diff --git "a/logs.txt" "b/logs.txt"
new file mode 100644--- /dev/null
+++ "b/logs.txt"
@@ -0,0 +1,473 @@
+/Users/cfruan/miniconda3/envs/mlc-chat-venv/bin/python -m mlc_chat gen_config /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo --quantization q4f16_1 --conv-template codellama_instruct --output /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y --context-window-size 16384
+[2024-01-30 00:51:30] INFO auto_config.py:115: Found model configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/config.json
+[2024-01-30 00:51:30] INFO auto_config.py:153: Found model type: llama. Use `--model-type` to override.
+[2024-01-30 00:51:30] INFO llama_model.py:51: context_window_size not found in config.json. Falling back to max_position_embeddings (16384)
+[2024-01-30 00:51:30] INFO llama_model.py:71: prefill_chunk_size defaults to context_window_size (16384)
+[2024-01-30 00:51:30] INFO config.py:106: Overriding context_window_size from 16384 to 16384
+[2024-01-30 00:51:30] INFO config.py:106: Overriding max_batch_size from 1 to 80
+[2024-01-30 00:51:30] INFO gen_config.py:116: [generation_config.json] Setting bos_token_id: 1
+[2024-01-30 00:51:30] INFO gen_config.py:116: [generation_config.json] Setting eos_token_id: 2
+[2024-01-30 00:51:30] INFO gen_config.py:128: Found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/tokenizer.model. Copying to /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y/tokenizer.model
+[2024-01-30 00:51:30] INFO gen_config.py:128: Found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/tokenizer.json. Copying to /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y/tokenizer.json
+[2024-01-30 00:51:30] INFO gen_config.py:130: Not found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/vocab.json
+[2024-01-30 00:51:30] INFO gen_config.py:130: Not found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/merges.txt
+[2024-01-30 00:51:30] INFO gen_config.py:130: Not found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/added_tokens.json
+[2024-01-30 00:51:30] INFO gen_config.py:128: Found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/tokenizer_config.json. Copying to /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y/tokenizer_config.json
+[2024-01-30 00:51:30] INFO gen_config.py:69: [System default] Setting pad_token_id: 0
+[2024-01-30 00:51:30] INFO gen_config.py:69: [System default] Setting temperature: 0.7
+[2024-01-30 00:51:30] INFO gen_config.py:69: [System default] Setting repetition_penalty: 1.0
+[2024-01-30 00:51:30] INFO gen_config.py:69: [System default] Setting top_p: 0.95
+[2024-01-30 00:51:30] INFO gen_config.py:69: [System default] Setting mean_gen_len: 128
+[2024-01-30 00:51:30] INFO gen_config.py:69: [System default] Setting max_gen_len: 512
+[2024-01-30 00:51:30] INFO gen_config.py:69: [System default] Setting shift_fill_factor: 0.3
+[2024-01-30 00:51:30] INFO gen_config.py:158: Dumping configuration file to: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y/mlc-chat-config.json
+/Users/cfruan/miniconda3/envs/mlc-chat-venv/bin/python -m mlc_chat convert_weight /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo --quantization q4f16_1 --source-format auto --output /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y
+[2024-01-30 00:51:30] INFO auto_config.py:115: Found model configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/config.json
+[2024-01-30 00:51:31] INFO auto_device.py:85: Not found device: cuda:0
+[2024-01-30 00:51:31] INFO auto_device.py:85: Not found device: rocm:0
+[2024-01-30 00:51:31] INFO auto_device.py:76: Found device: metal:0
+[2024-01-30 00:51:32] INFO auto_device.py:85: Not found device: vulkan:0
+[2024-01-30 00:51:32] INFO auto_device.py:85: Not found device: opencl:0
+[2024-01-30 00:51:32] INFO auto_device.py:33: Using device: metal:0
+[2024-01-30 00:51:32] INFO auto_weight.py:70: Finding weights in: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo
+[2024-01-30 00:51:32] INFO auto_weight.py:120: Found source weight format: huggingface-torch. Source configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model.bin.index.json
+[2024-01-30 00:51:32] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/model.safetensors.index.json
+[2024-01-30 00:51:32] INFO auto_weight.py:106: Using source weight configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model.bin.index.json. Use `--source` to override.
+[2024-01-30 00:51:32] INFO auto_weight.py:110: Using source weight format: huggingface-torch. Use `--source-format` to override.
+[2024-01-30 00:51:32] INFO auto_config.py:153: Found model type: llama. Use `--model-type` to override.
+[2024-01-30 00:51:32] INFO llama_model.py:51: context_window_size not found in config.json. Falling back to max_position_embeddings (16384)
+[2024-01-30 00:51:32] INFO llama_model.py:71: prefill_chunk_size defaults to context_window_size (16384)
+Weight conversion with arguments:
+  --config          /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/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/tmpoi4p39pd/repo/pytorch_model.bin.index.json
+  --source-format   huggingface-torch
+  --output          /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y
+
  0%|                                                                                                                    | 0/243 [00:00<?, ?it/s]
                                                                                                                                                 
[2024-01-30 00:51:37] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model-00003-of-00003.bin
+
  0%|                                                                                                                    | 0/243 [00:00<?, ?it/s]
                                                                                                                                                 
[2024-01-30 00:51:41] INFO group_quantization.py:227: Compiling quantize function for key: ((32000, 5120), float16, metal, axis=1, output_transpose=False)
+
  0%|                                                                                                                    | 0/243 [00:04<?, ?it/s]
                                                                                                                                                 
[2024-01-30 00:51:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "lm_head.q_weight", shape: (32000, 640), dtype: uint32
+
  0%|                                                                                                                    | 0/243 [00:04<?, ?it/s]
                                                                                                                                                 
[2024-01-30 00:51:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "lm_head.q_scale", shape: (32000, 160), dtype: float16
+
  0%|                                                                                                                    | 0/243 [00:04<?, ?it/s]
  0%|▍                                                                                                           | 1/243 [00:04<17:50,  4.43s/it]
                                                                                                                                                 
[2024-01-30 00:51:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.30.input_layernorm.weight", shape: (5120,), dtype: float16
+
  0%|▍                                                                                                           | 1/243 [00:04<17:50,  4.43s/it]
                                                                                                                                                 
[2024-01-30 00:51:41] INFO group_quantization.py:227: Compiling quantize function for key: ((5120, 13824), float16, metal, axis=1, output_transpose=False)
+
  0%|▍                                                                                                           | 1/243 [00:04<17:50,  4.43s/it]
                                                                                                                                                 
[2024-01-30 00:51:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
  0%|▍                                                                                                           | 1/243 [00:04<17:50,  4.43s/it]
                                                                                                                                                 
[2024-01-30 00:51:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
  0%|▍                                                                                                           | 1/243 [00:04<17:50,  4.43s/it]
  1%|█▎                                                                                                          | 3/243 [00:04<04:57,  1.24s/it]
                                                                                                                                                 
[2024-01-30 00:51:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.30.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
  1%|█▎                                                                                                          | 3/243 [00:04<04:57,  1.24s/it]
                                                                                                                                                 
[2024-01-30 00:51:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.31.input_layernorm.weight", shape: (5120,), dtype: float16
+
  1%|█▎                                                                                                          | 3/243 [00:04<04:57,  1.24s/it]
                                                                                                                                                 
[2024-01-30 00:51:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
  1%|█▎                                                                                                          | 3/243 [00:04<04:57,  1.24s/it]
                                                                                                                                                 
[2024-01-30 00:51:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
  1%|█▎                                                                                                          | 3/243 [00:04<04:57,  1.24s/it]
  2%|██▋                                                                                                         | 6/243 [00:04<02:02,  1.93it/s]
                                                                                                                                                 
[2024-01-30 00:51:42] INFO group_quantization.py:227: Compiling quantize function for key: ((27648, 5120), float16, metal, axis=1, output_transpose=False)
+
  2%|██▋                                                                                                         | 6/243 [00:05<02:02,  1.93it/s]
                                                                                                                                                 
[2024-01-30 00:51:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
  2%|██▋                                                                                                         | 6/243 [00:05<02:02,  1.93it/s]
                                                                                                                                                 
[2024-01-30 00:51:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
  2%|██▋                                                                                                         | 6/243 [00:05<02:02,  1.93it/s]
  3%|███                                                                                                         | 7/243 [00:05<02:01,  1.94it/s]
                                                                                                                                                 
[2024-01-30 00:51:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.31.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
  3%|███                                                                                                         | 7/243 [00:05<02:01,  1.94it/s]
                                                                                                                                                 
[2024-01-30 00:51:42] INFO group_quantization.py:227: Compiling quantize function for key: ((15360, 5120), float16, metal, axis=1, output_transpose=False)
+
  3%|███                                                                                                         | 7/243 [00:05<02:01,  1.94it/s]
                                                                                                                                                 
[2024-01-30 00:51:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
  3%|███                                                                                                         | 7/243 [00:05<02:01,  1.94it/s]
                                                                                                                                                 
[2024-01-30 00:51:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
  3%|███                                                                                                         | 7/243 [00:05<02:01,  1.94it/s]
  4%|████                                                                                                        | 9/243 [00:05<01:27,  2.68it/s]
                                                                                                                                                 
[2024-01-30 00:51:42] INFO group_quantization.py:227: Compiling quantize function for key: ((5120, 5120), float16, metal, axis=1, output_transpose=False)
+
  4%|████                                                                                                        | 9/243 [00:05<01:27,  2.68it/s]
                                                                                                                                                 
[2024-01-30 00:51:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
  4%|████                                                                                                        | 9/243 [00:05<01:27,  2.68it/s]
                                                                                                                                                 
[2024-01-30 00:51:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
  4%|████                                                                                                        | 9/243 [00:05<01:27,  2.68it/s]
  4%|████▍                                                                                                      | 10/243 [00:05<01:14,  3.13it/s]
                                                                                                                                                 
[2024-01-30 00:51:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.32.input_layernorm.weight", shape: (5120,), dtype: float16
+
  4%|████▍                                                                                                      | 10/243 [00:05<01:14,  3.13it/s]
                                                                                                                                                 
[2024-01-30 00:51:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.32.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
  4%|████▍                                                                                                      | 10/243 [00:05<01:14,  3.13it/s]
                                                                                                                                                 
[2024-01-30 00:51:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.32.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
  4%|████▍                                                                                                      | 10/243 [00:05<01:14,  3.13it/s]
  5%|█████▎                                                                                                     | 12/243 [00:05<00:53,  4.29it/s]
                                                                                                                                                 
[2024-01-30 00:51:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.32.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
  5%|█████▎                                                                                                     | 12/243 [00:06<00:53,  4.29it/s]
                                                                                                                                                 
[2024-01-30 00:51:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.32.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
  5%|█████▎                                                                                                     | 12/243 [00:06<00:53,  4.29it/s]
  5%|█████▋                                                                                                     | 13/243 [00:06<01:04,  3.58it/s]
                                                                                                                                                 
[2024-01-30 00:51:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.32.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
  5%|█████▋                                                                                                     | 13/243 [00:06<01:04,  3.58it/s]
                                                                                                                                                 
[2024-01-30 00:51:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.32.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
  5%|█████▋                                                                                                     | 13/243 [00:06<01:04,  3.58it/s]
                                                                                                                                                 
[2024-01-30 00:51:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.32.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
  5%|█████▋                                                                                                     | 13/243 [00:06<01:04,  3.58it/s]
  6%|██████▌                                                                                                    | 15/243 [00:06<00:49,  4.56it/s]
                                                                                                                                                 
[2024-01-30 00:51:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.32.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
  6%|██████▌                                                                                                    | 15/243 [00:06<00:49,  4.56it/s]
                                                                                                                                                 
[2024-01-30 00:51:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.32.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
  6%|██████▌                                                                                                    | 15/243 [00:06<00:49,  4.56it/s]
                                                                                                                                                 
[2024-01-30 00:51:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.33.input_layernorm.weight", shape: (5120,), dtype: float16
+
  6%|██████▌                                                                                                    | 15/243 [00:06<00:49,  4.56it/s]
                                                                                                                                                 
[2024-01-30 00:51:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.33.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
  6%|██████▌                                                                                                    | 15/243 [00:06<00:49,  4.56it/s]
                                                                                                                                                 
[2024-01-30 00:51:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.33.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
  6%|██████▌                                                                                                    | 15/243 [00:06<00:49,  4.56it/s]
  7%|███████▉                                                                                                   | 18/243 [00:06<00:36,  6.23it/s]
                                                                                                                                                 
[2024-01-30 00:51:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.33.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
  7%|███████▉                                                                                                   | 18/243 [00:07<00:36,  6.23it/s]
                                                                                                                                                 
[2024-01-30 00:51:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.33.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
  7%|███████▉                                                                                                   | 18/243 [00:07<00:36,  6.23it/s]
  8%|████████▎                                                                                                  | 19/243 [00:07<00:47,  4.72it/s]
                                                                                                                                                 
[2024-01-30 00:51:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.33.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
  8%|████████▎                                                                                                  | 19/243 [00:07<00:47,  4.72it/s]
                                                                                                                                                 
[2024-01-30 00:51:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.33.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
  8%|████████▎                                                                                                  | 19/243 [00:07<00:47,  4.72it/s]
                                                                                                                                                 
[2024-01-30 00:51:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.33.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
  8%|████████▎                                                                                                  | 19/243 [00:07<00:47,  4.72it/s]
  9%|█████████▏                                                                                                 | 21/243 [00:07<00:40,  5.49it/s]
                                                                                                                                                 
[2024-01-30 00:51:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.33.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
  9%|█████████▏                                                                                                 | 21/243 [00:07<00:40,  5.49it/s]
                                                                                                                                                 
[2024-01-30 00:51:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.33.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
  9%|█████████▏                                                                                                 | 21/243 [00:07<00:40,  5.49it/s]
                                                                                                                                                 
[2024-01-30 00:51:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.34.input_layernorm.weight", shape: (5120,), dtype: float16
+
  9%|█████████▏                                                                                                 | 21/243 [00:07<00:40,  5.49it/s]
                                                                                                                                                 
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.34.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
  9%|█████████▏                                                                                                 | 21/243 [00:07<00:40,  5.49it/s]
                                                                                                                                                 
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.34.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
  9%|█████████▏                                                                                                 | 21/243 [00:07<00:40,  5.49it/s]
 10%|██████████▌                                                                                                | 24/243 [00:07<00:31,  6.98it/s]
                                                                                                                                                 
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.34.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 10%|██████████▌                                                                                                | 24/243 [00:08<00:31,  6.98it/s]
                                                                                                                                                 
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.34.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 10%|██████████▌                                                                                                | 24/243 [00:08<00:31,  6.98it/s]
 10%|███████████                                                                                                | 25/243 [00:08<00:42,  5.13it/s]
                                                                                                                                                 
[2024-01-30 00:51:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.34.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 10%|███████████                                                                                                | 25/243 [00:08<00:42,  5.13it/s]
                                                                                                                                                 
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.34.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 10%|███████████                                                                                                | 25/243 [00:08<00:42,  5.13it/s]
                                                                                                                                                 
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.34.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 10%|███████████                                                                                                | 25/243 [00:08<00:42,  5.13it/s]
 11%|███████████▉                                                                                               | 27/243 [00:08<00:37,  5.82it/s]
                                                                                                                                                 
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.34.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 11%|███████████▉                                                                                               | 27/243 [00:08<00:37,  5.82it/s]
                                                                                                                                                 
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.34.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 11%|███████████▉                                                                                               | 27/243 [00:08<00:37,  5.82it/s]
                                                                                                                                                 
[2024-01-30 00:51:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.35.input_layernorm.weight", shape: (5120,), dtype: float16
+
 11%|███████████▉                                                                                               | 27/243 [00:08<00:37,  5.82it/s]
                                                                                                                                                 
[2024-01-30 00:51:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.35.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 11%|███████████▉                                                                                               | 27/243 [00:08<00:37,  5.82it/s]
                                                                                                                                                 
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.35.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 11%|███████████▉                                                                                               | 27/243 [00:08<00:37,  5.82it/s]
 12%|█████████████▏                                                                                             | 30/243 [00:08<00:29,  7.24it/s]
                                                                                                                                                 
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.35.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 12%|█████████████▏                                                                                             | 30/243 [00:09<00:29,  7.24it/s]
                                                                                                                                                 
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.35.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 12%|█████████████▏                                                                                             | 30/243 [00:09<00:29,  7.24it/s]
 13%|█████████████▋                                                                                             | 31/243 [00:09<00:40,  5.28it/s]
                                                                                                                                                 
[2024-01-30 00:51:46] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.35.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 13%|█████████████▋                                                                                             | 31/243 [00:09<00:40,  5.28it/s]
                                                                                                                                                 
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.35.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 13%|█████████████▋                                                                                             | 31/243 [00:09<00:40,  5.28it/s]
                                                                                                                                                 
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.35.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 13%|█████████████▋                                                                                             | 31/243 [00:09<00:40,  5.28it/s]
 14%|██████████████▌                                                                                            | 33/243 [00:09<00:35,  5.94it/s]
                                                                                                                                                 
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.35.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 14%|██████████████▌                                                                                            | 33/243 [00:09<00:35,  5.94it/s]
                                                                                                                                                 
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.35.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 14%|██████████████▌                                                                                            | 33/243 [00:09<00:35,  5.94it/s]
                                                                                                                                                 
[2024-01-30 00:51:46] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.36.input_layernorm.weight", shape: (5120,), dtype: float16
+
 14%|██████████████▌                                                                                            | 33/243 [00:09<00:35,  5.94it/s]
                                                                                                                                                 
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.36.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 14%|██████████████▌                                                                                            | 33/243 [00:09<00:35,  5.94it/s]
                                                                                                                                                 
[2024-01-30 00:51:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.36.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 14%|██████████████▌                                                                                            | 33/243 [00:09<00:35,  5.94it/s]
 15%|███████████████▊                                                                                           | 36/243 [00:09<00:28,  7.36it/s]
                                                                                                                                                 
[2024-01-30 00:51:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.36.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 15%|███████████████▊                                                                                           | 36/243 [00:10<00:28,  7.36it/s]
                                                                                                                                                 
[2024-01-30 00:51:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.36.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 15%|███████████████▊                                                                                           | 36/243 [00:10<00:28,  7.36it/s]
 15%|████████████████▎                                                                                          | 37/243 [00:10<00:38,  5.34it/s]
                                                                                                                                                 
[2024-01-30 00:51:47] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.36.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 15%|████████████████▎                                                                                          | 37/243 [00:10<00:38,  5.34it/s]
                                                                                                                                                 
[2024-01-30 00:51:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.36.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 15%|████████████████▎                                                                                          | 37/243 [00:10<00:38,  5.34it/s]
                                                                                                                                                 
[2024-01-30 00:51:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.36.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 15%|████████████████▎                                                                                          | 37/243 [00:10<00:38,  5.34it/s]
 16%|█████████████████▏                                                                                         | 39/243 [00:10<00:34,  5.95it/s]
                                                                                                                                                 
[2024-01-30 00:51:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.36.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 16%|█████████████████▏                                                                                         | 39/243 [00:10<00:34,  5.95it/s]
                                                                                                                                                 
[2024-01-30 00:51:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.36.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 16%|█████████████████▏                                                                                         | 39/243 [00:10<00:34,  5.95it/s]
                                                                                                                                                 
[2024-01-30 00:51:47] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.37.input_layernorm.weight", shape: (5120,), dtype: float16
+
 16%|█████████████████▏                                                                                         | 39/243 [00:10<00:34,  5.95it/s]
                                                                                                                                                 
[2024-01-30 00:51:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.37.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 16%|█████████████████▏                                                                                         | 39/243 [00:10<00:34,  5.95it/s]
                                                                                                                                                 
[2024-01-30 00:51:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.37.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 16%|█████████████████▏                                                                                         | 39/243 [00:10<00:34,  5.95it/s]
 17%|██████████████████▍                                                                                        | 42/243 [00:10<00:27,  7.36it/s]
                                                                                                                                                 
[2024-01-30 00:51:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.37.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 17%|██████████████████▍                                                                                        | 42/243 [00:11<00:27,  7.36it/s]
                                                                                                                                                 
[2024-01-30 00:51:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.37.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 17%|██████████████████▍                                                                                        | 42/243 [00:11<00:27,  7.36it/s]
 18%|██████████████████▉                                                                                        | 43/243 [00:11<00:37,  5.36it/s]
                                                                                                                                                 
[2024-01-30 00:51:48] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.37.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 18%|██████████████████▉                                                                                        | 43/243 [00:11<00:37,  5.36it/s]
                                                                                                                                                 
[2024-01-30 00:51:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.37.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 18%|██████████████████▉                                                                                        | 43/243 [00:11<00:37,  5.36it/s]
                                                                                                                                                 
[2024-01-30 00:51:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.37.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 18%|██████████████████▉                                                                                        | 43/243 [00:11<00:37,  5.36it/s]
 19%|███████████████████▊                                                                                       | 45/243 [00:11<00:32,  6.01it/s]
                                                                                                                                                 
[2024-01-30 00:51:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.37.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 19%|███████████████████▊                                                                                       | 45/243 [00:11<00:32,  6.01it/s]
                                                                                                                                                 
[2024-01-30 00:51:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.37.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 19%|███████████████████▊                                                                                       | 45/243 [00:11<00:32,  6.01it/s]
                                                                                                                                                 
[2024-01-30 00:51:48] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.38.input_layernorm.weight", shape: (5120,), dtype: float16
+
 19%|███████████████████▊                                                                                       | 45/243 [00:11<00:32,  6.01it/s]
                                                                                                                                                 
[2024-01-30 00:51:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.38.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 19%|███████████████████▊                                                                                       | 45/243 [00:11<00:32,  6.01it/s]
                                                                                                                                                 
[2024-01-30 00:51:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.38.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 19%|███████████████████▊                                                                                       | 45/243 [00:11<00:32,  6.01it/s]
 20%|█████████████████████▏                                                                                     | 48/243 [00:11<00:26,  7.40it/s]
                                                                                                                                                 
[2024-01-30 00:51:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.38.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 20%|█████████████████████▏                                                                                     | 48/243 [00:12<00:26,  7.40it/s]
                                                                                                                                                 
[2024-01-30 00:51:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.38.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 20%|█████████████████████▏                                                                                     | 48/243 [00:12<00:26,  7.40it/s]
 20%|█████████████████████▌                                                                                     | 49/243 [00:12<00:35,  5.40it/s]
                                                                                                                                                 
[2024-01-30 00:51:49] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.38.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 20%|█████████████████████▌                                                                                     | 49/243 [00:12<00:35,  5.40it/s]
                                                                                                                                                 
[2024-01-30 00:51:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.38.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 20%|█████████████████████▌                                                                                     | 49/243 [00:12<00:35,  5.40it/s]
                                                                                                                                                 
[2024-01-30 00:51:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.38.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 20%|█████████████████████▌                                                                                     | 49/243 [00:12<00:35,  5.40it/s]
 21%|██████████████████████▍                                                                                    | 51/243 [00:12<00:31,  6.06it/s]
                                                                                                                                                 
[2024-01-30 00:51:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.38.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 21%|██████████████████████▍                                                                                    | 51/243 [00:12<00:31,  6.06it/s]
                                                                                                                                                 
[2024-01-30 00:51:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.38.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 21%|██████████████████████▍                                                                                    | 51/243 [00:12<00:31,  6.06it/s]
                                                                                                                                                 
[2024-01-30 00:51:49] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.39.input_layernorm.weight", shape: (5120,), dtype: float16
+
 21%|██████████████████████▍                                                                                    | 51/243 [00:12<00:31,  6.06it/s]
                                                                                                                                                 
[2024-01-30 00:51:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.39.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 21%|██████████████████████▍                                                                                    | 51/243 [00:12<00:31,  6.06it/s]
                                                                                                                                                 
[2024-01-30 00:51:49] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.39.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 21%|██████████████████████▍                                                                                    | 51/243 [00:12<00:31,  6.06it/s]
 22%|███████████████████████▊                                                                                   | 54/243 [00:12<00:25,  7.45it/s]
                                                                                                                                                 
[2024-01-30 00:51:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.39.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 22%|███████████████████████▊                                                                                   | 54/243 [00:13<00:25,  7.45it/s]
                                                                                                                                                 
[2024-01-30 00:51:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.39.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 22%|███████████████████████▊                                                                                   | 54/243 [00:13<00:25,  7.45it/s]
 23%|████████████████████████▏                                                                                  | 55/243 [00:13<00:34,  5.39it/s]
                                                                                                                                                 
[2024-01-30 00:51:50] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.39.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 23%|████████████████████████▏                                                                                  | 55/243 [00:13<00:34,  5.39it/s]
                                                                                                                                                 
[2024-01-30 00:51:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.39.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 23%|████████████████████████▏                                                                                  | 55/243 [00:13<00:34,  5.39it/s]
                                                                                                                                                 
[2024-01-30 00:51:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.39.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 23%|████████████████████████▏                                                                                  | 55/243 [00:13<00:34,  5.39it/s]
 23%|█████████████████████████                                                                                  | 57/243 [00:13<00:30,  6.02it/s]
                                                                                                                                                 
[2024-01-30 00:51:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.39.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 23%|█████████████████████████                                                                                  | 57/243 [00:13<00:30,  6.02it/s]
                                                                                                                                                 
[2024-01-30 00:51:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.39.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 23%|█████████████████████████                                                                                  | 57/243 [00:13<00:30,  6.02it/s]
                                                                                                                                                 
[2024-01-30 00:51:50] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.norm.weight", shape: (5120,), dtype: float16
+
 23%|█████████████████████████                                                                                  | 57/243 [00:13<00:30,  6.02it/s]
                                                                                                                                                 
[2024-01-30 00:51:50] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model-00003-of-00003.bin
+
 23%|█████████████████████████                                                                                  | 57/243 [00:13<00:30,  6.02it/s]
                                                                                                                                                 
[2024-01-30 00:51:50] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model-00001-of-00003.bin
+
 23%|█████████████████████████                                                                                  | 57/243 [00:13<00:30,  6.02it/s]
                                                                                                                                                 
[2024-01-30 00:51:54] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (32000, 640), dtype: uint32
+
 23%|█████████████████████████                                                                                  | 57/243 [00:17<00:30,  6.02it/s]
                                                                                                                                                 
[2024-01-30 00:51:54] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (32000, 160), dtype: float16
+
 23%|█████████████████████████                                                                                  | 57/243 [00:17<00:30,  6.02it/s]
 25%|██████████████████████████▍                                                                                | 60/243 [00:17<01:58,  1.54it/s]
                                                                                                                                                 
[2024-01-30 00:51:54] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (5120,), dtype: float16
+
 25%|██████████████████████████▍                                                                                | 60/243 [00:17<01:58,  1.54it/s]
                                                                                                                                                 
[2024-01-30 00:51:54] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 25%|██████████████████████████▍                                                                                | 60/243 [00:17<01:58,  1.54it/s]
                                                                                                                                                 
[2024-01-30 00:51:54] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 25%|██████████████████████████▍                                                                                | 60/243 [00:17<01:58,  1.54it/s]
 26%|███████████████████████████▎                                                                               | 62/243 [00:17<01:30,  2.01it/s]
                                                                                                                                                 
[2024-01-30 00:51:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 26%|███████████████████████████▎                                                                               | 62/243 [00:18<01:30,  2.01it/s]
                                                                                                                                                 
[2024-01-30 00:51:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 26%|███████████████████████████▎                                                                               | 62/243 [00:18<01:30,  2.01it/s]
 26%|███████████████████████████▋                                                                               | 63/243 [00:18<01:28,  2.04it/s]
                                                                                                                                                 
[2024-01-30 00:51:55] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 26%|███████████████████████████▋                                                                               | 63/243 [00:18<01:28,  2.04it/s]
                                                                                                                                                 
[2024-01-30 00:51:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 26%|███████████████████████████▋                                                                               | 63/243 [00:18<01:28,  2.04it/s]
                                                                                                                                                 
[2024-01-30 00:51:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 26%|███████████████████████████▋                                                                               | 63/243 [00:18<01:28,  2.04it/s]
 27%|████████████████████████████▌                                                                              | 65/243 [00:18<01:06,  2.68it/s]
                                                                                                                                                 
[2024-01-30 00:51:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 27%|████████████████████████████▌                                                                              | 65/243 [00:18<01:06,  2.68it/s]
                                                                                                                                                 
[2024-01-30 00:51:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 27%|████████████████████████████▌                                                                              | 65/243 [00:18<01:06,  2.68it/s]
                                                                                                                                                 
[2024-01-30 00:51:55] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (5120,), dtype: float16
+
 27%|████████████████████████████▌                                                                              | 65/243 [00:18<01:06,  2.68it/s]
                                                                                                                                                 
[2024-01-30 00:51:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 27%|████████████████████████████▌                                                                              | 65/243 [00:18<01:06,  2.68it/s]
                                                                                                                                                 
[2024-01-30 00:51:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 27%|████████████████████████████▌                                                                              | 65/243 [00:18<01:06,  2.68it/s]
 28%|█████████████████████████████▉                                                                             | 68/243 [00:18<00:45,  3.89it/s]
                                                                                                                                                 
[2024-01-30 00:51:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 28%|█████████████████████████████▉                                                                             | 68/243 [00:19<00:45,  3.89it/s]
                                                                                                                                                 
[2024-01-30 00:51:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 28%|█████████████████████████████▉                                                                             | 68/243 [00:19<00:45,  3.89it/s]
 28%|██████████████████████████████▍                                                                            | 69/243 [00:19<00:50,  3.48it/s]
                                                                                                                                                 
[2024-01-30 00:51:56] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 28%|██████████████████████████████▍                                                                            | 69/243 [00:19<00:50,  3.48it/s]
                                                                                                                                                 
[2024-01-30 00:51:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 28%|██████████████████████████████▍                                                                            | 69/243 [00:19<00:50,  3.48it/s]
                                                                                                                                                 
[2024-01-30 00:51:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 28%|██████████████████████████████▍                                                                            | 69/243 [00:19<00:50,  3.48it/s]
 29%|███████████████████████████████▎                                                                           | 71/243 [00:19<00:40,  4.25it/s]
                                                                                                                                                 
[2024-01-30 00:51:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 29%|███████████████████████████████▎                                                                           | 71/243 [00:19<00:40,  4.25it/s]
                                                                                                                                                 
[2024-01-30 00:51:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 29%|███████████████████████████████▎                                                                           | 71/243 [00:19<00:40,  4.25it/s]
                                                                                                                                                 
[2024-01-30 00:51:56] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (5120,), dtype: float16
+
 29%|███████████████████████████████▎                                                                           | 71/243 [00:19<00:40,  4.25it/s]
                                                                                                                                                 
[2024-01-30 00:51:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 29%|███████████████████████████████▎                                                                           | 71/243 [00:19<00:40,  4.25it/s]
                                                                                                                                                 
[2024-01-30 00:51:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 29%|███████████████████████████████▎                                                                           | 71/243 [00:19<00:40,  4.25it/s]
 30%|████████████████████���███████████▌                                                                          | 74/243 [00:19<00:29,  5.67it/s]
                                                                                                                                                 
[2024-01-30 00:51:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 30%|████████████████████████████████▌                                                                          | 74/243 [00:20<00:29,  5.67it/s]
                                                                                                                                                 
[2024-01-30 00:51:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 30%|████████████████████████████████▌                                                                          | 74/243 [00:20<00:29,  5.67it/s]
 31%|█████████████████████████████████                                                                          | 75/243 [00:20<00:37,  4.53it/s]
                                                                                                                                                 
[2024-01-30 00:51:57] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 31%|█████████████████████████████████                                                                          | 75/243 [00:20<00:37,  4.53it/s]
                                                                                                                                                 
[2024-01-30 00:51:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 31%|█████████████████████████████████                                                                          | 75/243 [00:20<00:37,  4.53it/s]
                                                                                                                                                 
[2024-01-30 00:51:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 31%|█████████████████████████████████                                                                          | 75/243 [00:20<00:37,  4.53it/s]
 32%|█████████████████████████████████▉                                                                         | 77/243 [00:20<00:31,  5.27it/s]
                                                                                                                                                 
[2024-01-30 00:51:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 32%|█████████████████████████████████▉                                                                         | 77/243 [00:20<00:31,  5.27it/s]
                                                                                                                                                 
[2024-01-30 00:51:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 32%|█████████████████████████████████▉                                                                         | 77/243 [00:20<00:31,  5.27it/s]
                                                                                                                                                 
[2024-01-30 00:51:57] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (5120,), dtype: float16
+
 32%|█████████████████████████████████▉                                                                         | 77/243 [00:20<00:31,  5.27it/s]
                                                                                                                                                 
[2024-01-30 00:51:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 32%|███████���█████████████████████████▉                                                                         | 77/243 [00:20<00:31,  5.27it/s]
                                                                                                                                                 
[2024-01-30 00:51:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 32%|█████████████████████████████████▉                                                                         | 77/243 [00:20<00:31,  5.27it/s]
 33%|███████████████████████████████████▏                                                                       | 80/243 [00:20<00:24,  6.69it/s]
                                                                                                                                                 
[2024-01-30 00:51:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 33%|███████████████████████████████████▏                                                                       | 80/243 [00:21<00:24,  6.69it/s]
                                                                                                                                                 
[2024-01-30 00:51:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 33%|███████████████████████████████████▏                                                                       | 80/243 [00:21<00:24,  6.69it/s]
 33%|███████████████████████████████████▋                                                                       | 81/243 [00:21<00:32,  5.05it/s]
                                                                                                                                                 
[2024-01-30 00:51:58] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 33%|███████████████████████████████████▋                                                                       | 81/243 [00:21<00:32,  5.05it/s]
                                                                                                                                                 
[2024-01-30 00:51:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 33%|███████████████████████████████████▋                                                                       | 81/243 [00:21<00:32,  5.05it/s]
                                                                                                                                                 
[2024-01-30 00:51:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 33%|███████████████████████████████████▋                                                                       | 81/243 [00:21<00:32,  5.05it/s]
 34%|████████████████████████████████████▌                                                                      | 83/243 [00:21<00:28,  5.71it/s]
                                                                                                                                                 
[2024-01-30 00:51:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 34%|████████████████████████████████████▌                                                                      | 83/243 [00:21<00:28,  5.71it/s]
                                                                                                                                                 
[2024-01-30 00:51:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 34%|████████████████████████████████████▌                                                                      | 83/243 [00:21<00:28,  5.71it/s]
                                                                                                                                                 
[2024-01-30 00:51:58] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (5120,), dtype: float16
+
 34%|████████████████████████████████████▌                                                                      | 83/243 [00:21<00:28,  5.71it/s]
                                                                                                                                                 
[2024-01-30 00:51:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 34%|████████████████████████████████████▌                                                                      | 83/243 [00:21<00:28,  5.71it/s]
                                                                                                                                                 
[2024-01-30 00:51:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 34%|████████████████████████████████████▌                                                                      | 83/243 [00:21<00:28,  5.71it/s]
 35%|█████████████████████████████████████▊                                                                     | 86/243 [00:21<00:22,  7.11it/s]
                                                                                                                                                 
[2024-01-30 00:51:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 35%|█████████████████████████████████████▊                                                                     | 86/243 [00:22<00:22,  7.11it/s]
                                                                                                                                                 
[2024-01-30 00:51:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 35%|█████████████████████████████████████▊                                                                     | 86/243 [00:22<00:22,  7.11it/s]
 36%|██████████████████████████████████████▎                                                                    | 87/243 [00:22<00:29,  5.26it/s]
                                                                                                                                                 
[2024-01-30 00:51:59] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 36%|██████████████████████████████████████▎                                                                    | 87/243 [00:22<00:29,  5.26it/s]
                                                                                                                                                 
[2024-01-30 00:51:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 36%|██████████████████████████████████████▎                                                                    | 87/243 [00:22<00:29,  5.26it/s]
                                                                                                                                                 
[2024-01-30 00:51:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 36%|██████████████████████████████████████▎                                                                    | 87/243 [00:22<00:29,  5.26it/s]
 37%|███████████████████████████████████████▏                                                                   | 89/243 [00:22<00:25,  5.93it/s]
                                                                                                                                                 
[2024-01-30 00:51:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 37%|███████████████████████████████████████▏                                                                   | 89/243 [00:22<00:25,  5.93it/s]
                                                                                                                                                 
[2024-01-30 00:51:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 37%|███████████████████████████████████████▏                                                                   | 89/243 [00:22<00:25,  5.93it/s]
                                                                                                                                                 
[2024-01-30 00:51:59] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (5120,), dtype: float16
+
 37%|███████████████████████████████████████▏                                                                   | 89/243 [00:22<00:25,  5.93it/s]
                                                                                                                                                 
[2024-01-30 00:51:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 37%|███████████████████████████████████████▏                                                                   | 89/243 [00:22<00:25,  5.93it/s]
                                                                                                                                                 
[2024-01-30 00:51:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 37%|███████████████████████████████████████▏                                                                   | 89/243 [00:22<00:25,  5.93it/s]
 38%|████████████████████████████████████████▌                                                                  | 92/243 [00:22<00:21,  7.17it/s]
                                                                                                                                                 
[2024-01-30 00:52:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 38%|████████████████████████████████████████▌                                                                  | 92/243 [00:23<00:21,  7.17it/s]
                                                                                                                                                 
[2024-01-30 00:52:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 38%|████████████████████████████████████████▌                                                                  | 92/243 [00:23<00:21,  7.17it/s]
 38%|████████████████████████████████████████▉                                                                  | 93/243 [00:23<00:28,  5.21it/s]
                                                                                                                                                 
[2024-01-30 00:52:00] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 38%|████████████████████████████████████████▉                                                                  | 93/243 [00:23<00:28,  5.21it/s]
                                                                                                                                                 
[2024-01-30 00:52:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 38%|████████████████████████████████████████▉                                                                  | 93/243 [00:23<00:28,  5.21it/s]
                                                                                                                                                 
[2024-01-30 00:52:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 38%|████████████████████████████████████████▉                                                                  | 93/243 [00:23<00:28,  5.21it/s]
 39%|█████████████████████████████████████████▊                                                                 | 95/243 [00:23<00:25,  5.90it/s]
                                                                                                                                                 
[2024-01-30 00:52:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 39%|█████████████████████████████████████████▊                                                                 | 95/243 [00:23<00:25,  5.90it/s]
                                                                                                                                                 
[2024-01-30 00:52:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 39%|█████████████████████████████████████████▊                                                                 | 95/243 [00:23<00:25,  5.90it/s]
                                                                                                                                                 
[2024-01-30 00:52:00] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (5120,), dtype: float16
+
 39%|█████████████████████████████████████████▊                                                                 | 95/243 [00:23<00:25,  5.90it/s]
                                                                                                                                                 
[2024-01-30 00:52:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 39%|█████████████████████████████████████████▊                                                                 | 95/243 [00:23<00:25,  5.90it/s]
                                                                                                                                                 
[2024-01-30 00:52:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 39%|█████████████████████████████████████████▊                                                                 | 95/243 [00:23<00:25,  5.90it/s]
 40%|███████████████████████████████████████████▏                                                               | 98/243 [00:23<00:20,  7.16it/s]
                                                                                                                                                 
[2024-01-30 00:52:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 40%|███████████████████████████████████████████▏                                                               | 98/243 [00:24<00:20,  7.16it/s]
                                                                                                                                                 
[2024-01-30 00:52:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 40%|███████████████████████████████████████████▏                                                               | 98/243 [00:24<00:20,  7.16it/s]
 41%|███████████████████████████████████████████▌                                                               | 99/243 [00:24<00:28,  5.10it/s]
                                                                                                                                                 
[2024-01-30 00:52:01] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 41%|███████████████████████████████████████████▌                                                               | 99/243 [00:24<00:28,  5.10it/s]
                                                                                                                                                 
[2024-01-30 00:52:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 41%|███████████████████████████████████████████▌                                                               | 99/243 [00:24<00:28,  5.10it/s]
                                                                                                                                                 
[2024-01-30 00:52:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 41%|███████████████████████████████████████████▌                                                               | 99/243 [00:24<00:28,  5.10it/s]
 42%|████████████████████████████████████████████                                                              | 101/243 [00:24<00:25,  5.66it/s]
                                                                                                                                                 
[2024-01-30 00:52:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 42%|████████████████████████████████████████████                                                              | 101/243 [00:24<00:25,  5.66it/s]
                                                                                                                                                 
[2024-01-30 00:52:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 42%|████████████████████████████████████████████                                                              | 101/243 [00:24<00:25,  5.66it/s]
                                                                                                                                                 
[2024-01-30 00:52:01] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model-00002-of-00003.bin
+
 42%|████████████████████████████████████████████                                                              | 101/243 [00:24<00:25,  5.66it/s]
                                                                                                                                                 
[2024-01-30 00:52:13] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 42%|████████████████████████████████████████████                                                              | 101/243 [00:36<00:25,  5.66it/s]
                                                                                                                                                 
[2024-01-30 00:52:13] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 42%|████████████████████████████████████████████                                                              | 101/243 [00:36<00:25,  5.66it/s]
 42%|████████████████████████████████████████████▉                                                             | 103/243 [00:36<04:42,  2.02s/it]
                                                                                                                                                 
[2024-01-30 00:52:13] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (5120,), dtype: float16
+
 42%|█████���██████████████████████████████████████▉                                                             | 103/243 [00:36<04:42,  2.02s/it]
                                                                                                                                                 
[2024-01-30 00:52:13] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 42%|████████████████████████████████████████████▉                                                             | 103/243 [00:36<04:42,  2.02s/it]
                                                                                                                                                 
[2024-01-30 00:52:13] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 42%|████████████████████████████████████████████▉                                                             | 103/243 [00:36<04:42,  2.02s/it]
 43%|█████████████████████████████████████████████▊                                                            | 105/243 [00:36<03:18,  1.44s/it]
                                                                                                                                                 
[2024-01-30 00:52:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 43%|█████████████████████████████████████████████▊                                                            | 105/243 [00:37<03:18,  1.44s/it]
                                                                                                                                                 
[2024-01-30 00:52:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 43%|█████████████████████████████████████████████▊                                                            | 105/243 [00:37<03:18,  1.44s/it]
 44%|██████████████████████████████████████████████▏                                                           | 106/243 [00:37<02:53,  1.26s/it]
                                                                                                                                                 
[2024-01-30 00:52:14] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 44%|██████████████████████████████████████████████▏                                                           | 106/243 [00:37<02:53,  1.26s/it]
                                                                                                                                                 
[2024-01-30 00:52:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 44%|██████████████████████████████████████████████▏                                                           | 106/243 [00:37<02:53,  1.26s/it]
                                                                                                                                                 
[2024-01-30 00:52:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 44%|██████████████████████████████████████████████▏                                                           | 106/243 [00:37<02:53,  1.26s/it]
 44%|███████████████████████████████████████████████                                                           | 108/243 [00:37<01:58,  1.14it/s]
                                                                                                                                                 
[2024-01-30 00:52:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 44%|█████���█████████████████████████████████████████                                                           | 108/243 [00:37<01:58,  1.14it/s]
                                                                                                                                                 
[2024-01-30 00:52:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 44%|███████████████████████████████████████████████                                                           | 108/243 [00:37<01:58,  1.14it/s]
                                                                                                                                                 
[2024-01-30 00:52:14] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (5120,), dtype: float16
+
 44%|███████████████████████████████████████████████                                                           | 108/243 [00:37<01:58,  1.14it/s]
                                                                                                                                                 
[2024-01-30 00:52:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 44%|███████████████████████████████████████████████                                                           | 108/243 [00:37<01:58,  1.14it/s]
                                                                                                                                                 
[2024-01-30 00:52:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 44%|███████████████████████████████████████████████                                                           | 108/243 [00:37<01:58,  1.14it/s]
 46%|████████████████████████████████████████████████▍                                                         | 111/243 [00:37<01:12,  1.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:15] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 46%|████████████████████████████████████████████████▍                                                         | 111/243 [00:38<01:12,  1.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:15] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 46%|████████████████████████████████████████████████▍                                                         | 111/243 [00:38<01:12,  1.82it/s]
 46%|████████████████████████████████████████████████▊                                                         | 112/243 [00:38<01:10,  1.85it/s]
                                                                                                                                                 
[2024-01-30 00:52:15] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 46%|████████████████████████████████████████████████▊                                                         | 112/243 [00:38<01:10,  1.85it/s]
                                                                                                                                                 
[2024-01-30 00:52:15] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 46%|████████████████████████████████████████████████▊                                                         | 112/243 [00:38<01:10,  1.85it/s]
                                                                                                                                                 
[2024-01-30 00:52:15] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 46%|████████████████████████████████████████████████▊                                                         | 112/243 [00:38<01:10,  1.85it/s]
 47%|█████████████████████████████████████████████████▋                                                        | 114/243 [00:38<00:52,  2.47it/s]
                                                                                                                                                 
[2024-01-30 00:52:15] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 47%|█████████████████████████████████████████████████▋                                                        | 114/243 [00:38<00:52,  2.47it/s]
                                                                                                                                                 
[2024-01-30 00:52:15] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 47%|█████████████████████████████████████████████████▋                                                        | 114/243 [00:38<00:52,  2.47it/s]
                                                                                                                                                 
[2024-01-30 00:52:15] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (5120,), dtype: float16
+
 47%|█████████████████████████████████████████████████▋                                                        | 114/243 [00:38<00:52,  2.47it/s]
                                                                                                                                                 
[2024-01-30 00:52:15] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 47%|█████████████████████████████████████████████████▋                                                        | 114/243 [00:38<00:52,  2.47it/s]
                                                                                                                                                 
[2024-01-30 00:52:15] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 47%|█████████████████████████████████████████████████▋                                                        | 114/243 [00:38<00:52,  2.47it/s]
 48%|███████████████████████████████████████████████████                                                       | 117/243 [00:38<00:34,  3.61it/s]
                                                                                                                                                 
[2024-01-30 00:52:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 48%|███████████████████████████████████████████████████                                                       | 117/243 [00:39<00:34,  3.61it/s]
                                                                                                                                                 
[2024-01-30 00:52:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 48%|███████████████████████████████████████████████████                                                       | 117/243 [00:39<00:34,  3.61it/s]
 49%|█████████████████████████████████████████████████��█▍                                                      | 118/243 [00:39<00:38,  3.26it/s]
                                                                                                                                                 
[2024-01-30 00:52:16] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 49%|███████████████████████████████████████████████████▍                                                      | 118/243 [00:39<00:38,  3.26it/s]
                                                                                                                                                 
[2024-01-30 00:52:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 49%|███████████████████████████████████████████████████▍                                                      | 118/243 [00:39<00:38,  3.26it/s]
                                                                                                                                                 
[2024-01-30 00:52:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 49%|███████████████████████████████████████████████████▍                                                      | 118/243 [00:39<00:38,  3.26it/s]
 49%|████████████████████████████████████████████████████▎                                                     | 120/243 [00:39<00:30,  4.01it/s]
                                                                                                                                                 
[2024-01-30 00:52:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 49%|████████████████████████████████████████████████████▎                                                     | 120/243 [00:39<00:30,  4.01it/s]
                                                                                                                                                 
[2024-01-30 00:52:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 49%|████████████████████████████████████████████████████▎                                                     | 120/243 [00:39<00:30,  4.01it/s]
                                                                                                                                                 
[2024-01-30 00:52:16] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (5120,), dtype: float16
+
 49%|████████████████████████████████████████████████████▎                                                     | 120/243 [00:39<00:30,  4.01it/s]
                                                                                                                                                 
[2024-01-30 00:52:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 49%|████████████████████████████████████████████████████▎                                                     | 120/243 [00:39<00:30,  4.01it/s]
                                                                                                                                                 
[2024-01-30 00:52:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 49%|████████████████████████████████████████████████████▎                                                     | 120/243 [00:39<00:30,  4.01it/s]
 51%|█████████████████████████████████████████████████████▋                                                    | 123/243 [00:39<00:22,  5.41it/s]
                                                                                                                                                 
[2024-01-30 00:52:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 51%|█████████████████████████████████████████████████████▋                                                    | 123/243 [00:40<00:22,  5.41it/s]
                                                                                                                                                 
[2024-01-30 00:52:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 51%|█████████████████████████████████████████████████████▋                                                    | 123/243 [00:40<00:22,  5.41it/s]
 51%|██████████████████████████████████████████████████████                                                    | 124/243 [00:40<00:27,  4.37it/s]
                                                                                                                                                 
[2024-01-30 00:52:17] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 51%|██████████████████████████████████████████████████████                                                    | 124/243 [00:40<00:27,  4.37it/s]
                                                                                                                                                 
[2024-01-30 00:52:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 51%|██████████████████████████████████████████████████████                                                    | 124/243 [00:40<00:27,  4.37it/s]
                                                                                                                                                 
[2024-01-30 00:52:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 51%|██████████████████████████████████████████████████████                                                    | 124/243 [00:40<00:27,  4.37it/s]
 52%|██████████████████████████████████████████████████████▉                                                   | 126/243 [00:40<00:22,  5.09it/s]
                                                                                                                                                 
[2024-01-30 00:52:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 52%|██████████████████████████████████████████████████████▉                                                   | 126/243 [00:40<00:22,  5.09it/s]
                                                                                                                                                 
[2024-01-30 00:52:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 52%|██████████████████████████████████████████████████████▉                                                   | 126/243 [00:40<00:22,  5.09it/s]
                                                                                                                                                 
[2024-01-30 00:52:17] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (5120,), dtype: float16
+
 52%|██████████████████████████████████████████████████████▉                                                   | 126/243 [00:40<00:22,  5.09it/s]
                                                                                                                                                 
[2024-01-30 00:52:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 52%|██████████████████████████████████████████████████████▉                                                   | 126/243 [00:40<00:22,  5.09it/s]
                                                                                                                                                 
[2024-01-30 00:52:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 52%|██████████████████████████████████████████████████████▉                                                   | 126/243 [00:40<00:22,  5.09it/s]
 53%|████████████████████████████████████████████████████████▎                                                 | 129/243 [00:40<00:17,  6.49it/s]
                                                                                                                                                 
[2024-01-30 00:52:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 53%|████████████████████████████████████████████████████████▎                                                 | 129/243 [00:41<00:17,  6.49it/s]
                                                                                                                                                 
[2024-01-30 00:52:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 53%|████████████████████████████████████████████████████████▎                                                 | 129/243 [00:41<00:17,  6.49it/s]
 53%|████████████████████████████████████████████████████████▋                                                 | 130/243 [00:41<00:22,  4.92it/s]
                                                                                                                                                 
[2024-01-30 00:52:18] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 53%|████████████████████████████████████████████████████████▋                                                 | 130/243 [00:41<00:22,  4.92it/s]
                                                                                                                                                 
[2024-01-30 00:52:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 53%|████████████████████████████████████████████████████████▋                                                 | 130/243 [00:41<00:22,  4.92it/s]
                                                                                                                                                 
[2024-01-30 00:52:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 53%|████████████████████████████████████████████████████████▋                                                 | 130/243 [00:41<00:22,  4.92it/s]
 54%|█████████████████████████████████████████████████████████▌                                                | 132/243 [00:41<00:19,  5.61it/s]
                                                                                                                                                 
[2024-01-30 00:52:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 54%|█████████████████████████████████████████████████████████▌                                                | 132/243 [00:41<00:19,  5.61it/s]
                                                                                                                                                 
[2024-01-30 00:52:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 54%|█████████████████████████████████████████████████████████▌                                                | 132/243 [00:41<00:19,  5.61it/s]
                                                                                                                                                 
[2024-01-30 00:52:18] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (5120,), dtype: float16
+
 54%|█████████████████████████████████████████████████████████▌                                                | 132/243 [00:41<00:19,  5.61it/s]
                                                                                                                                                 
[2024-01-30 00:52:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 54%|█████████████████████████████████████████████████████████▌                                                | 132/243 [00:41<00:19,  5.61it/s]
                                                                                                                                                 
[2024-01-30 00:52:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 54%|█████████████████████████████████████████████████████████▌                                                | 132/243 [00:41<00:19,  5.61it/s]
 56%|██████████████████████████████████████████████████████████▉                                               | 135/243 [00:41<00:15,  6.99it/s]
                                                                                                                                                 
[2024-01-30 00:52:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 56%|██████████████████████████████████████████████████████████▉                                               | 135/243 [00:42<00:15,  6.99it/s]
                                                                                                                                                 
[2024-01-30 00:52:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 56%|██████████████████████████████████████████████████████████▉                                               | 135/243 [00:42<00:15,  6.99it/s]
 56%|███████████████████████████████████████████████████████████▎                                              | 136/243 [00:42<00:20,  5.16it/s]
                                                                                                                                                 
[2024-01-30 00:52:19] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 56%|███████████████████████████████████████████████████████████▎                                              | 136/243 [00:42<00:20,  5.16it/s]
                                                                                                                                                 
[2024-01-30 00:52:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 56%|█████████████████████████████████��█████████████████████████▎                                              | 136/243 [00:42<00:20,  5.16it/s]
                                                                                                                                                 
[2024-01-30 00:52:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 56%|███████████████████████████████████████████████████████████▎                                              | 136/243 [00:42<00:20,  5.16it/s]
 57%|████████████████████████████████████████████████████████████▏                                             | 138/243 [00:42<00:18,  5.83it/s]
                                                                                                                                                 
[2024-01-30 00:52:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 57%|████████████████████████████████████████████████████████████▏                                             | 138/243 [00:42<00:18,  5.83it/s]
                                                                                                                                                 
[2024-01-30 00:52:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 57%|████████████████████████████████████████████████████████████▏                                             | 138/243 [00:42<00:18,  5.83it/s]
                                                                                                                                                 
[2024-01-30 00:52:19] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (5120,), dtype: float16
+
 57%|████████████████████████████████████████████████████████████▏                                             | 138/243 [00:42<00:18,  5.83it/s]
                                                                                                                                                 
[2024-01-30 00:52:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 57%|████████████████████████████████████████████████████████████▏                                             | 138/243 [00:42<00:18,  5.83it/s]
                                                                                                                                                 
[2024-01-30 00:52:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 57%|████████████████████████████████████████████████████████████▏                                             | 138/243 [00:42<00:18,  5.83it/s]
 58%|█████████████████████████████████████████████████████████████▌                                            | 141/243 [00:42<00:14,  7.19it/s]
                                                                                                                                                 
[2024-01-30 00:52:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 58%|█████████████████████████████████████████████████████████████▌                                            | 141/243 [00:43<00:14,  7.19it/s]
                                                                                                                                                 
[2024-01-30 00:52:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 58%|██████████████████���██████████████████████████████████████████▌                                            | 141/243 [00:43<00:14,  7.19it/s]
 58%|█████████████████████████████████████████████████████████████▉                                            | 142/243 [00:43<00:19,  5.25it/s]
                                                                                                                                                 
[2024-01-30 00:52:20] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 58%|█████████████████████████████████████████████████████████████▉                                            | 142/243 [00:43<00:19,  5.25it/s]
                                                                                                                                                 
[2024-01-30 00:52:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 58%|█████████████████████████████████████████████████████████████▉                                            | 142/243 [00:43<00:19,  5.25it/s]
                                                                                                                                                 
[2024-01-30 00:52:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 58%|█████████████████████████████████████████████████████████████▉                                            | 142/243 [00:43<00:19,  5.25it/s]
 59%|██████████████████████████████████████████████████████████████▊                                           | 144/243 [00:43<00:16,  5.90it/s]
                                                                                                                                                 
[2024-01-30 00:52:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 59%|██████████████████████████████████████████████████████████████▊                                           | 144/243 [00:43<00:16,  5.90it/s]
                                                                                                                                                 
[2024-01-30 00:52:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 59%|██████████████████████████████████████████████████████████████▊                                           | 144/243 [00:43<00:16,  5.90it/s]
                                                                                                                                                 
[2024-01-30 00:52:20] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (5120,), dtype: float16
+
 59%|██████████████████████████████████████████████████████████████▊                                           | 144/243 [00:43<00:16,  5.90it/s]
                                                                                                                                                 
[2024-01-30 00:52:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 59%|██████████████████████████████████████████████████████████████▊                                           | 144/243 [00:43<00:16,  5.90it/s]
                                                                                                                                                 
[2024-01-30 00:52:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 59%|██████████████████████████████████████████████████████████████▊                                           | 144/243 [00:43<00:16,  5.90it/s]
 60%|████████████████████████████████████████████████████████████████                                          | 147/243 [00:43<00:13,  7.11it/s]
                                                                                                                                                 
[2024-01-30 00:52:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 60%|████████████████████████████████████████████████████████████████                                          | 147/243 [00:44<00:13,  7.11it/s]
                                                                                                                                                 
[2024-01-30 00:52:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 60%|████████████████████████████████████████████████████████████████                                          | 147/243 [00:44<00:13,  7.11it/s]
 61%|████████████████████████████████████████████████████████████████▌                                         | 148/243 [00:44<00:18,  5.13it/s]
                                                                                                                                                 
[2024-01-30 00:52:21] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 61%|████████████████████████████████████████████████████████████████▌                                         | 148/243 [00:44<00:18,  5.13it/s]
                                                                                                                                                 
[2024-01-30 00:52:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 61%|████████████████████████████████████████████████████████████████▌                                         | 148/243 [00:44<00:18,  5.13it/s]
                                                                                                                                                 
[2024-01-30 00:52:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 61%|████████████████████████████████████████████████████████████████▌                                         | 148/243 [00:44<00:18,  5.13it/s]
 62%|█████████████████████████████████████████████████████████████████▍                                        | 150/243 [00:44<00:16,  5.68it/s]
                                                                                                                                                 
[2024-01-30 00:52:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 62%|█████████████████████████████████████████████████████████████████▍                                        | 150/243 [00:44<00:16,  5.68it/s]
                                                                                                                                                 
[2024-01-30 00:52:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 62%|████████████████████████████████████████████████���████████████████▍                                        | 150/243 [00:44<00:16,  5.68it/s]
                                                                                                                                                 
[2024-01-30 00:52:21] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (5120,), dtype: float16
+
 62%|█████████████████████████████████████████████████████████████████▍                                        | 150/243 [00:44<00:16,  5.68it/s]
                                                                                                                                                 
[2024-01-30 00:52:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 62%|█████████████████████████████████████████████████████████████████▍                                        | 150/243 [00:44<00:16,  5.68it/s]
                                                                                                                                                 
[2024-01-30 00:52:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 62%|█████████████████████████████████████████████████████████████████▍                                        | 150/243 [00:44<00:16,  5.68it/s]
 63%|██████████████████████████████████████████████████████████████████▋                                       | 153/243 [00:44<00:13,  6.64it/s]
                                                                                                                                                 
[2024-01-30 00:52:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 63%|██████████████████████████████████████████████████████████████████▋                                       | 153/243 [00:45<00:13,  6.64it/s]
                                                                                                                                                 
[2024-01-30 00:52:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 63%|██████████████████████████████████████████████████████████████████▋                                       | 153/243 [00:45<00:13,  6.64it/s]
 63%|███████████████████████████████████████████████████████████████████▏                                      | 154/243 [00:45<00:19,  4.56it/s]
                                                                                                                                                 
[2024-01-30 00:52:22] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 63%|███████████████████████████████████████████████████████████████████▏                                      | 154/243 [00:45<00:19,  4.56it/s]
                                                                                                                                                 
[2024-01-30 00:52:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 63%|███████████████████████████████████████████████████████████████████▏                                      | 154/243 [00:45<00:19,  4.56it/s]
                                                                                                                                                 
[2024-01-30 00:52:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 63%|███████████████████████████████████████████████████████████████████▏                                      | 154/243 [00:45<00:19,  4.56it/s]
 64%|████████████████████████████████████████████████████████████████████                                      | 156/243 [00:45<00:14,  5.97it/s]
                                                                                                                                                 
[2024-01-30 00:52:22] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (5120,), dtype: float16
+
 64%|████████████████████████████████████████████████████████████████████                                      | 156/243 [00:45<00:14,  5.97it/s]
                                                                                                                                                 
[2024-01-30 00:52:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 64%|████████████████████████████████████████████████████████████████████                                      | 156/243 [00:45<00:14,  5.97it/s]
                                                                                                                                                 
[2024-01-30 00:52:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 64%|████████████████████████████████████████████████████████████████████                                      | 156/243 [00:45<00:14,  5.97it/s]
 65%|████████████████████████████████████████████████████████████████████▉                                     | 158/243 [00:45<00:13,  6.41it/s]
                                                                                                                                                 
[2024-01-30 00:52:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 65%|████████████████████████████████████████████████████████████████████▉                                     | 158/243 [00:46<00:13,  6.41it/s]
                                                                                                                                                 
[2024-01-30 00:52:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 65%|████████████████████████████████████████████████████████████████████▉                                     | 158/243 [00:46<00:13,  6.41it/s]
 65%|█████████████████████████████████████████████████████████████████████▎                                    | 159/243 [00:46<00:19,  4.23it/s]
                                                                                                                                                 
[2024-01-30 00:52:23] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 65%|█████████████████████████████████████████████████████████████████████▎                                    | 159/243 [00:46<00:19,  4.23it/s]
                                                                                                                                                 
[2024-01-30 00:52:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 65%|█████████████████████████████████████████████████████████████████████▎                                    | 159/243 [00:46<00:19,  4.23it/s]
                                                                                                                                                 
[2024-01-30 00:52:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 65%|█████████████████████████████████████████████████████████████████████▎                                    | 159/243 [00:46<00:19,  4.23it/s]
 66%|██████████████████████████████████████████████████████████████████████▏                                   | 161/243 [00:46<00:17,  4.74it/s]
                                                                                                                                                 
[2024-01-30 00:52:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 66%|██████████████████████████████████████████████████████████████████████▏                                   | 161/243 [00:46<00:17,  4.74it/s]
                                                                                                                                                 
[2024-01-30 00:52:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 66%|██████████████████████████████████████████████████████████████████████▏                                   | 161/243 [00:46<00:17,  4.74it/s]
 67%|██████████████████████████████████████████████████████████████████████▋                                   | 162/243 [00:46<00:15,  5.25it/s]
                                                                                                                                                 
[2024-01-30 00:52:23] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (5120,), dtype: float16
+
 67%|██████████████████████████████████████████████████████████████████████▋                                   | 162/243 [00:46<00:15,  5.25it/s]
                                                                                                                                                 
[2024-01-30 00:52:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 67%|██████████████████████████████████████████████████████████████████████▋                                   | 162/243 [00:47<00:15,  5.25it/s]
                                                                                                                                                 
[2024-01-30 00:52:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 67%|██████████████████████████████████████████████████████████████████████▋                                   | 162/243 [00:47<00:15,  5.25it/s]
 67%|███████████████████████████████████████████████████████████████████████▌                                  | 164/243 [00:47<00:13,  5.93it/s]
                                                                                                                                                 
[2024-01-30 00:52:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 67%|██████████████████████████████████████████���████████████████████████████▌                                  | 164/243 [00:47<00:13,  5.93it/s]
                                                                                                                                                 
[2024-01-30 00:52:24] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 67%|███████████████████████████████████████████████████████████████████████▌                                  | 164/243 [00:47<00:13,  5.93it/s]
 68%|███████████████████████████████████████████████████████████████████████▉                                  | 165/243 [00:47<00:19,  3.91it/s]
                                                                                                                                                 
[2024-01-30 00:52:24] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 68%|███████████████████████████████████████████████████████████████████████▉                                  | 165/243 [00:47<00:19,  3.91it/s]
                                                                                                                                                 
[2024-01-30 00:52:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 68%|███████████████████████████████████████████████████████████████████████▉                                  | 165/243 [00:48<00:19,  3.91it/s]
                                                                                                                                                 
[2024-01-30 00:52:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 68%|███████████████████████████████████████████████████████████████████████▉                                  | 165/243 [00:48<00:19,  3.91it/s]
 69%|████████████████████████████████████████████████████████████████████████▊                                 | 167/243 [00:48<00:16,  4.52it/s]
                                                                                                                                                 
[2024-01-30 00:52:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 69%|████████████████████████████████████████████████████████████████████████▊                                 | 167/243 [00:48<00:16,  4.52it/s]
                                                                                                                                                 
[2024-01-30 00:52:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 69%|████████████████████████████████████████████████████████████████████████▊                                 | 167/243 [00:48<00:16,  4.52it/s]
 69%|█████████████████████████████████████████████████████████████████████████▎                                | 168/243 [00:48<00:14,  5.08it/s]
                                                                                                                                                 
[2024-01-30 00:52:25] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (5120,), dtype: float16
+
 69%|█████████████████████████████████████████████████████████████████████████▎                                | 168/243 [00:48<00:14,  5.08it/s]
                                                                                                                                                 
[2024-01-30 00:52:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 69%|█████████████████████████████████████████████████████████████████████████▎                                | 168/243 [00:48<00:14,  5.08it/s]
                                                                                                                                                 
[2024-01-30 00:52:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 69%|█████████████████████████████████████████████████████████████████████████▎                                | 168/243 [00:48<00:14,  5.08it/s]
 70%|██████████████████████████████████████████████████████████████████████████▏                               | 170/243 [00:48<00:12,  5.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 70%|██████████████████████████████████████████████████████████████████████████▏                               | 170/243 [00:48<00:12,  5.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 70%|██████████████████████████████████████████████████████████████████████████▏                               | 170/243 [00:48<00:12,  5.82it/s]
 70%|██████████████████████████████████████████████████████████████████████████▌                               | 171/243 [00:48<00:18,  3.83it/s]
                                                                                                                                                 
[2024-01-30 00:52:26] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 70%|██████████████████████████████████████████████████████████████████████████▌                               | 171/243 [00:48<00:18,  3.83it/s]
                                                                                                                                                 
[2024-01-30 00:52:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 70%|██████████████████████████████████████████████████████████████████████████▌                               | 171/243 [00:49<00:18,  3.83it/s]
                                                                                                                                                 
[2024-01-30 00:52:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 70%|██████████████████████████████████████████████████████████████████████████▌                               | 171/243 [00:49<00:18,  3.83it/s]
 71%|█████████████████████████████████████��█████████████████████████████████████▍                              | 173/243 [00:49<00:15,  4.46it/s]
                                                                                                                                                 
[2024-01-30 00:52:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 71%|███████████████████████████████████████████████████████████████████████████▍                              | 173/243 [00:49<00:15,  4.46it/s]
                                                                                                                                                 
[2024-01-30 00:52:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 71%|███████████████████████████████████████████████████████████████████████████▍                              | 173/243 [00:49<00:15,  4.46it/s]
 72%|███████████████████████████████████████████████████████████████████████████▉                              | 174/243 [00:49<00:13,  5.03it/s]
                                                                                                                                                 
[2024-01-30 00:52:26] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (5120,), dtype: float16
+
 72%|███████████████████████████████████████████████████████████████████████████▉                              | 174/243 [00:49<00:13,  5.03it/s]
                                                                                                                                                 
[2024-01-30 00:52:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 72%|███████████████████████████████████████████████████████████████████████████▉                              | 174/243 [00:49<00:13,  5.03it/s]
                                                                                                                                                 
[2024-01-30 00:52:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 72%|███████████████████████████████████████████████████████████████████████████▉                              | 174/243 [00:49<00:13,  5.03it/s]
 72%|████████████████████████████████████████████████████████████████████████████▊                             | 176/243 [00:49<00:11,  5.80it/s]
                                                                                                                                                 
[2024-01-30 00:52:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 72%|████████████████████████████████████████████████████████████████████████████▊                             | 176/243 [00:50<00:11,  5.80it/s]
                                                                                                                                                 
[2024-01-30 00:52:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 72%|████████████████████████████████████████████████████████████████████████████▊                             | 176/243 [00:50<00:11,  5.80it/s]
 73%|██████████████████████��██████████████████████████████████████████████████████▏                            | 177/243 [00:50<00:17,  3.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:27] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 73%|█████████████████████████████████████████████████████████████████████████████▏                            | 177/243 [00:50<00:17,  3.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 73%|█████████████████████████████████████████████████████████████████████████████▏                            | 177/243 [00:50<00:17,  3.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 73%|█████████████████████████████████████████████████████████████████████████████▏                            | 177/243 [00:50<00:17,  3.81it/s]
 74%|██████████████████████████████████████████████████████████████████████████████                            | 179/243 [00:50<00:14,  4.45it/s]
                                                                                                                                                 
[2024-01-30 00:52:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 74%|██████████████████████████████████████████████████████████████████████████████                            | 179/243 [00:50<00:14,  4.45it/s]
                                                                                                                                                 
[2024-01-30 00:52:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 74%|██████████████████████████████████████████████████████████████████████████████                            | 179/243 [00:50<00:14,  4.45it/s]
 74%|██████████████████████████████████████████████████████████████████████████████▌                           | 180/243 [00:50<00:12,  5.02it/s]
                                                                                                                                                 
[2024-01-30 00:52:27] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (5120,), dtype: float16
+
 74%|██████████████████████████████████████████████████████████████████████████████▌                           | 180/243 [00:50<00:12,  5.02it/s]
                                                                                                                                                 
[2024-01-30 00:52:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 74%|██████████████████████████████████████████████████████████████████████████████▌                           | 180/243 [00:50<00:12,  5.02it/s]
                                                                                                                                                 
[2024-01-30 00:52:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 74%|██████████████████████████████████████████████████████████████████████████████▌                           | 180/243 [00:50<00:12,  5.02it/s]
 75%|███████████████████████████████████████████████████████████████████████████████▍                          | 182/243 [00:50<00:10,  5.80it/s]
                                                                                                                                                 
[2024-01-30 00:52:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 75%|███████████████████████████████████████████████████████████████████████████████▍                          | 182/243 [00:51<00:10,  5.80it/s]
                                                                                                                                                 
[2024-01-30 00:52:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 75%|███████████████████████████████████████████████████████████████████████████████▍                          | 182/243 [00:51<00:10,  5.80it/s]
 75%|███████████████████████████████████████████████████████████████████████████████▊                          | 183/243 [00:51<00:15,  3.80it/s]
                                                                                                                                                 
[2024-01-30 00:52:28] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 75%|███████████████████████████████████████████████████████████████████████████████▊                          | 183/243 [00:51<00:15,  3.80it/s]
                                                                                                                                                 
[2024-01-30 00:52:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 75%|███████████████████████████████████████████████████████████████████████████████▊                          | 183/243 [00:51<00:15,  3.80it/s]
                                                                                                                                                 
[2024-01-30 00:52:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 75%|███████████████████████████████████████████████████████████████████████████████▊                          | 183/243 [00:51<00:15,  3.80it/s]
 76%|████████████████████████████████████████████████████████████████████████████████▋                         | 185/243 [00:51<00:13,  4.44it/s]
                                                                                                                                                 
[2024-01-30 00:52:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 76%|██████████████████████████████████████████████���█████████████████████████████████▋                         | 185/243 [00:51<00:13,  4.44it/s]
                                                                                                                                                 
[2024-01-30 00:52:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 76%|████████████████████████████████████████████████████████████████████████████████▋                         | 185/243 [00:51<00:13,  4.44it/s]
 77%|█████████████████████████████████████████████████████████████████████████████████▏                        | 186/243 [00:51<00:11,  5.01it/s]
                                                                                                                                                 
[2024-01-30 00:52:29] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (5120,), dtype: float16
+
 77%|█████████████████████████████████████████████████████████████████████████████████▏                        | 186/243 [00:51<00:11,  5.01it/s]
                                                                                                                                                 
[2024-01-30 00:52:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 77%|█████████████████████████████████████████████████████████████████████████████████▏                        | 186/243 [00:52<00:11,  5.01it/s]
                                                                                                                                                 
[2024-01-30 00:52:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 77%|█████████████████████████████████████████████████████████████████████████████████▏                        | 186/243 [00:52<00:11,  5.01it/s]
 77%|██████████████████████████████████████████████████████████████████████████████████                        | 188/243 [00:52<00:09,  5.80it/s]
                                                                                                                                                 
[2024-01-30 00:52:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 77%|██████████████████████████████████████████████████████████████████████████████████                        | 188/243 [00:52<00:09,  5.80it/s]
                                                                                                                                                 
[2024-01-30 00:52:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 77%|██████████████████████████████████████████████████████████████████████████████████                        | 188/243 [00:52<00:09,  5.80it/s]
 78%|██████████████████████████████████████████████████████████████████████████████████▍                       | 189/243 [00:52<00:14,  3.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:29] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 78%|██████████████████████████████████████████████████████████████████████████████████▍                       | 189/243 [00:52<00:14,  3.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:30] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 78%|██████████████████████████████████████████████████████████████████████████████████▍                       | 189/243 [00:53<00:14,  3.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:30] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 78%|██████████████████████████████████████████████████████████████████████████████████▍                       | 189/243 [00:53<00:14,  3.82it/s]
 79%|███████████████████████████████████████████████████████████████████████████████████▎                      | 191/243 [00:53<00:11,  4.48it/s]
                                                                                                                                                 
[2024-01-30 00:52:30] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 79%|███████████████████████████████████████████████████████████████████████████████████▎                      | 191/243 [00:53<00:11,  4.48it/s]
                                                                                                                                                 
[2024-01-30 00:52:30] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 79%|███████████████████████████████████████████████████████████████████████████████████▎                      | 191/243 [00:53<00:11,  4.48it/s]
 79%|███████████████████████████████████████████████████████████████████████████████████▊                      | 192/243 [00:53<00:10,  5.04it/s]
                                                                                                                                                 
[2024-01-30 00:52:30] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (5120,), dtype: float16
+
 79%|███████████████████████████████████████████████████████████████████████████████████▊                      | 192/243 [00:53<00:10,  5.04it/s]
                                                                                                                                                 
[2024-01-30 00:52:30] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 79%|███████████████████████████████████████████████████████████████████████████████████▊                      | 192/243 [00:53<00:10,  5.04it/s]
                                                                                                                                                 
[2024-01-30 00:52:30] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 79%|██████████████████████████████��████████████████████████████████████████████████████▊                      | 192/243 [00:53<00:10,  5.04it/s]
 80%|████████████████████████████████████████████████████████████████████████████████████▋                     | 194/243 [00:53<00:08,  5.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 80%|████████████████████████████████████████████████████████████████████████████████████▋                     | 194/243 [00:54<00:08,  5.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 80%|████████████████████████████████████████████████████████████████████████████████████▋                     | 194/243 [00:54<00:08,  5.81it/s]
 80%|█████████████████████████████████████████████████████████████████████████████████████                     | 195/243 [00:54<00:12,  3.83it/s]
                                                                                                                                                 
[2024-01-30 00:52:31] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 80%|█████████████████████████████████████████████████████████████████████████████████████                     | 195/243 [00:54<00:12,  3.83it/s]
                                                                                                                                                 
[2024-01-30 00:52:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 80%|█████████████████████████████████████████████████████████████████████████████████████                     | 195/243 [00:54<00:12,  3.83it/s]
                                                                                                                                                 
[2024-01-30 00:52:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 80%|█████████████████████████████████████████████████████████████████████████████████████                     | 195/243 [00:54<00:12,  3.83it/s]
 81%|█████████████████████████████████████████████████████████████████████████████████████▉                    | 197/243 [00:54<00:10,  4.47it/s]
                                                                                                                                                 
[2024-01-30 00:52:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 81%|█████████████████████████████████████████████████████████████████████████████████████▉                    | 197/243 [00:54<00:10,  4.47it/s]
                                                                                                                                                 
[2024-01-30 00:52:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 81%|█████████████████████████████████████████████████████████████████████████████████████▉                    | 197/243 [00:54<00:10,  4.47it/s]
 81%|██████████████████████████████████████████████████████████████████████████████████████▎                   | 198/243 [00:54<00:08,  5.04it/s]
                                                                                                                                                 
[2024-01-30 00:52:31] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (5120,), dtype: float16
+
 81%|██████████████████████████████████████████████████████████████████████████████████████▎                   | 198/243 [00:54<00:08,  5.04it/s]
                                                                                                                                                 
[2024-01-30 00:52:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 81%|██████████████████████████████████████████████████████████████████████████████████████▎                   | 198/243 [00:54<00:08,  5.04it/s]
                                                                                                                                                 
[2024-01-30 00:52:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 81%|██████████████████████████████████████████████████████████████████████████████████████▎                   | 198/243 [00:54<00:08,  5.04it/s]
 82%|███████████████████████████████████████████████████████████████████████████████████████▏                  | 200/243 [00:54<00:07,  5.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 82%|███████████████████████████████████████████████████████████████████████████████████████▏                  | 200/243 [00:55<00:07,  5.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 82%|███████████████████████████████████████████████████████████████████████████████████████▏                  | 200/243 [00:55<00:07,  5.82it/s]
 83%|███████████████████████████████████████████████████████████████████████████████████████▋                  | 201/243 [00:55<00:10,  3.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:32] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 83%|██████████████████████████████████████████████████████████████████████���████████████████▋                  | 201/243 [00:55<00:10,  3.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 83%|███████████████████████████████████████████████████████████████████████████████████████▋                  | 201/243 [00:55<00:10,  3.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 83%|███████████████████████████████████████████████████████████████████████████████████████▋                  | 201/243 [00:55<00:10,  3.82it/s]
 84%|████████████████████████████████████████████████████████████████████████████████████████▌                 | 203/243 [00:55<00:08,  4.47it/s]
                                                                                                                                                 
[2024-01-30 00:52:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 84%|████████████████████████████████████████████████████████████████████████████████████████▌                 | 203/243 [00:55<00:08,  4.47it/s]
                                                                                                                                                 
[2024-01-30 00:52:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 84%|████████████████████████████████████████████████████████████████████████████████████████▌                 | 203/243 [00:55<00:08,  4.47it/s]
 84%|████████████████████████████████████████████████████████████████████████████████████████▉                 | 204/243 [00:55<00:07,  5.04it/s]
                                                                                                                                                 
[2024-01-30 00:52:32] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (5120,), dtype: float16
+
 84%|████████████████████████████████████████████████████████████████████████████████████████▉                 | 204/243 [00:55<00:07,  5.04it/s]
                                                                                                                                                 
[2024-01-30 00:52:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 84%|████████████████████████████████████████████████████████████████████████████████████████▉                 | 204/243 [00:56<00:07,  5.04it/s]
                                                                                                                                                 
[2024-01-30 00:52:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 84%|███████████████████████████████████████████████████████████████████████████████���████████▉                 | 204/243 [00:56<00:07,  5.04it/s]
 85%|█████████████████████████████████████████████████████████████████████████████████████████▊                | 206/243 [00:56<00:06,  5.84it/s]
                                                                                                                                                 
[2024-01-30 00:52:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 85%|█████████████████████████████████████████████████████████████████████████████████████████▊                | 206/243 [00:56<00:06,  5.84it/s]
                                                                                                                                                 
[2024-01-30 00:52:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 85%|█████████████████████████████████████████████████████████████████████████████████████████▊                | 206/243 [00:56<00:06,  5.84it/s]
 85%|██████████████████████████████████████████████████████████████████████████████████████████▎               | 207/243 [00:56<00:09,  3.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:33] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 85%|██████████████████████████████████████████████████████████████████████████████████████████▎               | 207/243 [00:56<00:09,  3.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 85%|██████████████████████████████████████████████████████████████████████████████████████████▎               | 207/243 [00:56<00:09,  3.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 85%|██████████████████████████████████████████████████████████████████████████████████████████▎               | 207/243 [00:56<00:09,  3.81it/s]
 86%|███████████████████████████████████████████████████████████████████████████████████████████▏              | 209/243 [00:56<00:07,  4.45it/s]
                                                                                                                                                 
[2024-01-30 00:52:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 86%|███████████████████████████████████████████████████████████████████████████████████████████▏              | 209/243 [00:57<00:07,  4.45it/s]
                                                                                                                                                 
[2024-01-30 00:52:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 86%|███████████████████████████████████████████████████████████████████████████████████████████▏              | 209/243 [00:57<00:07,  4.45it/s]
 86%|███████████████████████████████████████████████████████████████████████████████████████████▌              | 210/243 [00:57<00:06,  5.02it/s]
                                                                                                                                                 
[2024-01-30 00:52:34] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (5120,), dtype: float16
+
 86%|███████████████████████████████████████████████████████████████████████████████████████████▌              | 210/243 [00:57<00:06,  5.02it/s]
                                                                                                                                                 
[2024-01-30 00:52:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 86%|███████████████████████████████████████████████████████████████████████████████████████████▌              | 210/243 [00:57<00:06,  5.02it/s]
                                                                                                                                                 
[2024-01-30 00:52:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 86%|███████████████████████████████████████████████████████████████████████████████████████████▌              | 210/243 [00:57<00:06,  5.02it/s]
 87%|████████████████████████████████████████████████████████████████████████████████████████████▍             | 212/243 [00:57<00:05,  5.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 87%|████████████████████████████████████████████████████████████████████████████████████████████▍             | 212/243 [00:57<00:05,  5.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 87%|████████████████████████████████████████████████████████████████████████████████████████████▍             | 212/243 [00:57<00:05,  5.81it/s]
 88%|████████████████████████████████████████████████████████████████████████████████████████████▉             | 213/243 [00:57<00:07,  3.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:35] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 88%|████████████████████████████████████████████████████████████████████████████████████████████▉             | 213/243 [00:57<00:07,  3.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 88%|████████████████████████████████████████████████████████████████████████████████████████████▉             | 213/243 [00:58<00:07,  3.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 88%|████████████████████████████████████████████████████████████████████████████████████████████▉             | 213/243 [00:58<00:07,  3.81it/s]
 88%|█████████████████████████████████████████████████████████████████████████████████████████████▊            | 215/243 [00:58<00:06,  4.44it/s]
                                                                                                                                                 
[2024-01-30 00:52:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 88%|█████████████████████████████████████████████████████████████████████████████████████████████▊            | 215/243 [00:58<00:06,  4.44it/s]
                                                                                                                                                 
[2024-01-30 00:52:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 88%|█████████████████████████████████████████████████████████████████████████████████████████████▊            | 215/243 [00:58<00:06,  4.44it/s]
 89%|██████████████████████████████████████████████████████████████████████████████████████████████▏           | 216/243 [00:58<00:05,  5.01it/s]
                                                                                                                                                 
[2024-01-30 00:52:35] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (5120,), dtype: float16
+
 89%|██████████████████████████████████████████████████████████████████████████████████████████████▏           | 216/243 [00:58<00:05,  5.01it/s]
                                                                                                                                                 
[2024-01-30 00:52:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 89%|██████████████████████████████████████████████████████████████████████████████████████████████▏           | 216/243 [00:58<00:05,  5.01it/s]
                                                                                                                                                 
[2024-01-30 00:52:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 89%|██████████████████████████████████████████████████████████████████████████████████████████████▏           | 216/243 [00:58<00:05,  5.01it/s]
 90%|███████████████████████████████████████████████████████████████████████████████████████████████           | 218/243 [00:58<00:04,  5.80it/s]
                                                                                                                                                 
[2024-01-30 00:52:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 90%|███████████████████████████████████████████████████████████████████████████████████████████████           | 218/243 [00:59<00:04,  5.80it/s]
                                                                                                                                                 
[2024-01-30 00:52:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 90%|███████████████████████████████████████████████████████████████████████████████████████████████           | 218/243 [00:59<00:04,  5.80it/s]
 90%|███████████████████████████████████████████████████████████████████████████████████████████████▌          | 219/243 [00:59<00:06,  3.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:36] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 90%|███████████████████████████████████████████████████████████████████████████████████████████████▌          | 219/243 [00:59<00:06,  3.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 90%|███████████████████████████████████████████████████████████████████████████████████████████████▌          | 219/243 [00:59<00:06,  3.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 90%|███████████████████████████████████████████████████████████████████████████████████████████████▌          | 219/243 [00:59<00:06,  3.82it/s]
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▍         | 221/243 [00:59<00:05,  4.40it/s]
                                                                                                                                                 
[2024-01-30 00:52:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 91%|█████████████████████████████████████████████████████████████████████████████████████████████��██▍         | 221/243 [00:59<00:05,  4.40it/s]
                                                                                                                                                 
[2024-01-30 00:52:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▍         | 221/243 [00:59<00:05,  4.40it/s]
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▊         | 222/243 [00:59<00:04,  4.97it/s]
                                                                                                                                                 
[2024-01-30 00:52:36] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (5120,), dtype: float16
+
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▊         | 222/243 [00:59<00:04,  4.97it/s]
                                                                                                                                                 
[2024-01-30 00:52:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▊         | 222/243 [00:59<00:04,  4.97it/s]
                                                                                                                                                 
[2024-01-30 00:52:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▊         | 222/243 [00:59<00:04,  4.97it/s]
 92%|█████████████████████████████████████████████████████████████████████████████████████████████████▋        | 224/243 [00:59<00:03,  5.75it/s]
                                                                                                                                                 
[2024-01-30 00:52:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 92%|█████████████████████████████████████████████████████████████████████████████████████████████████▋        | 224/243 [01:00<00:03,  5.75it/s]
                                                                                                                                                 
[2024-01-30 00:52:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 92%|█████████████████████████████████████████████████████████████████████████████████████████████████▋        | 224/243 [01:00<00:03,  5.75it/s]
 93%|██████████████████████████████████████████████████████████████████████████████████████████████████▏       | 225/243 [01:00<00:04,  3.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:37] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 93%|██████████████████████████████████████████████████████████████████████████████████████████████████▏       | 225/243 [01:00<00:04,  3.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 93%|██████████████████████████████████████████████████████████████████████████████████████████████████▏       | 225/243 [01:00<00:04,  3.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 93%|██████████████████████████████████████████████████████████████████████████████████████████████████▏       | 225/243 [01:00<00:04,  3.81it/s]
 93%|███████████████████████████████████████████████████████████████████████████████████████████████████       | 227/243 [01:00<00:03,  4.39it/s]
                                                                                                                                                 
[2024-01-30 00:52:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 93%|███████████████████████████████████████████████████████████████████████████████████████████████████       | 227/243 [01:00<00:03,  4.39it/s]
                                                                                                                                                 
[2024-01-30 00:52:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 93%|███████████████████████████████████████████████████████████████████████████████████████████████████       | 227/243 [01:00<00:03,  4.39it/s]
 94%|███████████████████████████████████████████████████████████████████████████████████████████████████▍      | 228/243 [01:00<00:03,  4.96it/s]
                                                                                                                                                 
[2024-01-30 00:52:38] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.28.input_layernorm.weight", shape: (5120,), dtype: float16
+
 94%|███████████████████████████████████████████████████████████████████████████████████████████████████▍      | 228/243 [01:00<00:03,  4.96it/s]
                                                                                                                                                 
[2024-01-30 00:52:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 94%|██████████████████████████████████████████████████████████████████████████████████████████████████���▍      | 228/243 [01:01<00:03,  4.96it/s]
                                                                                                                                                 
[2024-01-30 00:52:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 94%|███████████████████████████████████████████████████████████████████████████████████████████████████▍      | 228/243 [01:01<00:03,  4.96it/s]
 95%|████████████████████████████████████████████████████████████████████████████████████████████████████▎     | 230/243 [01:01<00:02,  5.74it/s]
                                                                                                                                                 
[2024-01-30 00:52:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 95%|████████████████████████████████████████████████████████████████████████████████████████████████████▎     | 230/243 [01:01<00:02,  5.74it/s]
                                                                                                                                                 
[2024-01-30 00:52:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 95%|████████████████████████████████████████████████████████████████████████████████████████████████████▎     | 230/243 [01:01<00:02,  5.74it/s]
 95%|████████████████████████████████████████████████████████████████████████████████████████████████████▊     | 231/243 [01:01<00:03,  3.80it/s]
                                                                                                                                                 
[2024-01-30 00:52:38] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.28.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 95%|████████████████████████████████████████████████████████████████████████████████████████████████████▊     | 231/243 [01:01<00:03,  3.80it/s]
                                                                                                                                                 
[2024-01-30 00:52:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 95%|████████████████████████████████████████████████████████████████████████████████████████████████████▊     | 231/243 [01:02<00:03,  3.80it/s]
                                                                                                                                                 
[2024-01-30 00:52:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 95%|████████████████████████████████████████████████████████████████████████████████████████████████████▊     | 231/243 [01:02<00:03,  3.80it/s]
 96%|█████████████████████████████████████████████████████████████████████████████████████████████████████▋    | 233/243 [01:02<00:02,  4.39it/s]
                                                                                                                                                 
[2024-01-30 00:52:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 96%|█████████████████████████████████████████████████████████████████████████████████████████████████████▋    | 233/243 [01:02<00:02,  4.39it/s]
                                                                                                                                                 
[2024-01-30 00:52:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 96%|█████████████████████████████████████████████████████████████████████████████████████████████████████▋    | 233/243 [01:02<00:02,  4.39it/s]
 96%|██████████████████████████████████████████████████████████████████████████████████████████████████████    | 234/243 [01:02<00:01,  4.96it/s]
                                                                                                                                                 
[2024-01-30 00:52:39] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.29.input_layernorm.weight", shape: (5120,), dtype: float16
+
 96%|██████████████████████████████████████████████████████████████████████████████████████████████████████    | 234/243 [01:02<00:01,  4.96it/s]
                                                                                                                                                 
[2024-01-30 00:52:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_weight", shape: (5120, 1728), dtype: uint32
+
 96%|██████████████████████████████████████████████████████████████████████████████████████████████████████    | 234/243 [01:02<00:01,  4.96it/s]
                                                                                                                                                 
[2024-01-30 00:52:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_scale", shape: (5120, 432), dtype: float16
+
 96%|██████████████████████████████████████████████████████████████████████████████████████████████████████    | 234/243 [01:02<00:01,  4.96it/s]
 97%|██████████████████████████████████████████████████████████████████████████████████████████████████████▉   | 236/243 [01:02<00:01,  5.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 97%|██████████████████████████████████████████████████████████████████████████████████████████████████████▉   | 236/243 [01:03<00:01,  5.81it/s]
                                                                                                                                                 
[2024-01-30 00:52:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 97%|███████████████████████████████████████████████████████████████���██████████████████████████████████████▉   | 236/243 [01:03<00:01,  5.81it/s]
 98%|███████████████████████████████████████████████████████████████████████████████████████████████████████▍  | 237/243 [01:03<00:01,  3.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.29.post_attention_layernorm.weight", shape: (5120,), dtype: float16
+
 98%|███████████████████████████████████████████████████████████████████████████████████████████████████████▍  | 237/243 [01:03<00:01,  3.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 98%|███████████████████████████████████████████████████████████████████████████████████████████████████████▍  | 237/243 [01:03<00:01,  3.82it/s]
                                                                                                                                                 
[2024-01-30 00:52:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 98%|███████████████████████████████████████████████████████████████████████████████████████████████████████▍  | 237/243 [01:03<00:01,  3.82it/s]
 98%|████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 239/243 [01:03<00:00,  4.42it/s]
                                                                                                                                                 
[2024-01-30 00:52:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
 98%|████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 239/243 [01:03<00:00,  4.42it/s]
                                                                                                                                                 
[2024-01-30 00:52:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
 98%|████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 239/243 [01:03<00:00,  4.42it/s]
 99%|████████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 240/243 [01:03<00:00,  5.00it/s]
                                                                                                                                                 
[2024-01-30 00:52:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_weight", shape: (27648, 640), dtype: uint32
+
 99%|█████████████████████████████████████████████████████████████████████████████���██████████████████████████▋ | 240/243 [01:04<00:00,  5.00it/s]
                                                                                                                                                 
[2024-01-30 00:52:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_scale", shape: (27648, 160), dtype: float16
+
 99%|████████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 240/243 [01:04<00:00,  5.00it/s]
 99%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▏| 241/243 [01:04<00:00,  3.73it/s]
                                                                                                                                                 
[2024-01-30 00:52:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_weight", shape: (15360, 640), dtype: uint32
+
 99%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▏| 241/243 [01:04<00:00,  3.73it/s]
                                                                                                                                                 
[2024-01-30 00:52:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_scale", shape: (15360, 160), dtype: float16
+
 99%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▏| 241/243 [01:04<00:00,  3.73it/s]
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▌| 242/243 [01:04<00:00,  3.64it/s]
                                                                                                                                                 
[2024-01-30 00:52:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_weight", shape: (5120, 640), dtype: uint32
+
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▌| 242/243 [01:04<00:00,  3.64it/s]
                                                                                                                                                 
[2024-01-30 00:52:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_scale", shape: (5120, 160), dtype: float16
+
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▌| 242/243 [01:04<00:00,  3.64it/s]
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████| 243/243 [01:04<00:00,  3.77it/s]
+[2024-01-30 00:52:41] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model-00001-of-00003.bin
+[2024-01-30 00:52:42] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpoi4p39pd/repo/pytorch_model-00002-of-00003.bin
+[2024-01-30 00:52:42] INFO stats.py:76: Time usage: HF loading: 19.855 sec; Pre-quantization mapping: 40.581 sec; Quantization: 1.120 sec
+[2024-01-30 00:52:42] INFO stats.py:90: RAM usage: Peak RAM: 36.979 GB. Total bytes loaded from disk: 48.488 GB
+[2024-01-30 00:52:42] INFO convert_weight.py:121: Parameter size after quantization: 6.819 GB
+[2024-01-30 00:52:42] INFO convert_weight.py:126: Total parameters: 13,015,864,320
+[2024-01-30 00:52:42] INFO convert_weight.py:127: Bits per parameter: 4.500
+Start storing to cache /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y
+

[0001/0405] saving lm_head.q_weight
                                   
[0002/0405] saving lm_head.q_scale
                                   
[0003/0405] saving model.layers.30.input_layernorm.weight
                                                         
[0004/0405] saving model.layers.30.mlp.down_proj.q_weight
                                                         
[0005/0405] saving model.layers.30.mlp.down_proj.q_scale
                                                         
[0006/0405] saving model.layers.30.post_attention_layernorm.weight
                                                                  
[0007/0405] saving model.layers.31.input_layernorm.weight
                                                                  
[0008/0405] saving model.layers.31.mlp.down_proj.q_weight
                                                                  
[0009/0405] saving model.layers.31.mlp.down_proj.q_scale
                                                                  
[0010/0405] saving model.layers.31.mlp.gate_up_proj.q_weight
                                                                  
[0011/0405] saving model.layers.31.mlp.gate_up_proj.q_scale
                                                                  
[0012/0405] saving model.layers.31.post_attention_layernorm.weight
                                                                  
[0013/0405] saving model.layers.31.self_attn.qkv_proj.q_weight
                                                                  
[0014/0405] saving model.layers.31.self_attn.qkv_proj.q_scale
                                                                  
[0015/0405] saving model.layers.31.self_attn.o_proj.q_weight
                                                                  
[0016/0405] saving model.layers.31.self_attn.o_proj.q_scale
                                                                  
[0017/0405] saving model.layers.32.input_layernorm.weight
                                                                  
[0018/0405] saving model.layers.32.mlp.down_proj.q_weight
                                                                  
[0019/0405] saving model.layers.32.mlp.down_proj.q_scale
                                                                  
[0020/0405] saving model.layers.32.mlp.gate_up_proj.q_weight
                                                                  
[0021/0405] saving model.layers.32.mlp.gate_up_proj.q_scale
                                                                  
[0022/0405] saving model.layers.32.post_attention_layernorm.weight
                                                                  
[0023/0405] saving model.layers.32.self_attn.qkv_proj.q_weight
                                                                  
[0024/0405] saving model.layers.32.self_attn.qkv_proj.q_scale
                                                                  
[0025/0405] saving model.layers.32.self_attn.o_proj.q_weight
                                                                  
[0026/0405] saving model.layers.32.self_attn.o_proj.q_scale
                                                                  
[0027/0405] saving model.layers.33.input_layernorm.weight
                                                                  
[0028/0405] saving model.layers.33.mlp.down_proj.q_weight
                                                                  
[0029/0405] saving model.layers.33.mlp.down_proj.q_scale
                                                                  
[0030/0405] saving model.layers.33.mlp.gate_up_proj.q_weight
                                                                  
[0031/0405] saving model.layers.33.mlp.gate_up_proj.q_scale
                                                                  
[0032/0405] saving model.layers.33.post_attention_layernorm.weight
                                                                  
[0033/0405] saving model.layers.33.self_attn.qkv_proj.q_weight
                                                                  
[0034/0405] saving model.layers.33.self_attn.qkv_proj.q_scale
                                                                  
[0035/0405] saving model.layers.33.self_attn.o_proj.q_weight
                                                                  
[0036/0405] saving model.layers.33.self_attn.o_proj.q_scale
                                                                  
[0037/0405] saving model.layers.34.input_layernorm.weight
                                                                  
[0038/0405] saving model.layers.34.mlp.down_proj.q_weight
                                                                  
[0039/0405] saving model.layers.34.mlp.down_proj.q_scale
                                                                  
[0040/0405] saving model.layers.34.mlp.gate_up_proj.q_weight
                                                                  
[0041/0405] saving model.layers.34.mlp.gate_up_proj.q_scale
                                                                  
[0042/0405] saving model.layers.34.post_attention_layernorm.weight
                                                                  
[0043/0405] saving model.layers.34.self_attn.qkv_proj.q_weight
                                                                  
[0044/0405] saving model.layers.34.self_attn.qkv_proj.q_scale
                                                                  
[0045/0405] saving model.layers.34.self_attn.o_proj.q_weight
                                                                  
[0046/0405] saving model.layers.34.self_attn.o_proj.q_scale
                                                                  
[0047/0405] saving model.layers.35.input_layernorm.weight
                                                                  
[0048/0405] saving model.layers.35.mlp.down_proj.q_weight
                                                                  
[0049/0405] saving model.layers.35.mlp.down_proj.q_scale
                                                                  
[0050/0405] saving model.layers.35.mlp.gate_up_proj.q_weight
                                                                  
[0051/0405] saving model.layers.35.mlp.gate_up_proj.q_scale
                                                                  
[0052/0405] saving model.layers.35.post_attention_layernorm.weight
                                                                  
[0053/0405] saving model.layers.35.self_attn.qkv_proj.q_weight
                                                                  
[0054/0405] saving model.layers.35.self_attn.qkv_proj.q_scale
                                                                  
[0055/0405] saving model.layers.35.self_attn.o_proj.q_weight
                                                                  
[0056/0405] saving model.layers.35.self_attn.o_proj.q_scale
                                                                  
[0057/0405] saving model.layers.36.input_layernorm.weight
                                                                  
[0058/0405] saving model.layers.36.mlp.down_proj.q_weight
                                                                  
[0059/0405] saving model.layers.36.mlp.down_proj.q_scale
                                                                  
[0060/0405] saving model.layers.36.mlp.gate_up_proj.q_weight
                                                                  
[0061/0405] saving model.layers.36.mlp.gate_up_proj.q_scale
                                                                  
[0062/0405] saving model.layers.36.post_attention_layernorm.weight
                                                                  
[0063/0405] saving model.layers.36.self_attn.qkv_proj.q_weight
                                                                  
[0064/0405] saving model.layers.36.self_attn.qkv_proj.q_scale
                                                                  
[0065/0405] saving model.layers.36.self_attn.o_proj.q_weight
                                                                  
[0066/0405] saving model.layers.36.self_attn.o_proj.q_scale
                                                                  
[0067/0405] saving model.layers.37.input_layernorm.weight
                                                                  
[0068/0405] saving model.layers.37.mlp.down_proj.q_weight
                                                                  
[0069/0405] saving model.layers.37.mlp.down_proj.q_scale
                                                                  
[0070/0405] saving model.layers.37.mlp.gate_up_proj.q_weight
                                                                  
[0071/0405] saving model.layers.37.mlp.gate_up_proj.q_scale
                                                                  
[0072/0405] saving model.layers.37.post_attention_layernorm.weight
                                                                  
[0073/0405] saving model.layers.37.self_attn.qkv_proj.q_weight
                                                                  
[0074/0405] saving model.layers.37.self_attn.qkv_proj.q_scale
                                                                  
[0075/0405] saving model.layers.37.self_attn.o_proj.q_weight
                                                                  
[0076/0405] saving model.layers.37.self_attn.o_proj.q_scale
                                                                  
[0077/0405] saving model.layers.38.input_layernorm.weight
                                                                  
[0078/0405] saving model.layers.38.mlp.down_proj.q_weight
                                                                  
[0079/0405] saving model.layers.38.mlp.down_proj.q_scale
                                                                  
[0080/0405] saving model.layers.38.mlp.gate_up_proj.q_weight
                                                                  
[0081/0405] saving model.layers.38.mlp.gate_up_proj.q_scale
                                                                  
[0082/0405] saving model.layers.38.post_attention_layernorm.weight
                                                                  
[0083/0405] saving model.layers.38.self_attn.qkv_proj.q_weight
                                                                  
[0084/0405] saving model.layers.38.self_attn.qkv_proj.q_scale
                                                                  
[0085/0405] saving model.layers.38.self_attn.o_proj.q_weight
                                                                  
[0086/0405] saving model.layers.38.self_attn.o_proj.q_scale
                                                                  
[0087/0405] saving model.layers.39.input_layernorm.weight
                                                                  
[0088/0405] saving model.layers.39.mlp.down_proj.q_weight
                                                                  
[0089/0405] saving model.layers.39.mlp.down_proj.q_scale
                                                                  
[0090/0405] saving model.layers.39.mlp.gate_up_proj.q_weight
                                                                  
[0091/0405] saving model.layers.39.mlp.gate_up_proj.q_scale
                                                                  
[0092/0405] saving model.layers.39.post_attention_layernorm.weight
                                                                  
[0093/0405] saving model.layers.39.self_attn.qkv_proj.q_weight
                                                                  
[0094/0405] saving model.layers.39.self_attn.qkv_proj.q_scale
                                                                  
[0095/0405] saving model.layers.39.self_attn.o_proj.q_weight
                                                                  
[0096/0405] saving model.layers.39.self_attn.o_proj.q_scale
                                                                  
[0097/0405] saving model.norm.weight
                                                                  
[0098/0405] saving model.embed_tokens.q_weight
                                                                  
[0099/0405] saving model.embed_tokens.q_scale
                                                                  
[0100/0405] saving model.layers.0.input_layernorm.weight
                                                                  
[0101/0405] saving model.layers.0.mlp.down_proj.q_weight
                                                                  
[0102/0405] saving model.layers.0.mlp.down_proj.q_scale
                                                                  
[0103/0405] saving model.layers.0.mlp.gate_up_proj.q_weight
                                                                  
[0104/0405] saving model.layers.0.mlp.gate_up_proj.q_scale
                                                                  
[0105/0405] saving model.layers.0.post_attention_layernorm.weight
                                                                  
[0106/0405] saving model.layers.0.self_attn.qkv_proj.q_weight
                                                                  
[0107/0405] saving model.layers.0.self_attn.qkv_proj.q_scale
                                                                  
[0108/0405] saving model.layers.0.self_attn.o_proj.q_weight
                                                                  
[0109/0405] saving model.layers.0.self_attn.o_proj.q_scale
                                                                  
[0110/0405] saving model.layers.1.input_layernorm.weight
                                                                  
[0111/0405] saving model.layers.1.mlp.down_proj.q_weight
                                                                  
[0112/0405] saving model.layers.1.mlp.down_proj.q_scale
                                                                  
[0113/0405] saving model.layers.1.mlp.gate_up_proj.q_weight
                                                                  
[0114/0405] saving model.layers.1.mlp.gate_up_proj.q_scale
                                                                  
[0115/0405] saving model.layers.1.post_attention_layernorm.weight
                                                                  
[0116/0405] saving model.layers.1.self_attn.qkv_proj.q_weight
                                                                  
[0117/0405] saving model.layers.1.self_attn.qkv_proj.q_scale
                                                                  
[0118/0405] saving model.layers.1.self_attn.o_proj.q_weight
                                                                  
[0119/0405] saving model.layers.1.self_attn.o_proj.q_scale
                                                                  
[0120/0405] saving model.layers.10.input_layernorm.weight
                                                                  
[0121/0405] saving model.layers.10.mlp.down_proj.q_weight
                                                                  
[0122/0405] saving model.layers.10.mlp.down_proj.q_scale
                                                                  
[0123/0405] saving model.layers.10.mlp.gate_up_proj.q_weight
                                                                  
[0124/0405] saving model.layers.10.mlp.gate_up_proj.q_scale
                                                                  
[0125/0405] saving model.layers.10.post_attention_layernorm.weight
                                                                  
[0126/0405] saving model.layers.10.self_attn.qkv_proj.q_weight
                                                                  
[0127/0405] saving model.layers.10.self_attn.qkv_proj.q_scale
                                                                  
[0128/0405] saving model.layers.10.self_attn.o_proj.q_weight
                                                                  
[0129/0405] saving model.layers.10.self_attn.o_proj.q_scale
                                                                  
[0130/0405] saving model.layers.11.input_layernorm.weight
                                                                  
[0131/0405] saving model.layers.11.mlp.down_proj.q_weight
                                                                  
[0132/0405] saving model.layers.11.mlp.down_proj.q_scale
                                                                  
[0133/0405] saving model.layers.11.mlp.gate_up_proj.q_weight
                                                                  
[0134/0405] saving model.layers.11.mlp.gate_up_proj.q_scale
                                                                  
[0135/0405] saving model.layers.11.post_attention_layernorm.weight
                                                                  
[0136/0405] saving model.layers.11.self_attn.qkv_proj.q_weight
                                                                  
[0137/0405] saving model.layers.11.self_attn.qkv_proj.q_scale
                                                                  
[0138/0405] saving model.layers.11.self_attn.o_proj.q_weight
                                                                  
[0139/0405] saving model.layers.11.self_attn.o_proj.q_scale
                                                                  
[0140/0405] saving model.layers.12.input_layernorm.weight
                                                                  
[0141/0405] saving model.layers.12.mlp.down_proj.q_weight
                                                                  
[0142/0405] saving model.layers.12.mlp.down_proj.q_scale
                                                                  
[0143/0405] saving model.layers.12.mlp.gate_up_proj.q_weight
                                                                  
[0144/0405] saving model.layers.12.mlp.gate_up_proj.q_scale
                                                                  
[0145/0405] saving model.layers.12.post_attention_layernorm.weight
                                                                  
[0146/0405] saving model.layers.12.self_attn.qkv_proj.q_weight
                                                                  
[0147/0405] saving model.layers.12.self_attn.qkv_proj.q_scale
                                                                  
[0148/0405] saving model.layers.12.self_attn.o_proj.q_weight
                                                                  
[0149/0405] saving model.layers.12.self_attn.o_proj.q_scale
                                                                  
[0150/0405] saving model.layers.13.input_layernorm.weight
                                                                  
[0151/0405] saving model.layers.13.mlp.down_proj.q_weight
                                                                  
[0152/0405] saving model.layers.13.mlp.down_proj.q_scale
                                                                  
[0153/0405] saving model.layers.13.mlp.gate_up_proj.q_weight
                                                                  
[0154/0405] saving model.layers.13.mlp.gate_up_proj.q_scale
                                                                  
[0155/0405] saving model.layers.13.post_attention_layernorm.weight
                                                                  
[0156/0405] saving model.layers.13.self_attn.qkv_proj.q_weight
                                                                  
[0157/0405] saving model.layers.13.self_attn.qkv_proj.q_scale
                                                                  
[0158/0405] saving model.layers.13.self_attn.o_proj.q_weight
                                                                  
[0159/0405] saving model.layers.13.self_attn.o_proj.q_scale
                                                                  
[0160/0405] saving model.layers.14.input_layernorm.weight
                                                                  
[0161/0405] saving model.layers.14.mlp.down_proj.q_weight
                                                                  
[0162/0405] saving model.layers.14.mlp.down_proj.q_scale
                                                                  
[0163/0405] saving model.layers.14.mlp.gate_up_proj.q_weight
                                                                  
[0164/0405] saving model.layers.14.mlp.gate_up_proj.q_scale
                                                                  
[0165/0405] saving model.layers.14.post_attention_layernorm.weight
                                                                  
[0166/0405] saving model.layers.14.self_attn.qkv_proj.q_weight
                                                                  
[0167/0405] saving model.layers.14.self_attn.qkv_proj.q_scale
                                                                  
[0168/0405] saving model.layers.14.self_attn.o_proj.q_weight
                                                                  
[0169/0405] saving model.layers.14.self_attn.o_proj.q_scale
                                                                  
[0170/0405] saving model.layers.15.self_attn.qkv_proj.q_weight
                                                                  
[0171/0405] saving model.layers.15.self_attn.qkv_proj.q_scale
                                                                  
[0172/0405] saving model.layers.2.input_layernorm.weight
                                                                  
[0173/0405] saving model.layers.2.mlp.down_proj.q_weight
                                                                  
[0174/0405] saving model.layers.2.mlp.down_proj.q_scale
                                                                  
[0175/0405] saving model.layers.2.mlp.gate_up_proj.q_weight
                                                                  
[0176/0405] saving model.layers.2.mlp.gate_up_proj.q_scale
                                                                  
[0177/0405] saving model.layers.2.post_attention_layernorm.weight
                                                                  
[0178/0405] saving model.layers.2.self_attn.qkv_proj.q_weight
                                                                  
[0179/0405] saving model.layers.2.self_attn.qkv_proj.q_scale
                                                                  
[0180/0405] saving model.layers.2.self_attn.o_proj.q_weight
                                                                  
[0181/0405] saving model.layers.2.self_attn.o_proj.q_scale
                                                                  
[0182/0405] saving model.layers.3.input_layernorm.weight
                                                                  
[0183/0405] saving model.layers.3.mlp.down_proj.q_weight
                                                                  
[0184/0405] saving model.layers.3.mlp.down_proj.q_scale
                                                                  
[0185/0405] saving model.layers.3.mlp.gate_up_proj.q_weight
                                                                  
[0186/0405] saving model.layers.3.mlp.gate_up_proj.q_scale
                                                                  
[0187/0405] saving model.layers.3.post_attention_layernorm.weight
                                                                  
[0188/0405] saving model.layers.3.self_attn.qkv_proj.q_weight
                                                                  
[0189/0405] saving model.layers.3.self_attn.qkv_proj.q_scale
                                                                  
[0190/0405] saving model.layers.3.self_attn.o_proj.q_weight
                                                                  
[0191/0405] saving model.layers.3.self_attn.o_proj.q_scale
                                                                  
[0192/0405] saving model.layers.4.input_layernorm.weight
                                                                  
[0193/0405] saving model.layers.4.mlp.down_proj.q_weight
                                                                  
[0194/0405] saving model.layers.4.mlp.down_proj.q_scale
                                                                  
[0195/0405] saving model.layers.4.mlp.gate_up_proj.q_weight
                                                                  
[0196/0405] saving model.layers.4.mlp.gate_up_proj.q_scale
                                                                  
[0197/0405] saving model.layers.4.post_attention_layernorm.weight
                                                                  
[0198/0405] saving model.layers.4.self_attn.qkv_proj.q_weight
                                                                  
[0199/0405] saving model.layers.4.self_attn.qkv_proj.q_scale
                                                                  
[0200/0405] saving model.layers.4.self_attn.o_proj.q_weight
                                                                  
[0201/0405] saving model.layers.4.self_attn.o_proj.q_scale
                                                                  
[0202/0405] saving model.layers.5.input_layernorm.weight
                                                                  
[0203/0405] saving model.layers.5.mlp.down_proj.q_weight
                                                                  
[0204/0405] saving model.layers.5.mlp.down_proj.q_scale
                                                                  
[0205/0405] saving model.layers.5.mlp.gate_up_proj.q_weight
                                                                  
[0206/0405] saving model.layers.5.mlp.gate_up_proj.q_scale
                                                                  
[0207/0405] saving model.layers.5.post_attention_layernorm.weight
                                                                  
[0208/0405] saving model.layers.5.self_attn.qkv_proj.q_weight
                                                                  
[0209/0405] saving model.layers.5.self_attn.qkv_proj.q_scale
                                                                  
[0210/0405] saving model.layers.5.self_attn.o_proj.q_weight
                                                                  
[0211/0405] saving model.layers.5.self_attn.o_proj.q_scale
                                                                  
[0212/0405] saving model.layers.6.input_layernorm.weight
                                                                  
[0213/0405] saving model.layers.6.mlp.down_proj.q_weight
                                                                  
[0214/0405] saving model.layers.6.mlp.down_proj.q_scale
                                                                  
[0215/0405] saving model.layers.6.mlp.gate_up_proj.q_weight
                                                                  
[0216/0405] saving model.layers.6.mlp.gate_up_proj.q_scale
                                                                  
[0217/0405] saving model.layers.6.post_attention_layernorm.weight
                                                                  
[0218/0405] saving model.layers.6.self_attn.qkv_proj.q_weight
                                                                  
[0219/0405] saving model.layers.6.self_attn.qkv_proj.q_scale
                                                                  
[0220/0405] saving model.layers.6.self_attn.o_proj.q_weight
                                                                  
[0221/0405] saving model.layers.6.self_attn.o_proj.q_scale
                                                                  
[0222/0405] saving model.layers.7.input_layernorm.weight
                                                                  
[0223/0405] saving model.layers.7.mlp.down_proj.q_weight
                                                                  
[0224/0405] saving model.layers.7.mlp.down_proj.q_scale
                                                                  
[0225/0405] saving model.layers.7.mlp.gate_up_proj.q_weight
                                                                  
[0226/0405] saving model.layers.7.mlp.gate_up_proj.q_scale
                                                                  
[0227/0405] saving model.layers.7.post_attention_layernorm.weight
                                                                  
[0228/0405] saving model.layers.7.self_attn.qkv_proj.q_weight
                                                                  
[0229/0405] saving model.layers.7.self_attn.qkv_proj.q_scale
                                                                  
[0230/0405] saving model.layers.7.self_attn.o_proj.q_weight
                                                                  
[0231/0405] saving model.layers.7.self_attn.o_proj.q_scale
                                                                  
[0232/0405] saving model.layers.8.input_layernorm.weight
                                                                  
[0233/0405] saving model.layers.8.mlp.down_proj.q_weight
                                                                  
[0234/0405] saving model.layers.8.mlp.down_proj.q_scale
                                                                  
[0235/0405] saving model.layers.8.mlp.gate_up_proj.q_weight
                                                                  
[0236/0405] saving model.layers.8.mlp.gate_up_proj.q_scale
                                                                  
[0237/0405] saving model.layers.8.post_attention_layernorm.weight
                                                                  
[0238/0405] saving model.layers.8.self_attn.qkv_proj.q_weight
                                                                  
[0239/0405] saving model.layers.8.self_attn.qkv_proj.q_scale
                                                                  
[0240/0405] saving model.layers.8.self_attn.o_proj.q_weight
                                                                  
[0241/0405] saving model.layers.8.self_attn.o_proj.q_scale
                                                                  
[0242/0405] saving model.layers.9.input_layernorm.weight
                                                                  
[0243/0405] saving model.layers.9.mlp.down_proj.q_weight
                                                                  
[0244/0405] saving model.layers.9.mlp.down_proj.q_scale
                                                                  
[0245/0405] saving model.layers.9.mlp.gate_up_proj.q_weight
                                                                  
[0246/0405] saving model.layers.9.mlp.gate_up_proj.q_scale
                                                                  
[0247/0405] saving model.layers.9.post_attention_layernorm.weight
                                                                  
[0248/0405] saving model.layers.9.self_attn.qkv_proj.q_weight
                                                                  
[0249/0405] saving model.layers.9.self_attn.qkv_proj.q_scale
                                                                  
[0250/0405] saving model.layers.9.self_attn.o_proj.q_weight
                                                                  
[0251/0405] saving model.layers.9.self_attn.o_proj.q_scale
                                                                  
[0252/0405] saving model.layers.15.input_layernorm.weight
                                                                  
[0253/0405] saving model.layers.15.mlp.down_proj.q_weight
                                                                  
[0254/0405] saving model.layers.15.mlp.down_proj.q_scale
                                                                  
[0255/0405] saving model.layers.15.mlp.gate_up_proj.q_weight
                                                                  
[0256/0405] saving model.layers.15.mlp.gate_up_proj.q_scale
                                                                  
[0257/0405] saving model.layers.15.post_attention_layernorm.weight
                                                                  
[0258/0405] saving model.layers.15.self_attn.o_proj.q_weight
                                                                  
[0259/0405] saving model.layers.15.self_attn.o_proj.q_scale
                                                                  
[0260/0405] saving model.layers.16.input_layernorm.weight
                                                                  
[0261/0405] saving model.layers.16.mlp.down_proj.q_weight
                                                                  
[0262/0405] saving model.layers.16.mlp.down_proj.q_scale
                                                                  
[0263/0405] saving model.layers.16.mlp.gate_up_proj.q_weight
                                                                  
[0264/0405] saving model.layers.16.mlp.gate_up_proj.q_scale
                                                                  
[0265/0405] saving model.layers.16.post_attention_layernorm.weight
                                                                  
[0266/0405] saving model.layers.16.self_attn.qkv_proj.q_weight
                                                                  
[0267/0405] saving model.layers.16.self_attn.qkv_proj.q_scale
                                                                  
[0268/0405] saving model.layers.16.self_attn.o_proj.q_weight
                                                                  
[0269/0405] saving model.layers.16.self_attn.o_proj.q_scale
                                                                  
[0270/0405] saving model.layers.17.input_layernorm.weight
                                                                  
[0271/0405] saving model.layers.17.mlp.down_proj.q_weight
                                                                  
[0272/0405] saving model.layers.17.mlp.down_proj.q_scale
                                                                  
[0273/0405] saving model.layers.17.mlp.gate_up_proj.q_weight
                                                                  
[0274/0405] saving model.layers.17.mlp.gate_up_proj.q_scale
                                                                  
[0275/0405] saving model.layers.17.post_attention_layernorm.weight
                                                                  
[0276/0405] saving model.layers.17.self_attn.qkv_proj.q_weight
                                                                  
[0277/0405] saving model.layers.17.self_attn.qkv_proj.q_scale
                                                                  
[0278/0405] saving model.layers.17.self_attn.o_proj.q_weight
                                                                  
[0279/0405] saving model.layers.17.self_attn.o_proj.q_scale
                                                                  
[0280/0405] saving model.layers.18.input_layernorm.weight
                                                                  
[0281/0405] saving model.layers.18.mlp.down_proj.q_weight
                                                                  
[0282/0405] saving model.layers.18.mlp.down_proj.q_scale
                                                                  
[0283/0405] saving model.layers.18.mlp.gate_up_proj.q_weight
                                                                  
[0284/0405] saving model.layers.18.mlp.gate_up_proj.q_scale
                                                                  
[0285/0405] saving model.layers.18.post_attention_layernorm.weight
                                                                  
[0286/0405] saving model.layers.18.self_attn.qkv_proj.q_weight
                                                                  
[0287/0405] saving model.layers.18.self_attn.qkv_proj.q_scale
                                                                  
[0288/0405] saving model.layers.18.self_attn.o_proj.q_weight
                                                                  
[0289/0405] saving model.layers.18.self_attn.o_proj.q_scale
                                                                  
[0290/0405] saving model.layers.19.input_layernorm.weight
                                                                  
[0291/0405] saving model.layers.19.mlp.down_proj.q_weight
                                                                  
[0292/0405] saving model.layers.19.mlp.down_proj.q_scale
                                                                  
[0293/0405] saving model.layers.19.mlp.gate_up_proj.q_weight
                                                                  
[0294/0405] saving model.layers.19.mlp.gate_up_proj.q_scale
                                                                  
[0295/0405] saving model.layers.19.post_attention_layernorm.weight
                                                                  
[0296/0405] saving model.layers.19.self_attn.qkv_proj.q_weight
                                                                  
[0297/0405] saving model.layers.19.self_attn.qkv_proj.q_scale
                                                                  
[0298/0405] saving model.layers.19.self_attn.o_proj.q_weight
                                                                  
[0299/0405] saving model.layers.19.self_attn.o_proj.q_scale
                                                                  
[0300/0405] saving model.layers.20.input_layernorm.weight
                                                                  
[0301/0405] saving model.layers.20.mlp.down_proj.q_weight
                                                                  
[0302/0405] saving model.layers.20.mlp.down_proj.q_scale
                                                                  
[0303/0405] saving model.layers.20.mlp.gate_up_proj.q_weight
                                                                  
[0304/0405] saving model.layers.20.mlp.gate_up_proj.q_scale
                                                                  
[0305/0405] saving model.layers.20.post_attention_layernorm.weight
                                                                  
[0306/0405] saving model.layers.20.self_attn.qkv_proj.q_weight
                                                                  
[0307/0405] saving model.layers.20.self_attn.qkv_proj.q_scale
                                                                  
[0308/0405] saving model.layers.20.self_attn.o_proj.q_weight
                                                                  
[0309/0405] saving model.layers.20.self_attn.o_proj.q_scale
                                                                  
[0310/0405] saving model.layers.21.input_layernorm.weight
                                                                  
[0311/0405] saving model.layers.21.mlp.down_proj.q_weight
                                                                  
[0312/0405] saving model.layers.21.mlp.down_proj.q_scale
                                                                  
[0313/0405] saving model.layers.21.mlp.gate_up_proj.q_weight
                                                                  
[0314/0405] saving model.layers.21.mlp.gate_up_proj.q_scale
                                                                  
[0315/0405] saving model.layers.21.post_attention_layernorm.weight
                                                                  
[0316/0405] saving model.layers.21.self_attn.qkv_proj.q_weight
                                                                  
[0317/0405] saving model.layers.21.self_attn.qkv_proj.q_scale
                                                                  
[0318/0405] saving model.layers.21.self_attn.o_proj.q_weight
                                                                  
[0319/0405] saving model.layers.21.self_attn.o_proj.q_scale
                                                                  
[0320/0405] saving model.layers.22.input_layernorm.weight
                                                                  
[0321/0405] saving model.layers.22.mlp.down_proj.q_weight
                                                                  
[0322/0405] saving model.layers.22.mlp.down_proj.q_scale
                                                                  
[0323/0405] saving model.layers.22.mlp.gate_up_proj.q_weight
                                                                  
[0324/0405] saving model.layers.22.mlp.gate_up_proj.q_scale
                                                                  
[0325/0405] saving model.layers.22.post_attention_layernorm.weight
                                                                  
[0326/0405] saving model.layers.22.self_attn.qkv_proj.q_weight
                                                                  
[0327/0405] saving model.layers.22.self_attn.qkv_proj.q_scale
                                                                  
[0328/0405] saving model.layers.22.self_attn.o_proj.q_weight
                                                                  
[0329/0405] saving model.layers.22.self_attn.o_proj.q_scale
                                                                  
[0330/0405] saving model.layers.23.input_layernorm.weight
                                                                  
[0331/0405] saving model.layers.23.mlp.down_proj.q_weight
                                                                  
[0332/0405] saving model.layers.23.mlp.down_proj.q_scale
                                                                  
[0333/0405] saving model.layers.23.mlp.gate_up_proj.q_weight
                                                                  
[0334/0405] saving model.layers.23.mlp.gate_up_proj.q_scale
                                                                  
[0335/0405] saving model.layers.23.post_attention_layernorm.weight
                                                                  
[0336/0405] saving model.layers.23.self_attn.qkv_proj.q_weight
                                                                  
[0337/0405] saving model.layers.23.self_attn.qkv_proj.q_scale
                                                                  
[0338/0405] saving model.layers.23.self_attn.o_proj.q_weight
                                                                  
[0339/0405] saving model.layers.23.self_attn.o_proj.q_scale
                                                                  
[0340/0405] saving model.layers.24.input_layernorm.weight
                                                                  
[0341/0405] saving model.layers.24.mlp.down_proj.q_weight
                                                                  
[0342/0405] saving model.layers.24.mlp.down_proj.q_scale
                                                                  
[0343/0405] saving model.layers.24.mlp.gate_up_proj.q_weight
                                                                  
[0344/0405] saving model.layers.24.mlp.gate_up_proj.q_scale
                                                                  
[0345/0405] saving model.layers.24.post_attention_layernorm.weight
                                                                  
[0346/0405] saving model.layers.24.self_attn.qkv_proj.q_weight
                                                                  
[0347/0405] saving model.layers.24.self_attn.qkv_proj.q_scale
                                                                  
[0348/0405] saving model.layers.24.self_attn.o_proj.q_weight
                                                                  
[0349/0405] saving model.layers.24.self_attn.o_proj.q_scale
                                                                  
[0350/0405] saving model.layers.25.input_layernorm.weight
                                                                  
[0351/0405] saving model.layers.25.mlp.down_proj.q_weight
                                                                  
[0352/0405] saving model.layers.25.mlp.down_proj.q_scale
                                                                  
[0353/0405] saving model.layers.25.mlp.gate_up_proj.q_weight
                                                                  
[0354/0405] saving model.layers.25.mlp.gate_up_proj.q_scale
                                                                  
[0355/0405] saving model.layers.25.post_attention_layernorm.weight
                                                                  
[0356/0405] saving model.layers.25.self_attn.qkv_proj.q_weight
                                                                  
[0357/0405] saving model.layers.25.self_attn.qkv_proj.q_scale
                                                                  
[0358/0405] saving model.layers.25.self_attn.o_proj.q_weight
                                                                  
[0359/0405] saving model.layers.25.self_attn.o_proj.q_scale
                                                                  
[0360/0405] saving model.layers.26.input_layernorm.weight
                                                                  
[0361/0405] saving model.layers.26.mlp.down_proj.q_weight
                                                                  
[0362/0405] saving model.layers.26.mlp.down_proj.q_scale
                                                                  
[0363/0405] saving model.layers.26.mlp.gate_up_proj.q_weight
                                                                  
[0364/0405] saving model.layers.26.mlp.gate_up_proj.q_scale
                                                                  
[0365/0405] saving model.layers.26.post_attention_layernorm.weight
                                                                  
[0366/0405] saving model.layers.26.self_attn.qkv_proj.q_weight
                                                                  
[0367/0405] saving model.layers.26.self_attn.qkv_proj.q_scale
                                                                  
[0368/0405] saving model.layers.26.self_attn.o_proj.q_weight
                                                                  
[0369/0405] saving model.layers.26.self_attn.o_proj.q_scale
                                                                  
[0370/0405] saving model.layers.27.input_layernorm.weight
                                                                  
[0371/0405] saving model.layers.27.mlp.down_proj.q_weight
                                                                  
[0372/0405] saving model.layers.27.mlp.down_proj.q_scale
                                                                  
[0373/0405] saving model.layers.27.mlp.gate_up_proj.q_weight
                                                                  
[0374/0405] saving model.layers.27.mlp.gate_up_proj.q_scale
                                                                  
[0375/0405] saving model.layers.27.post_attention_layernorm.weight
                                                                  
[0376/0405] saving model.layers.27.self_attn.qkv_proj.q_weight
                                                                  
[0377/0405] saving model.layers.27.self_attn.qkv_proj.q_scale
                                                                  
[0378/0405] saving model.layers.27.self_attn.o_proj.q_weight
                                                                  
[0379/0405] saving model.layers.27.self_attn.o_proj.q_scale
                                                                  
[0380/0405] saving model.layers.28.input_layernorm.weight
                                                                  
[0381/0405] saving model.layers.28.mlp.down_proj.q_weight
                                                                  
[0382/0405] saving model.layers.28.mlp.down_proj.q_scale
                                                                  
[0383/0405] saving model.layers.28.mlp.gate_up_proj.q_weight
                                                                  
[0384/0405] saving model.layers.28.mlp.gate_up_proj.q_scale
                                                                  
[0385/0405] saving model.layers.28.post_attention_layernorm.weight[2024-01-30 00:52:56] INFO convert_weight.py:143: Saved to directory: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y
+
                                                                  
[0386/0405] saving model.layers.28.self_attn.qkv_proj.q_weight
                                                                  
[0387/0405] saving model.layers.28.self_attn.qkv_proj.q_scale
                                                                  
[0388/0405] saving model.layers.28.self_attn.o_proj.q_weight
                                                                  
[0389/0405] saving model.layers.28.self_attn.o_proj.q_scale
                                                                  
[0390/0405] saving model.layers.29.input_layernorm.weight
                                                                  
[0391/0405] saving model.layers.29.mlp.down_proj.q_weight
                                                                  
[0392/0405] saving model.layers.29.mlp.down_proj.q_scale
                                                                  
[0393/0405] saving model.layers.29.mlp.gate_up_proj.q_weight
                                                                  
[0394/0405] saving model.layers.29.mlp.gate_up_proj.q_scale
                                                                  
[0395/0405] saving model.layers.29.post_attention_layernorm.weight
                                                                  
[0396/0405] saving model.layers.29.self_attn.qkv_proj.q_weight
                                                                  
[0397/0405] saving model.layers.29.self_attn.qkv_proj.q_scale
                                                                  
[0398/0405] saving model.layers.29.self_attn.o_proj.q_weight
                                                                  
[0399/0405] saving model.layers.29.self_attn.o_proj.q_scale
                                                                  
[0400/0405] saving model.layers.30.mlp.gate_up_proj.q_weight
                                                                  
[0401/0405] saving model.layers.30.mlp.gate_up_proj.q_scale
                                                                  
[0402/0405] saving model.layers.30.self_attn.qkv_proj.q_weight
                                                                  
[0403/0405] saving model.layers.30.self_attn.qkv_proj.q_scale
                                                                  
[0404/0405] saving model.layers.30.self_attn.o_proj.q_weight
                                                                  
[0405/0405] saving model.layers.30.self_attn.o_proj.q_scale
+All finished, 163 total shards committed, record saved to /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmphvh7e60y/ndarray-cache.json