████████████████████████████▍            | 172/195 [00:25<00:02,  9.27it/s]
                                                                                                                                                 
[2024-01-30 00:31:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 88%|█████████████████████████████████████████████████████████████████████████████████████████████▍            | 172/195 [00:25<00:02,  9.27it/s]
                                                                                                                                                 
[2024-01-30 00:31:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 88%|█████████████████████████████████████████████████████████████████████████████████████████████▍            | 172/195 [00:25<00:02,  9.27it/s]
                                                                                                                                                 
[2024-01-30 00:31:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 88%|█████████████████████████████████████████████████████████████████████████████████████████████▍            | 172/195 [00:25<00:02,  9.27it/s]
 89%|██████████████████████████████████████████████████████████████████████████████████████████████▌           | 174/195 [00:25<00:02,  9.39it/s]
                                                                                                                                                 
[2024-01-30 00:31:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (4096,), dtype: float16
+
 89%|██████████████████████████████████████████████████████████████████████████████████████████████▌           | 174/195 [00:25<00:02,  9.39it/s]
                                                                                                                                                 
[2024-01-30 00:31:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 89%|██████████████████████████████████████████████████████████████████████████████████████████████▌           | 174/195 [00:26<00:02,  9.39it/s]
                                                                                                                                                 
[2024-01-30 00:31:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 89%|██████████████████████████████████████████████████████████████████████████████████████████████▌           | 174/195 [00:26<00:02,  9.39it/s]
 90%|███████████████████████████████████████████████████████████████████████████████████████████████▋          | 176/195 [00:26<00:01, 10.73it/s]
                                                                                                                                                 
[2024-01-30 00:31:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 90%|███████████████████████████████████████████████████████████████████████████████████████████████▋          | 176/195 [00:26<00:01, 10.73it/s]
                                                                                                                                                 
[2024-01-30 00:31:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 90%|███████████████████████████████████████████████████████████████████████████████████████████████▋          | 176/195 [00:26<00:01, 10.73it/s]
                                                                                                                                                 
[2024-01-30 00:31:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 90%|███████████████████████████████████████████████████████████████████████████████████████████████▋          | 176/195 [00:26<00:01, 10.73it/s]
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▊         | 178/195 [00:26<00:01,  9.29it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▊         | 178/195 [00:26<00:01,  9.29it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▊         | 178/195 [00:26<00:01,  9.29it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▊         | 178/195 [00:26<00:01,  9.29it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▊         | 178/195 [00:26<00:01,  9.29it/s]
 92%|█████████████████████████████████████████████████████████████████████████████████████████████████▊        | 180/195 [00:26<00:01,  9.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (4096,), dtype: float16
+
 92%|█████████████████████████████████████████████████████████████████████████████████████████████████▊        | 180/195 [00:26<00:01,  9.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 92%|█████████████████████████████████████████████████████████████████████████████████████████████████▊        | 180/195 [00:26<00:01,  9.41it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 92%|█████████████████████████████████████████████████████████████████████████████████████████████████▊        | 180/195 [00:26<00:01,  9.41it/s]
 93%|██████████████████████████████████████████████████████████████████████████████████████████████████▉       | 182/195 [00:26<00:01, 10.78it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 93%|██████████████████████████████████████████████████████████████████████████████████████████████████▉       | 182/195 [00:26<00:01, 10.78it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 93%|██████████████████████████████████████████████████████████████████████████████████████████████████▉       | 182/195 [00:26<00:01, 10.78it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 93%|██████████████████████████████████████████████████████████████████████████████████████████████████▉       | 182/195 [00:26<00:01, 10.78it/s]
 94%|████████████████████████████████████████████████████████████████████████████████████████████████████      | 184/195 [00:26<00:01,  9.30it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 94%|████████████████████████████████████████████████████████████████████████████████████████████████████      | 184/195 [00:27<00:01,  9.30it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 94%|████████████████████████████████████████████████████████████████████████████████████████████████████      | 184/195 [00:27<00:01,  9.30it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 94%|████████████████████████████████████████████████████████████████████████████████████████████████████      | 184/195 [00:27<00:01,  9.30it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 94%|████████████████████████████████████████████████████████████████████████████████████████████████████      | 184/195 [00:27<00:01,  9.30it/s]
 95%|█████████████████████████████████████████████████████████████████████████████████████████████████████     | 186/195 [00:27<00:00,  9.38it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (4096,), dtype: float16
+
 95%|█████████████████████████████████████████████████████████████████████████████████████████████████████     | 186/195 [00:27<00:00,  9.38it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (4096, 1376), dtype: uint32
+
 95%|█████████████████████████████████████████████████████████████████████████████████████████████████████     | 186/195 [00:27<00:00,  9.38it/s]
                                                                                                                                                 
[2024-01-30 00:31:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (4096, 344), dtype: float16
+
 95%|█████████████████████████████████████████████████████████████████████████████████████████████████████     | 186/195 [00:27<00:00,  9.38it/s]
 96%|██████████████████████████████████████████████████████████████████████████████████████████████████████▏   | 188/195 [00:27<00:00, 10.73it/s]
                                                                                                                                                 
[2024-01-30 00:31:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 96%|██████████████████████████████████████████████████████████████████████████████████████████████████████▏   | 188/195 [00:27<00:00, 10.73it/s]
                                                                                                                                                 
[2024-01-30 00:31:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 96%|██████████████████████████████████████████████████████████████████████████████████████████████████████▏   | 188/195 [00:27<00:00, 10.73it/s]
                                                                                                                                                 
[2024-01-30 00:31:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (4096,), dtype: float16
+
 96%|██████████████████████████████████████████████████████████████████████████████████████████████████████▏   | 188/195 [00:27<00:00, 10.73it/s]
 97%|███████████████████████████████████████████████████████████████████████████████████████████████████████▎  | 190/195 [00:27<00:00,  9.31it/s]
                                                                                                                                                 
[2024-01-30 00:31:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 97%|███████████████████████████████████████████████████████████████████████████████████████████████████████▎  | 190/195 [00:27<00:00,  9.31it/s]
                                                                                                                                                 
[2024-01-30 00:31:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 97%|███████████████████████████████████████████████████████████████████████████████████████████████████████▎  | 190/195 [00:27<00:00,  9.31it/s]
                                                                                                                                                 
[2024-01-30 00:31:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 97%|███████████████████████████████████████████████████████████████████████████████████████████████████████▎  | 190/195 [00:27<00:00,  9.31it/s]
                                                                                                                                                 
[2024-01-30 00:31:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 97%|███████████████████████████████████████████████████████████████████████████████████████████████████████▎  | 190/195 [00:27<00:00,  9.31it/s]
 98%|████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 192/195 [00:27<00:00,  9.48it/s]
                                                                                                                                                 
[2024-01-30 00:31:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (22016, 512), dtype: uint32
+
 98%|████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 192/195 [00:28<00:00,  9.48it/s]
                                                                                                                                                 
[2024-01-30 00:31:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (22016, 128), dtype: float16
+
 98%|████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 192/195 [00:28<00:00,  9.48it/s]
                                                                                                                                                 
[2024-01-30 00:31:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_weight", shape: (12288, 512), dtype: uint32
+
 98%|████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 192/195 [00:28<00:00,  9.48it/s]
                                                                                                                                                 
[2024-01-30 00:31:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_scale", shape: (12288, 128), dtype: float16
+
 98%|████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 192/195 [00:28<00:00,  9.48it/s]
 99%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▍| 194/195 [00:28<00:00,  7.21it/s]
                                                                                                                                                 
[2024-01-30 00:31:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (4096, 512), dtype: uint32
+
 99%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▍| 194/195 [00:28<00:00,  7.21it/s]
                                                                                                                                                 
[2024-01-30 00:31:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (4096, 128), dtype: float16
+
 99%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▍| 194/195 [00:28<00:00,  7.21it/s]
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████| 195/195 [00:28<00:00,  6.90it/s]
+[2024-01-30 00:31:44] 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 00:31:44] 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 00:31:45] INFO stats.py:76: Time usage: HF loading: 7.777 sec; Pre-quantization mapping: 18.199 sec; Quantization: 0.701 sec
+[2024-01-30 00:31:45] INFO stats.py:90: RAM usage: Peak RAM: 18.415 GB. Total bytes loaded from disk: 25.103 GB
+[2024-01-30 00:31:45] INFO convert_weight.py:121: Parameter size after quantization: 3.530 GB
+[2024-01-30 00:31:45] INFO convert_weight.py:126: Total parameters: 6,738,415,616
+[2024-01-30 00:31:45] INFO convert_weight.py:127: Bits per parameter: 4.500
+Start storing to cache /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpw9em1i59
+

[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 00:31:52] INFO convert_weight.py:143: Saved to directory: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpw9em1i59
+
                                                                  
[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/tmpw9em1i59/ndarray-cache.json