diff --git "a/logs.txt" "b/logs.txt"
new file mode 100644--- /dev/null
+++ "b/logs.txt"
@@ -0,0 +1,561 @@
+/Users/cfruan/miniconda3/envs/mlc-chat-venv/bin/python -m mlc_chat gen_config /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo --quantization q4f16_1 --conv-template codellama_instruct --output /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpukse82wg --context-window-size 16384
+[2024-01-30 01:54:21] INFO auto_config.py:115: Found model configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/config.json
+[2024-01-30 01:54:21] INFO auto_config.py:153: Found model type: llama. Use `--model-type` to override.
+[2024-01-30 01:54:21] INFO llama_model.py:51: context_window_size not found in config.json. Falling back to max_position_embeddings (16384)
+[2024-01-30 01:54:21] INFO llama_model.py:71: prefill_chunk_size defaults to context_window_size (16384)
+[2024-01-30 01:54:21] INFO config.py:106: Overriding context_window_size from 16384 to 16384
+[2024-01-30 01:54:21] INFO config.py:106: Overriding max_batch_size from 1 to 80
+[2024-01-30 01:54:21] INFO gen_config.py:116: [generation_config.json] Setting bos_token_id: 1
+[2024-01-30 01:54:21] INFO gen_config.py:116: [generation_config.json] Setting eos_token_id: 2
+[2024-01-30 01:54:21] INFO gen_config.py:128: Found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/tokenizer.model. Copying to /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpukse82wg/tokenizer.model
+[2024-01-30 01:54:21] INFO gen_config.py:128: Found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/tokenizer.json. Copying to /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpukse82wg/tokenizer.json
+[2024-01-30 01:54:21] INFO gen_config.py:130: Not found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/vocab.json
+[2024-01-30 01:54:21] INFO gen_config.py:130: Not found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/merges.txt
+[2024-01-30 01:54:21] INFO gen_config.py:130: Not found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/added_tokens.json
+[2024-01-30 01:54:21] INFO gen_config.py:128: Found tokenizer config: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/tokenizer_config.json. Copying to /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpukse82wg/tokenizer_config.json
+[2024-01-30 01:54:21] INFO gen_config.py:69: [System default] Setting pad_token_id: 0
+[2024-01-30 01:54:21] INFO gen_config.py:69: [System default] Setting temperature: 0.7
+[2024-01-30 01:54:21] INFO gen_config.py:69: [System default] Setting repetition_penalty: 1.0
+[2024-01-30 01:54:21] INFO gen_config.py:69: [System default] Setting top_p: 0.95
+[2024-01-30 01:54:21] INFO gen_config.py:69: [System default] Setting mean_gen_len: 128
+[2024-01-30 01:54:21] INFO gen_config.py:69: [System default] Setting max_gen_len: 512
+[2024-01-30 01:54:21] INFO gen_config.py:69: [System default] Setting shift_fill_factor: 0.3
+[2024-01-30 01:54:21] INFO gen_config.py:158: Dumping configuration file to: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpukse82wg/mlc-chat-config.json
+/Users/cfruan/miniconda3/envs/mlc-chat-venv/bin/python -m mlc_chat convert_weight /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo --quantization q4f16_1 --source-format auto --output /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpukse82wg
+[2024-01-30 01:54:21] INFO auto_config.py:115: Found model configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/config.json
+[2024-01-30 01:54:22] INFO auto_device.py:85: Not found device: cuda:0
+[2024-01-30 01:54:22] INFO auto_device.py:85: Not found device: rocm:0
+[2024-01-30 01:54:22] INFO auto_device.py:76: Found device: metal:0
+[2024-01-30 01:54:23] INFO auto_device.py:85: Not found device: vulkan:0
+[2024-01-30 01:54:23] INFO auto_device.py:85: Not found device: opencl:0
+[2024-01-30 01:54:23] INFO auto_device.py:33: Using device: metal:0
+[2024-01-30 01:54:23] INFO auto_weight.py:70: Finding weights in: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo
+[2024-01-30 01:54:23] INFO auto_weight.py:120: Found source weight format: huggingface-torch. Source configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/pytorch_model.bin.index.json
+[2024-01-30 01:54:23] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/model.safetensors.index.json
+[2024-01-30 01:54:23] INFO auto_weight.py:106: Using source weight configuration: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/pytorch_model.bin.index.json. Use `--source` to override.
+[2024-01-30 01:54:23] INFO auto_weight.py:110: Using source weight format: huggingface-torch. Use `--source-format` to override.
+[2024-01-30 01:54:23] INFO auto_config.py:153: Found model type: llama. Use `--model-type` to override.
+[2024-01-30 01:54:23] INFO llama_model.py:51: context_window_size not found in config.json. Falling back to max_position_embeddings (16384)
+[2024-01-30 01:54:23] INFO llama_model.py:71: prefill_chunk_size defaults to context_window_size (16384)
+Weight conversion with arguments:
+  --config          /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/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/tmp5j_y6e9a/repo/pytorch_model.bin.index.json
+  --source-format   huggingface-torch
+  --output          /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpukse82wg
+
  0%|                                                                                                                    | 0/291 [00:00<?, ?it/s]
                                                                                                                                                 
[2024-01-30 01:54:28] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/pytorch_model-00007-of-00007.bin
+
  0%|                                                                                                                    | 0/291 [00:00<?, ?it/s]
                                                                                                                                                 
[2024-01-30 01:54:33] INFO group_quantization.py:227: Compiling quantize function for key: ((32000, 8192), float16, metal, axis=1, output_transpose=False)
+
  0%|                                                                                                                    | 0/291 [00:04<?, ?it/s]
                                                                                                                                                 
[2024-01-30 01:54:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "lm_head.q_weight", shape: (32000, 1024), dtype: uint32
+
  0%|                                                                                                                    | 0/291 [00:04<?, ?it/s]
                                                                                                                                                 
[2024-01-30 01:54:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "lm_head.q_scale", shape: (32000, 256), dtype: float16
+
  0%|                                                                                                                    | 0/291 [00:04<?, ?it/s]
  0%|▎                                                                                                           | 1/291 [00:04<24:07,  4.99s/it]
                                                                                                                                                 
[2024-01-30 01:54:33] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.41.input_layernorm.weight", shape: (8192,), dtype: float16
+
  0%|▎                                                                                                           | 1/291 [00:04<24:07,  4.99s/it]
                                                                                                                                                 
[2024-01-30 01:54:34] INFO group_quantization.py:227: Compiling quantize function for key: ((8192, 22016), float16, metal, axis=1, output_transpose=False)
+
  0%|▎                                                                                                           | 1/291 [00:05<24:07,  4.99s/it]
                                                                                                                                                 
[2024-01-30 01:54:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.41.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
  0%|▎                                                                                                           | 1/291 [00:05<24:07,  4.99s/it]
                                                                                                                                                 
[2024-01-30 01:54:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.41.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
  0%|▎                                                                                                           | 1/291 [00:05<24:07,  4.99s/it]
  1%|█                                                                                                           | 3/291 [00:05<07:12,  1.50s/it]
                                                                                                                                                 
[2024-01-30 01:54:34] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.41.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
  1%|█                                                                                                           | 3/291 [00:05<07:12,  1.50s/it]
                                                                                                                                                 
[2024-01-30 01:54:34] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.42.input_layernorm.weight", shape: (8192,), dtype: float16
+
  1%|█                                                                                                           | 3/291 [00:05<07:12,  1.50s/it]
                                                                                                                                                 
[2024-01-30 01:54:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.42.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
  1%|█                                                                                                           | 3/291 [00:06<07:12,  1.50s/it]
                                                                                                                                                 
[2024-01-30 01:54:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.42.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
  1%|█                                                                                                           | 3/291 [00:06<07:12,  1.50s/it]
  2%|██▏                                                                                                         | 6/291 [00:06<03:14,  1.47it/s]
                                                                                                                                                 
[2024-01-30 01:54:36] INFO group_quantization.py:227: Compiling quantize function for key: ((44032, 8192), float16, metal, axis=1, output_transpose=False)
+
  2%|██▏                                                                                                         | 6/291 [00:07<03:14,  1.47it/s]
                                                                                                                                                 
[2024-01-30 01:54:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.42.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
  2%|██▏                                                                                                         | 6/291 [00:07<03:14,  1.47it/s]
                                                                                                                                                 
[2024-01-30 01:54:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.42.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
  2%|██▏                                                                                                         | 6/291 [00:07<03:14,  1.47it/s]
  2%|██▌                                                                                                         | 7/291 [00:07<03:52,  1.22it/s]
                                                                                                                                                 
[2024-01-30 01:54:36] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.42.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
  2%|██▌                                                                                                         | 7/291 [00:07<03:52,  1.22it/s]
                                                                                                                                                 
[2024-01-30 01:54:36] INFO group_quantization.py:227: Compiling quantize function for key: ((10240, 8192), float16, metal, axis=1, output_transpose=False)
+
  2%|██▌                                                                                                         | 7/291 [00:07<03:52,  1.22it/s]
                                                                                                                                                 
[2024-01-30 01:54:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.42.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
  2%|██▌                                                                                                         | 7/291 [00:07<03:52,  1.22it/s]
                                                                                                                                                 
[2024-01-30 01:54:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.42.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
  2%|██▌                                                                                                         | 7/291 [00:07<03:52,  1.22it/s]
  3%|███▎                                                                                                        | 9/291 [00:07<02:38,  1.78it/s]
                                                                                                                                                 
[2024-01-30 01:54:36] INFO group_quantization.py:227: Compiling quantize function for key: ((8192, 8192), float16, metal, axis=1, output_transpose=False)
+
  3%|███▎                                                                                                        | 9/291 [00:07<02:38,  1.78it/s]
                                                                                                                                                 
[2024-01-30 01:54:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.42.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
  3%|███▎                                                                                                        | 9/291 [00:07<02:38,  1.78it/s]
                                                                                                                                                 
[2024-01-30 01:54:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.42.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
  3%|███▎                                                                                                        | 9/291 [00:07<02:38,  1.78it/s]
  3%|███▋                                                                                                       | 10/291 [00:07<02:17,  2.04it/s]
                                                                                                                                                 
[2024-01-30 01:54:36] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.43.input_layernorm.weight", shape: (8192,), dtype: float16
+
  3%|███▋                                                                                                       | 10/291 [00:07<02:17,  2.04it/s]
                                                                                                                                                 
[2024-01-30 01:54:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.43.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
  3%|███▋                                                                                                       | 10/291 [00:08<02:17,  2.04it/s]
                                                                                                                                                 
[2024-01-30 01:54:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.43.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
  3%|███▋                                                                                                       | 10/291 [00:08<02:17,  2.04it/s]
  4%|████▍                                                                                                      | 12/291 [00:08<01:50,  2.53it/s]
                                                                                                                                                 
[2024-01-30 01:54:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.43.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
  4%|████▍                                                                                                      | 12/291 [00:09<01:50,  2.53it/s]
                                                                                                                                                 
[2024-01-30 01:54:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.43.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
  4%|████▍                                                                                                      | 12/291 [00:09<01:50,  2.53it/s]
  4%|████▊                                                                                                      | 13/291 [00:09<02:34,  1.80it/s]
                                                                                                                                                 
[2024-01-30 01:54:38] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.43.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
  4%|████▊                                                                                                      | 13/291 [00:09<02:34,  1.80it/s]
                                                                                                                                                 
[2024-01-30 01:54:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.43.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
  4%|████▊                                                                                                      | 13/291 [00:09<02:34,  1.80it/s]
                                                                                                                                                 
[2024-01-30 01:54:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.43.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
  4%|████▊                                                                                                      | 13/291 [00:09<02:34,  1.80it/s]
  5%|█████▌                                                                                                     | 15/291 [00:09<01:49,  2.52it/s]
                                                                                                                                                 
[2024-01-30 01:54:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.43.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
  5%|█████▌                                                                                                     | 15/291 [00:09<01:49,  2.52it/s]
                                                                                                                                                 
[2024-01-30 01:54:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.43.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
  5%|█████▌                                                                                                     | 15/291 [00:09<01:49,  2.52it/s]
  5%|█████▉                                                                                                     | 16/291 [00:09<01:36,  2.84it/s]
                                                                                                                                                 
[2024-01-30 01:54:38] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.44.input_layernorm.weight", shape: (8192,), dtype: float16
+
  5%|█████▉                                                                                                     | 16/291 [00:09<01:36,  2.84it/s]
                                                                                                                                                 
[2024-01-30 01:54:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.44.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
  5%|█████▉                                                                                                     | 16/291 [00:10<01:36,  2.84it/s]
                                                                                                                                                 
[2024-01-30 01:54:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.44.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
  5%|█████▉                                                                                                     | 16/291 [00:10<01:36,  2.84it/s]
  6%|██████▌                                                                                                    | 18/291 [00:10<01:24,  3.22it/s]
                                                                                                                                                 
[2024-01-30 01:54:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.44.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
  6%|██████▌                                                                                                    | 18/291 [00:11<01:24,  3.22it/s]
                                                                                                                                                 
[2024-01-30 01:54:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.44.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
  6%|██████▌                                                                                                    | 18/291 [00:11<01:24,  3.22it/s]
  7%|██████▉                                                                                                    | 19/291 [00:11<02:15,  2.01it/s]
                                                                                                                                                 
[2024-01-30 01:54:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.44.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
  7%|██████▉                                                                                                    | 19/291 [00:11<02:15,  2.01it/s]
                                                                                                                                                 
[2024-01-30 01:54:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.44.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
  7%|██████▉                                                                                                    | 19/291 [00:11<02:15,  2.01it/s]
                                                                                                                                                 
[2024-01-30 01:54:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.44.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
  7%|██████▉                                                                                                    | 19/291 [00:11<02:15,  2.01it/s]
  7%|███████▋                                                                                                   | 21/291 [00:11<01:37,  2.78it/s]
                                                                                                                                                 
[2024-01-30 01:54:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.44.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
  7%|███████▋                                                                                                   | 21/291 [00:12<01:37,  2.78it/s]
                                                                                                                                                 
[2024-01-30 01:54:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.44.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
  7%|███████▋                                                                                                   | 21/291 [00:12<01:37,  2.78it/s]
  8%|████████                                                                                                   | 22/291 [00:12<01:26,  3.10it/s]
                                                                                                                                                 
[2024-01-30 01:54:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.45.input_layernorm.weight", shape: (8192,), dtype: float16
+
  8%|████████                                                                                                   | 22/291 [00:12<01:26,  3.10it/s]
                                                                                                                                                 
[2024-01-30 01:54:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.45.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
  8%|████████                                                                                                   | 22/291 [00:12<01:26,  3.10it/s]
                                                                                                                                                 
[2024-01-30 01:54:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.45.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
  8%|████████                                                                                                   | 22/291 [00:12<01:26,  3.10it/s]
  8%|████████▊                                                                                                  | 24/291 [00:12<01:18,  3.41it/s]
                                                                                                                                                 
[2024-01-30 01:54:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.45.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
  8%|████████▊                                                                                                  | 24/291 [00:13<01:18,  3.41it/s]
                                                                                                                                                 
[2024-01-30 01:54:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.45.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
  8%|████████▊                                                                                                  | 24/291 [00:13<01:18,  3.41it/s]
  9%|█████████▏                                                                                                 | 25/291 [00:13<02:08,  2.07it/s]
                                                                                                                                                 
[2024-01-30 01:54:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.45.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
  9%|█████████▏                                                                                                 | 25/291 [00:13<02:08,  2.07it/s]
                                                                                                                                                 
[2024-01-30 01:54:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.45.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
  9%|█████████▏                                                                                                 | 25/291 [00:14<02:08,  2.07it/s]
                                                                                                                                                 
[2024-01-30 01:54:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.45.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
  9%|█████████▏                                                                                                 | 25/291 [00:14<02:08,  2.07it/s]
  9%|█████████▉                                                                                                 | 27/291 [00:14<01:32,  2.85it/s]
                                                                                                                                                 
[2024-01-30 01:54:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.45.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
  9%|█████████▉                                                                                                 | 27/291 [00:14<01:32,  2.85it/s]
                                                                                                                                                 
[2024-01-30 01:54:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.45.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
  9%|█████████▉                                                                                                 | 27/291 [00:14<01:32,  2.85it/s]
 10%|██████████▎                                                                                                | 28/291 [00:14<01:22,  3.17it/s]
                                                                                                                                                 
[2024-01-30 01:54:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.46.input_layernorm.weight", shape: (8192,), dtype: float16
+
 10%|██████████▎                                                                                                | 28/291 [00:14<01:22,  3.17it/s]
                                                                                                                                                 
[2024-01-30 01:54:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.46.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 10%|██████████▎                                                                                                | 28/291 [00:14<01:22,  3.17it/s]
                                                                                                                                                 
[2024-01-30 01:54:43] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.46.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 10%|██████████▎                                                                                                | 28/291 [00:14<01:22,  3.17it/s]
 10%|███████████                                                                                                | 30/291 [00:14<01:15,  3.46it/s]
                                                                                                                                                 
[2024-01-30 01:54:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.46.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 10%|███████████                                                                                                | 30/291 [00:15<01:15,  3.46it/s]
                                                                                                                                                 
[2024-01-30 01:54:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.46.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 10%|███████████                                                                                                | 30/291 [00:15<01:15,  3.46it/s]
 11%|███████████▍                                                                                               | 31/291 [00:15<02:04,  2.08it/s]
                                                                                                                                                 
[2024-01-30 01:54:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.46.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 11%|███████████▍                                                                                               | 31/291 [00:15<02:04,  2.08it/s]
                                                                                                                                                 
[2024-01-30 01:54:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.46.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 11%|███████████▍                                                                                               | 31/291 [00:16<02:04,  2.08it/s]
                                                                                                                                                 
[2024-01-30 01:54:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.46.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 11%|███████████▍                                                                                               | 31/291 [00:16<02:04,  2.08it/s]
 11%|████████████▏                                                                                              | 33/291 [00:16<01:30,  2.84it/s]
                                                                                                                                                 
[2024-01-30 01:54:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.46.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 11%|████████████▏                                                                                              | 33/291 [00:16<01:30,  2.84it/s]
                                                                                                                                                 
[2024-01-30 01:54:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.46.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 11%|████████████▏                                                                                              | 33/291 [00:16<01:30,  2.84it/s]
 12%|████████████▌                                                                                              | 34/291 [00:16<01:21,  3.16it/s]
                                                                                                                                                 
[2024-01-30 01:54:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.47.input_layernorm.weight", shape: (8192,), dtype: float16
+
 12%|████████████▌                                                                                              | 34/291 [00:16<01:21,  3.16it/s]
                                                                                                                                                 
[2024-01-30 01:54:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.47.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 12%|████████████▌                                                                                              | 34/291 [00:16<01:21,  3.16it/s]
                                                                                                                                                 
[2024-01-30 01:54:45] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.47.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 12%|████████████▌                                                                                              | 34/291 [00:16<01:21,  3.16it/s]
 12%|█████████████▏                                                                                             | 36/291 [00:16<01:13,  3.45it/s]
                                                                                                                                                 
[2024-01-30 01:54:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.47.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 12%|█████████████▏                                                                                             | 36/291 [00:18<01:13,  3.45it/s]
                                                                                                                                                 
[2024-01-30 01:54:46] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.47.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 12%|█████████████▏                                                                                             | 36/291 [00:18<01:13,  3.45it/s]
 13%|█████████████▌                                                                                             | 37/291 [00:18<02:04,  2.04it/s]
                                                                                                                                                 
[2024-01-30 01:54:46] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.47.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 13%|█████████████▌                                                                                             | 37/291 [00:18<02:04,  2.04it/s]
                                                                                                                                                 
[2024-01-30 01:54:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.47.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 13%|█████████████▌                                                                                             | 37/291 [00:18<02:04,  2.04it/s]
                                                                                                                                                 
[2024-01-30 01:54:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.47.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 13%|█████████████▌                                                                                             | 37/291 [00:18<02:04,  2.04it/s]
 13%|██████████████▎                                                                                            | 39/291 [00:18<01:29,  2.82it/s]
                                                                                                                                                 
[2024-01-30 01:54:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.47.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 13%|██████████████▎                                                                                            | 39/291 [00:18<01:29,  2.82it/s]
                                                                                                                                                 
[2024-01-30 01:54:47] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.47.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 13%|██████████████▎                                                                                            | 39/291 [00:18<01:29,  2.82it/s]
 14%|██████████████▋                                                                                            | 40/291 [00:18<01:20,  3.13it/s]
                                                                                                                                                 
[2024-01-30 01:54:47] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.norm.weight", shape: (8192,), dtype: float16
+
 14%|██████████████▋                                                                                            | 40/291 [00:18<01:20,  3.13it/s]
                                                                                                                                                 
[2024-01-30 01:54:47] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/pytorch_model-00007-of-00007.bin
+
 14%|██████████████▋                                                                                            | 40/291 [00:18<01:20,  3.13it/s]
                                                                                                                                                 
[2024-01-30 01:54:47] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/pytorch_model-00001-of-00007.bin
+
 14%|███████████��██▋                                                                                            | 40/291 [00:18<01:20,  3.13it/s]
                                                                                                                                                 
[2024-01-30 01:54:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (32000, 1024), dtype: uint32
+
 14%|██████████████▋                                                                                            | 40/291 [00:22<01:20,  3.13it/s]
                                                                                                                                                 
[2024-01-30 01:54:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (32000, 256), dtype: float16
+
 14%|██████████████▋                                                                                            | 40/291 [00:22<01:20,  3.13it/s]
 14%|███████████████▍                                                                                           | 42/291 [00:22<04:00,  1.03it/s]
                                                                                                                                                 
[2024-01-30 01:54:51] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (8192,), dtype: float16
+
 14%|███████████████▍                                                                                           | 42/291 [00:22<04:00,  1.03it/s]
                                                                                                                                                 
[2024-01-30 01:54:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 14%|███████████████▍                                                                                           | 42/291 [00:23<04:00,  1.03it/s]
                                                                                                                                                 
[2024-01-30 01:54:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 14%|███████████████▍                                                                                           | 42/291 [00:23<04:00,  1.03it/s]
 15%|████████████████▏                                                                                          | 44/291 [00:23<02:56,  1.40it/s]
                                                                                                                                                 
[2024-01-30 01:54:53] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 15%|████████████████▏                                                                                          | 44/291 [00:24<02:56,  1.40it/s]
                                                                                                                                                 
[2024-01-30 01:54:53] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 15%|████████████████▏                                                                                          | 44/291 [00:24<02:56,  1.40it/s]
 15%|████████████████▌                                                                                          | 45/291 [00:24<03:23,  1.21it/s]
                                                                                                                                                 
[2024-01-30 01:54:53] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 15%|████████████████▌                                                                                          | 45/291 [00:24<03:23,  1.21it/s]
                                                                                                                                                 
[2024-01-30 01:54:53] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 15%|████████████████▌                                                                                          | 45/291 [00:24<03:23,  1.21it/s]
                                                                                                                                                 
[2024-01-30 01:54:53] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 15%|████████████████▌                                                                                          | 45/291 [00:24<03:23,  1.21it/s]
 16%|█████████████████▎                                                                                         | 47/291 [00:24<02:20,  1.74it/s]
                                                                                                                                                 
[2024-01-30 01:54:53] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 16%|█████████████████▎                                                                                         | 47/291 [00:24<02:20,  1.74it/s]
                                                                                                                                                 
[2024-01-30 01:54:53] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 16%|█████████████████▎                                                                                         | 47/291 [00:24<02:20,  1.74it/s]
 16%|█████████████████▋                                                                                         | 48/291 [00:24<02:00,  2.02it/s]
                                                                                                                                                 
[2024-01-30 01:54:53] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (8192,), dtype: float16
+
 16%|█████████████████▋                                                                                         | 48/291 [00:24<02:00,  2.02it/s]
                                                                                                                                                 
[2024-01-30 01:54:54] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 16%|█████████████████▋                                                                                         | 48/291 [00:25<02:00,  2.02it/s]
                                                                                                                                                 
[2024-01-30 01:54:54] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 16%|█████████████████▋                                                                                         | 48/291 [00:25<02:00,  2.02it/s]
 17%|██████████████████▍                                                                                        | 50/291 [00:25<01:37,  2.48it/s]
                                                                                                                                                 
[2024-01-30 01:54:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 17%|██████████████████▍                                                                                        | 50/291 [00:26<01:37,  2.48it/s]
                                                                                                                                                 
[2024-01-30 01:54:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 17%|██████████████████▍                                                                                        | 50/291 [00:26<01:37,  2.48it/s]
 18%|██████████████████▊                                                                                        | 51/291 [00:26<02:17,  1.75it/s]
                                                                                                                                                 
[2024-01-30 01:54:55] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 18%|██████████████████▊                                                                                        | 51/291 [00:26<02:17,  1.75it/s]
                                                                                                                                                 
[2024-01-30 01:54:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 18%|██████████████████▊                                                                                        | 51/291 [00:26<02:17,  1.75it/s]
                                                                                                                                                 
[2024-01-30 01:54:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 18%|██████████████████▊                                                                                        | 51/291 [00:26<02:17,  1.75it/s]
 18%|███████████████████▍                                                                                       | 53/291 [00:26<01:36,  2.46it/s]
                                                                                                                                                 
[2024-01-30 01:54:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 18%|███████████████████▍                                                                                       | 53/291 [00:27<01:36,  2.46it/s]
                                                                                                                                                 
[2024-01-30 01:54:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 18%|███████████████████▍                                                                                       | 53/291 [00:27<01:36,  2.46it/s]
 19%|███████████████████▊                                                                                       | 54/291 [00:27<01:25,  2.77it/s]
                                                                                                                                                 
[2024-01-30 01:54:55] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (8192,), dtype: float16
+
 19%|███████████████████▊                                                                                       | 54/291 [00:27<01:25,  2.77it/s]
                                                                                                                                                 
[2024-01-30 01:54:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 19%|███████████████████▊                                                                                       | 54/291 [00:27<01:25,  2.77it/s]
                                                                                                                                                 
[2024-01-30 01:54:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 19%|███████████████████▊                                                                                       | 54/291 [00:27<01:25,  2.77it/s]
 19%|████████████████████▌                                                                                      | 56/291 [00:27<01:14,  3.13it/s]
                                                                                                                                                 
[2024-01-30 01:54:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 19%|████████████████████▌                                                                                      | 56/291 [00:28<01:14,  3.13it/s]
                                                                                                                                                 
[2024-01-30 01:54:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 19%|████████████████████▌                                                                                      | 56/291 [00:28<01:14,  3.13it/s]
 20%|████████████████████▉                                                                                      | 57/291 [00:28<02:00,  1.94it/s]
                                                                                                                                                 
[2024-01-30 01:54:57] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 20%|████████████████████▉                                                                                      | 57/291 [00:28<02:00,  1.94it/s]
                                                                                                                                                 
[2024-01-30 01:54:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 20%|████████████████████▉                                                                                      | 57/291 [00:29<02:00,  1.94it/s]
                                                                                                                                                 
[2024-01-30 01:54:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 20%|████████████████████▉                                                                                      | 57/291 [00:29<02:00,  1.94it/s]
 20%|█████████████████████▋                                                                                     | 59/291 [00:29<01:26,  2.69it/s]
                                                                                                                                                 
[2024-01-30 01:54:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 20%|█████████████████████▋                                                                                     | 59/291 [00:29<01:26,  2.69it/s]
                                                                                                                                                 
[2024-01-30 01:54:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 20%|█████████████████████▋                                                                                     | 59/291 [00:29<01:26,  2.69it/s]
 21%|██████████████████████                                                                                     | 60/291 [00:29<01:16,  3.01it/s]
                                                                                                                                                 
[2024-01-30 01:54:58] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (8192,), dtype: float16
+
 21%|██████████████████████                                                                                     | 60/291 [00:29<01:16,  3.01it/s]
                                                                                                                                                 
[2024-01-30 01:54:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 21%|██████████████████████                                                                                     | 60/291 [00:29<01:16,  3.01it/s]
                                                                                                                                                 
[2024-01-30 01:54:58] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 21%|██████████████████████                                                                                     | 60/291 [00:29<01:16,  3.01it/s]
 21%|██████████████████████▊                                                                                    | 62/291 [00:29<01:08,  3.34it/s]
                                                                                                                                                 
[2024-01-30 01:54:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 21%|██████████████████████▊                                                                                    | 62/291 [00:30<01:08,  3.34it/s]
                                                                                                                                                 
[2024-01-30 01:54:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 21%|██████████████████████▊                                                                                    | 62/291 [00:30<01:08,  3.34it/s]
 22%|███████████████████████▏                                                                                   | 63/291 [00:30<01:52,  2.03it/s]
                                                                                                                                                 
[2024-01-30 01:54:59] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 22%|███████████████████████▏                                                                                   | 63/291 [00:30<01:52,  2.03it/s]
                                                                                                                                                 
[2024-01-30 01:55:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 22%|███████████████████████▏                                                                                   | 63/291 [00:31<01:52,  2.03it/s]
                                                                                                                                                 
[2024-01-30 01:55:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 22%|███████████████████████▏                                                                                   | 63/291 [00:31<01:52,  2.03it/s]
 22%|███████████████████████▉                                                                                   | 65/291 [00:31<01:20,  2.80it/s]
                                                                                                                                                 
[2024-01-30 01:55:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 22%|███████████████████████▉                                                                                   | 65/291 [00:31<01:20,  2.80it/s]
                                                                                                                                                 
[2024-01-30 01:55:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 22%|███████████████████████▉                                                                                   | 65/291 [00:31<01:20,  2.80it/s]
 23%|████████████████████████▎                                                                                  | 66/291 [00:31<01:12,  3.11it/s]
                                                                                                                                                 
[2024-01-30 01:55:00] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (8192,), dtype: float16
+
 23%|████████████████████████▎                                                                                  | 66/291 [00:31<01:12,  3.11it/s]
                                                                                                                                                 
[2024-01-30 01:55:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 23%|████████████████████████▎                                                                                  | 66/291 [00:31<01:12,  3.11it/s]
                                                                                                                                                 
[2024-01-30 01:55:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 23%|████████████████████████▎                                                                                  | 66/291 [00:31<01:12,  3.11it/s]
 23%|█████████████████████████                                                                                  | 68/291 [00:31<01:05,  3.42it/s]
                                                                                                                                                 
[2024-01-30 01:55:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 23%|█████████████████████████                                                                                  | 68/291 [00:33<01:05,  3.42it/s]
                                                                                                                                                 
[2024-01-30 01:55:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 23%|█████████████████████████                                                                                  | 68/291 [00:33<01:05,  3.42it/s]
 24%|█████████████████████████▎                                                                                 | 69/291 [00:33<01:48,  2.04it/s]
                                                                                                                                                 
[2024-01-30 01:55:01] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 24%|█████████████████████████▎                                                                                 | 69/291 [00:33<01:48,  2.04it/s]
                                                                                                                                                 
[2024-01-30 01:55:02] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 24%|█████████████████████████▎                                                                                 | 69/291 [00:33<01:48,  2.04it/s]
                                                                                                                                                 
[2024-01-30 01:55:02] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 24%|█████████████████████████▎                                                                                 | 69/291 [00:33<01:48,  2.04it/s]
 24%|██████████████████████████                                                                                 | 71/291 [00:33<01:18,  2.82it/s]
                                                                                                                                                 
[2024-01-30 01:55:02] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 24%|██████████████████████████                                                                                 | 71/291 [00:33<01:18,  2.82it/s]
                                                                                                                                                 
[2024-01-30 01:55:02] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 24%|██████████████████████████                                                                                 | 71/291 [00:33<01:18,  2.82it/s]
 25%|██████████████████████████▍                                                                                | 72/291 [00:33<01:10,  3.12it/s]
                                                                                                                                                 
[2024-01-30 01:55:02] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (8192,), dtype: float16
+
 25%|██████████████████████████▍                                                                                | 72/291 [00:33<01:10,  3.12it/s]
                                                                                                                                                 
[2024-01-30 01:55:02] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 25%|██████████████████████████▍                                                                                | 72/291 [00:34<01:10,  3.12it/s]
                                                                                                                                                 
[2024-01-30 01:55:02] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 25%|██████████████████████████▍                                                                                | 72/291 [00:34<01:10,  3.12it/s]
 25%|███████████████████████████▏                                                                               | 74/291 [00:34<01:05,  3.32it/s]
                                                                                                                                                 
[2024-01-30 01:55:04] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 25%|███████████████████████████▏                                                                               | 74/291 [00:35<01:05,  3.32it/s]
                                                                                                                                                 
[2024-01-30 01:55:04] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 25%|███████████████████████████▏                                                                               | 74/291 [00:35<01:05,  3.32it/s]
 26%|███████████████████████████▌                                                                               | 75/291 [00:35<01:48,  1.98it/s]
                                                                                                                                                 
[2024-01-30 01:55:04] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 26%|███████████████████████████▌                                                                               | 75/291 [00:35<01:48,  1.98it/s]
                                                                                                                                                 
[2024-01-30 01:55:04] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 26%|███████████████████████████▌                                                                               | 75/291 [00:35<01:48,  1.98it/s]
                                                                                                                                                 
[2024-01-30 01:55:04] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 26%|███████████████████████████▌                                                                               | 75/291 [00:35<01:48,  1.98it/s]
 26%|████████████████████████████▎                                                                              | 77/291 [00:35<01:18,  2.74it/s]
                                                                                                                                                 
[2024-01-30 01:55:04] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 26%|████████████████████████████▎                                                                              | 77/291 [00:35<01:18,  2.74it/s]
                                                                                                                                                 
[2024-01-30 01:55:04] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 26%|████████████████████████████▎                                                                              | 77/291 [00:35<01:18,  2.74it/s]
 27%|███████���████████████████████▋                                                                              | 78/291 [00:35<01:09,  3.06it/s]
                                                                                                                                                 
[2024-01-30 01:55:05] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 27%|████████████████████████████▋                                                                              | 78/291 [00:37<01:09,  3.06it/s]
                                                                                                                                                 
[2024-01-30 01:55:05] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 27%|████████████████████████████▋                                                                              | 78/291 [00:37<01:09,  3.06it/s]
 27%|█████████████████████████████                                                                              | 79/291 [00:37<01:59,  1.78it/s]
                                                                                                                                                 
[2024-01-30 01:55:06] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 27%|█████████████████████████████                                                                              | 79/291 [00:37<01:59,  1.78it/s]
                                                                                                                                                 
[2024-01-30 01:55:06] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 27%|█████████████████████████████                                                                              | 79/291 [00:37<01:59,  1.78it/s]
 27%|█████████████████████████████▍                                                                             | 80/291 [00:37<01:44,  2.02it/s]
                                                                                                                                                 
[2024-01-30 01:55:06] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 27%|█████████████████████████████▍                                                                             | 80/291 [00:37<01:44,  2.02it/s]
                                                                                                                                                 
[2024-01-30 01:55:06] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 27%|█████████████████████████████▍                                                                             | 80/291 [00:37<01:44,  2.02it/s]
 28%|█████████████████████████████▊                                                                             | 81/291 [00:37<01:27,  2.39it/s]
                                                                                                                                                 
[2024-01-30 01:55:06] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/pytorch_model-00001-of-00007.bin
+
 28%|█████████████████████████████▊                                                                             | 81/291 [00:37<01:27,  2.39it/s]
                                                                                                                                                 
[2024-01-30 01:55:06] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/pytorch_model-00002-of-00007.bin
+
 28%|█████████████████████████████▊                                                                             | 81/291 [00:37<01:27,  2.39it/s]
                                                                                                                                                 
[2024-01-30 01:55:09] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (8192,), dtype: float16
+
 28%|█████████████████████████████▊                                                                             | 81/291 [00:40<01:27,  2.39it/s]
 28%|██████████████████████████████▏                                                                            | 82/291 [00:40<04:15,  1.22s/it]
                                                                                                                                                 
[2024-01-30 01:55:10] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 28%|██████████████████████████████▏                                                                            | 82/291 [00:41<04:15,  1.22s/it]
                                                                                                                                                 
[2024-01-30 01:55:10] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 28%|██████████████████████████████▏                                                                            | 82/291 [00:41<04:15,  1.22s/it]
 29%|██████████████████████████████▌                                                                            | 83/291 [00:41<03:31,  1.02s/it]
                                                                                                                                                 
[2024-01-30 01:55:11] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 29%|██████████████████████████████▌                                                                            | 83/291 [00:42<03:31,  1.02s/it]
                                                                                                                                                 
[2024-01-30 01:55:11] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 29%|██████████████████████████████▌                                                                            | 83/291 [00:42<03:31,  1.02s/it]
 29%|██████████████████████████████▉                                                                            | 84/291 [00:42<03:48,  1.11s/it]
                                                                                                                                                 
[2024-01-30 01:55:11] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 29%|██████████████████████████████▉                                                                            | 84/291 [00:42<03:48,  1.11s/it]
                                                                                                                                                 
[2024-01-30 01:55:11] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 29%|██████████████████████████████▉                                                                            | 84/291 [00:43<03:48,  1.11s/it]
                                                                                                                                                 
[2024-01-30 01:55:11] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 29%|██████████████████████████████▉                                                                            | 84/291 [00:43<03:48,  1.11s/it]
 30%|███████████████████████████████▌                                                                           | 86/291 [00:43<02:17,  1.50it/s]
                                                                                                                                                 
[2024-01-30 01:55:12] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 30%|███████████████████████████████▌                                                                           | 86/291 [00:43<02:17,  1.50it/s]
                                                                                                                                                 
[2024-01-30 01:55:12] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 30%|███████████████████████████████▌                                                                           | 86/291 [00:43<02:17,  1.50it/s]
 30%|███████████████████████████████▉                                                                           | 87/291 [00:43<01:52,  1.81it/s]
                                                                                                                                                 
[2024-01-30 01:55:12] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (8192,), dtype: float16
+
 30%|███████████████████████████████▉                                                                           | 87/291 [00:43<01:52,  1.81it/s]
                                                                                                                                                 
[2024-01-30 01:55:12] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 30%|███████████████████████████████▉                                                                           | 87/291 [00:43<01:52,  1.81it/s]
                                                                                                                                                 
[2024-01-30 01:55:12] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 30%|███████████████████████████████▉                                                                           | 87/291 [00:43<01:52,  1.81it/s]
 31%|████████████████████████████████▋                                                                          | 89/291 [00:43<01:26,  2.32it/s]
                                                                                                                                                 
[2024-01-30 01:55:13] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 31%|████████████████████████████████▋                                                                          | 89/291 [00:44<01:26,  2.32it/s]
                                                                                                                                                 
[2024-01-30 01:55:13] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 31%|████████████████████████████████▋                                                                          | 89/291 [00:44<01:26,  2.32it/s]
 31%|█████████████████████████████████                                                                          | 90/291 [00:44<02:02,  1.65it/s]
                                                                                                                                                 
[2024-01-30 01:55:13] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 31%|█████████████████████████████████                                                                          | 90/291 [00:44<02:02,  1.65it/s]
                                                                                                                                                 
[2024-01-30 01:55:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 31%|█████████████████████████████████                                                                          | 90/291 [00:45<02:02,  1.65it/s]
                                                                                                                                                 
[2024-01-30 01:55:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 31%|█████████████████████████████████                                                                          | 90/291 [00:45<02:02,  1.65it/s]
 32%|█████████████████████████████████▊                                                                         | 92/291 [00:45<01:23,  2.37it/s]
                                                                                                                                                 
[2024-01-30 01:55:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 32%|█████████████████████████████████▊                                                                         | 92/291 [00:45<01:23,  2.37it/s]
                                                                                                                                                 
[2024-01-30 01:55:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 32%|█████████████████████████████████▊                                                                         | 92/291 [00:45<01:23,  2.37it/s]
 32%|██████████████████████████████████▏                                                                        | 93/291 [00:45<01:13,  2.70it/s]
                                                                                                                                                 
[2024-01-30 01:55:14] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (8192,), dtype: float16
+
 32%|██████████████████████████████████▏                                                                        | 93/291 [00:45<01:13,  2.70it/s]
                                                                                                                                                 
[2024-01-30 01:55:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 32%|██████████████████████████████████▏                                                                        | 93/291 [00:45<01:13,  2.70it/s]
                                                                                                                                                 
[2024-01-30 01:55:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 32%|██████████████████████████████████▏                                                                        | 93/291 [00:45<01:13,  2.70it/s]
 33%|██████████████████████████████████▉                                                                        | 95/291 [00:45<01:04,  3.03it/s]
                                                                                                                                                 
[2024-01-30 01:55:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 33%|██████████████████████████████████▉                                                                        | 95/291 [00:47<01:04,  3.03it/s]
                                                                                                                                                 
[2024-01-30 01:55:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 33%|██████████████████████████████████▉                                                                        | 95/291 [00:47<01:04,  3.03it/s]
 33%|███████████████████████████████████▎                                                                       | 96/291 [00:47<01:48,  1.79it/s]
                                                                                                                                                 
[2024-01-30 01:55:16] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 33%|███████████████████████████████████▎                                                                       | 96/291 [00:47<01:48,  1.79it/s]
                                                                                                                                                 
[2024-01-30 01:55:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 33%|███████████████████████████████████▎                                                                       | 96/291 [00:47<01:48,  1.79it/s]
                                                                                                                                                 
[2024-01-30 01:55:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 33%|███████████████████████████████████▎                                                                       | 96/291 [00:47<01:48,  1.79it/s]
 34%|████████████████████████████████████                                                                       | 98/291 [00:47<01:16,  2.53it/s]
                                                                                                                                                 
[2024-01-30 01:55:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 34%|████████████████████████████████████                                                                       | 98/291 [00:47<01:16,  2.53it/s]
                                                                                                                                                 
[2024-01-30 01:55:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 34%|████████████████████████████████████                                                                       | 98/291 [00:47<01:16,  2.53it/s]
 34%|████████████████████████████████████▍                                                                      | 99/291 [00:47<01:07,  2.85it/s]
                                                                                                                                                 
[2024-01-30 01:55:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 34%|████████████████████████████████████▍                                                                      | 99/291 [00:49<01:07,  2.85it/s]
                                                                                                                                                 
[2024-01-30 01:55:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 34%|████████████████████████████████████▍                                                                      | 99/291 [00:49<01:07,  2.85it/s]
 34%|████████████████████████████████████▍                                                                     | 100/291 [00:49<01:50,  1.73it/s]
                                                                                                                                                 
[2024-01-30 01:55:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 34%|████████████████████████████████████▍                                                                     | 100/291 [00:49<01:50,  1.73it/s]
                                                                                                                                                 
[2024-01-30 01:55:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 34%|████████████████████████████████████▍                                                                     | 100/291 [00:49<01:50,  1.73it/s]
 35%|████████████████████████████████████▊                                                                     | 101/291 [00:49<01:35,  1.99it/s]
                                                                                                                                                 
[2024-01-30 01:55:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 35%|████████████████████████████████████▊                                                                     | 101/291 [00:49<01:35,  1.99it/s]
                                                                                                                                                 
[2024-01-30 01:55:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 35%|████████████████████████████████████▊                                                                     | 101/291 [00:49<01:35,  1.99it/s]
 35%|█████████████████████████████████████▏                                                                    | 102/291 [00:49<01:19,  2.38it/s]
                                                                                                                                                 
[2024-01-30 01:55:18] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (8192,), dtype: float16
+
 35%|█████████████████████████████████████▏                                                                    | 102/291 [00:49<01:19,  2.38it/s]
                                                                                                                                                 
[2024-01-30 01:55:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 35%|█████████████████████████████████████▏                                                                    | 102/291 [00:50<01:19,  2.38it/s]
                                                                                                                                                 
[2024-01-30 01:55:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 35%|█████████████████████████████████████▏                                                                    | 102/291 [00:50<01:19,  2.38it/s]
 36%|█████████████████████████████████████▉                                                                    | 104/291 [00:50<01:04,  2.91it/s]
                                                                                                                                                 
[2024-01-30 01:55:18] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 36%|█████████████████████████████████████▉                                                                    | 104/291 [00:50<01:04,  2.91it/s]
                                                                                                                                                 
[2024-01-30 01:55:18] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (8192,), dtype: float16
+
 36%|█████████████████████████████████████▉                                                                    | 104/291 [00:50<01:04,  2.91it/s]
                                                                                                                                                 
[2024-01-30 01:55:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 36%|█████████████████████████████████████▉                                                                    | 104/291 [00:50<01:04,  2.91it/s]
                                                                                                                                                 
[2024-01-30 01:55:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 36%|█████████████████████████████████████▉                                                                    | 104/291 [00:50<01:04,  2.91it/s]
 37%|██████████████████████████████████████▉                                                                   | 107/291 [00:50<00:47,  3.87it/s]
                                                                                                                                                 
[2024-01-30 01:55:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 37%|██████████████████████████████████████▉                                                                   | 107/291 [00:51<00:47,  3.87it/s]
                                                                                                                                                 
[2024-01-30 01:55:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 37%|██████████████████████████████████████▉                                                                   | 107/291 [00:51<00:47,  3.87it/s]
 37%|███████████████████████████████████████▎                                                                  | 108/291 [00:51<01:22,  2.22it/s]
                                                                                                                                                 
[2024-01-30 01:55:20] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 37%|███████████████████████████████████████▎                                                                  | 108/291 [00:51<01:22,  2.22it/s]
                                                                                                                                                 
[2024-01-30 01:55:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 37%|███████████████████████████████████████▎                                                                  | 108/291 [00:52<01:22,  2.22it/s]
                                                                                                                                                 
[2024-01-30 01:55:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 37%|███████████████████████████████████████▎                                                                  | 108/291 [00:52<01:22,  2.22it/s]
 38%|████████████████████████████████████████                                                                  | 110/291 [00:52<01:01,  2.95it/s]
                                                                                                                                                 
[2024-01-30 01:55:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 38%|████████████████████████████████████████                                                                  | 110/291 [00:52<01:01,  2.95it/s]
                                                                                                                                                 
[2024-01-30 01:55:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 38%|████████████████████████████████████████                                                                  | 110/291 [00:52<01:01,  2.95it/s]
 38%|█████████████████████████���██████████████▍                                                                 | 111/291 [00:52<00:55,  3.23it/s]
                                                                                                                                                 
[2024-01-30 01:55:21] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (8192,), dtype: float16
+
 38%|████████████████████████████████████████▍                                                                 | 111/291 [00:52<00:55,  3.23it/s]
                                                                                                                                                 
[2024-01-30 01:55:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 38%|████████████████████████████████████████▍                                                                 | 111/291 [00:52<00:55,  3.23it/s]
                                                                                                                                                 
[2024-01-30 01:55:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 38%|████████████████████████████████████████▍                                                                 | 111/291 [00:52<00:55,  3.23it/s]
 39%|█████████████████████████████████████████▏                                                                | 113/291 [00:52<00:51,  3.48it/s]
                                                                                                                                                 
[2024-01-30 01:55:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 39%|█████████████████████████████████████████▏                                                                | 113/291 [00:54<00:51,  3.48it/s]
                                                                                                                                                 
[2024-01-30 01:55:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 39%|█████████████████████████████████████████▏                                                                | 113/291 [00:54<00:51,  3.48it/s]
 39%|█████████████████████████████████████████▌                                                                | 114/291 [00:54<01:24,  2.09it/s]
                                                                                                                                                 
[2024-01-30 01:55:22] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 39%|█████████████████████████████████████████▌                                                                | 114/291 [00:54<01:24,  2.09it/s]
                                                                                                                                                 
[2024-01-30 01:55:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 39%|█████████████████████████████████████████▌                                                                | 114/291 [00:54<01:24,  2.09it/s]
                                                                                                                                                 
[2024-01-30 01:55:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 39%|█████████████████████████████████████████▌                                                                | 114/291 [00:54<01:24,  2.09it/s]
 40%|██████████████████████████████████████████▎                                                               | 116/291 [00:54<01:01,  2.85it/s]
                                                                                                                                                 
[2024-01-30 01:55:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 40%|██████████████████████████████████████████▎                                                               | 116/291 [00:54<01:01,  2.85it/s]
                                                                                                                                                 
[2024-01-30 01:55:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 40%|██████████████████████████████████████████▎                                                               | 116/291 [00:54<01:01,  2.85it/s]
 40%|██████████████████████████████████████████▌                                                               | 117/291 [00:54<00:55,  3.16it/s]
                                                                                                                                                 
[2024-01-30 01:55:23] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (8192,), dtype: float16
+
 40%|██████████████████████████████████████████▌                                                               | 117/291 [00:54<00:55,  3.16it/s]
                                                                                                                                                 
[2024-01-30 01:55:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 40%|██████████████████████████████████████████▌                                                               | 117/291 [00:54<00:55,  3.16it/s]
                                                                                                                                                 
[2024-01-30 01:55:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 40%|██████████████████████████████████████████▌                                                               | 117/291 [00:54<00:55,  3.16it/s]
 41%|███████████████████████████████████████████▎                                                              | 119/291 [00:54<00:50,  3.44it/s]
                                                                                                                                                 
[2024-01-30 01:55:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 41%|███████████████████████████████████████████▎                                                              | 119/291 [00:56<00:50,  3.44it/s]
                                                                                                                                                 
[2024-01-30 01:55:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 41%|███████████████████████████████████████████▎                                                              | 119/291 [00:56<00:50,  3.44it/s]
 41%|███████████████████████████████████████████▋                                                              | 120/291 [00:56<01:23,  2.05it/s]
                                                                                                                                                 
[2024-01-30 01:55:25] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 41%|███████████████████████████████████████████▋                                                              | 120/291 [00:56<01:23,  2.05it/s]
                                                                                                                                                 
[2024-01-30 01:55:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 41%|███████████████████████████████████████████▋                                                              | 120/291 [00:56<01:23,  2.05it/s]
                                                                                                                                                 
[2024-01-30 01:55:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 41%|███████████████████████████████████████████▋                                                              | 120/291 [00:56<01:23,  2.05it/s]
 42%|████████████████████████████████████████████▍                                                             | 122/291 [00:56<00:59,  2.82it/s]
                                                                                                                                                 
[2024-01-30 01:55:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 42%|████████████████████████████████████████████▍                                                             | 122/291 [00:56<00:59,  2.82it/s]
                                                                                                                                                 
[2024-01-30 01:55:25] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 42%|████████████████████████████████████████████▍                                                             | 122/291 [00:56<00:59,  2.82it/s]
 42%|████████████████████████████████████████████▊                                                             | 123/291 [00:56<00:53,  3.14it/s]
                                                                                                                                                 
[2024-01-30 01:55:25] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/pytorch_model-00002-of-00007.bin
+
 42%|████████████████████████████████████████████▊                                                             | 123/291 [00:56<00:53,  3.14it/s]
                                                                                                                                                 
[2024-01-30 01:55:25] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/pytorch_model-00003-of-00007.bin
+
 42%|████████████████████████████████████████████▊                                                             | 123/291 [00:56<00:53,  3.14it/s]
                                                                                                                                                 
[2024-01-30 01:55:28] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (8192,), dtype: float16
+
 42%|████████████████████████████████████████████▊                                                             | 123/291 [00:59<00:53,  3.14it/s]
 43%|█████████████████████████████████████████████▏                                                            | 124/291 [00:59<02:48,  1.01s/it]
                                                                                                                                                 
[2024-01-30 01:55:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 43%|█████████████████████████████████████████████▏                                                            | 124/291 [01:00<02:48,  1.01s/it]
                                                                                                                                                 
[2024-01-30 01:55:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 43%|█████████████████████████████████████████████▏                                                            | 124/291 [01:00<02:48,  1.01s/it]
 43%|█████████████████████████████████████████████▌                                                            | 125/291 [01:00<02:26,  1.13it/s]
                                                                                                                                                 
[2024-01-30 01:55:29] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 43%|█████████████████████████████████████████████▌                                                            | 125/291 [01:00<02:26,  1.13it/s]
                                                                                                                                                 
[2024-01-30 01:55:29] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (8192,), dtype: float16
+
 43%|█████████████████████████████████████████████▌                                                            | 125/291 [01:00<02:26,  1.13it/s]
                                                                                                                                                 
[2024-01-30 01:55:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 43%|█████████████████████████████████████████████▌                                                            | 125/291 [01:00<02:26,  1.13it/s]
                                                                                                                                                 
[2024-01-30 01:55:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 43%|█████████████████████████████████████████████▌                                                            | 125/291 [01:00<02:26,  1.13it/s]
 44%|██████████████████████████████████████████████▋                                                           | 128/291 [01:00<01:23,  1.96it/s]
                                                                                                                                                 
[2024-01-30 01:55:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 44%|██████████████████████████████████████████████▋                                                           | 128/291 [01:02<01:23,  1.96it/s]
                                                                                                                                                 
[2024-01-30 01:55:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 44%|██████████████████████████████████████████████▋                                                           | 128/291 [01:02<01:23,  1.96it/s]
 44%|██████████████████████████████████████████████▉                                                           | 129/291 [01:02<01:49,  1.49it/s]
                                                                                                                                                 
[2024-01-30 01:55:31] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 44%|██████████████████████████████████████████████▉                                                           | 129/291 [01:02<01:49,  1.49it/s]
                                                                                                                                                 
[2024-01-30 01:55:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 44%|██████████████████████████████████████████████▉                                                           | 129/291 [01:02<01:49,  1.49it/s]
                                                                                                                                                 
[2024-01-30 01:55:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 44%|██████████████████████████████████████████████▉                                                           | 129/291 [01:02<01:49,  1.49it/s]
 45%|███████████████████████████████████████████████▋                                                          | 131/291 [01:02<01:16,  2.09it/s]
                                                                                                                                                 
[2024-01-30 01:55:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 45%|███████████████████████████████████████████████▋                                                          | 131/291 [01:02<01:16,  2.09it/s]
                                                                                                                                                 
[2024-01-30 01:55:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 45%|███████████████████████████████████████████████▋                                                          | 131/291 [01:02<01:16,  2.09it/s]
 45%|████████████████████████████████████████████████                                                          | 132/291 [01:02<01:06,  2.39it/s]
                                                                                                                                                 
[2024-01-30 01:55:31] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (8192,), dtype: float16
+
 45%|████████████████████████████████████████████████                                                          | 132/291 [01:02<01:06,  2.39it/s]
                                                                                                                                                 
[2024-01-30 01:55:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 45%|████████████████████████████████████████████████                                                          | 132/291 [01:03<01:06,  2.39it/s]
                                                                                                                                                 
[2024-01-30 01:55:32] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 45%|████████████████████████████████████████████████                                                          | 132/291 [01:03<01:06,  2.39it/s]
 46%|████████████████████████████████████████████████▊                                                         | 134/291 [01:03<00:55,  2.81it/s]
                                                                                                                                                 
[2024-01-30 01:55:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 46%|████████████████████████████████████████████████▊                                                         | 134/291 [01:04<00:55,  2.81it/s]
                                                                                                                                                 
[2024-01-30 01:55:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 46%|████████████████████████████████████████████████▊                                                         | 134/291 [01:04<00:55,  2.81it/s]
 46%|█████████████████████████████████████████████████▏                                                        | 135/291 [01:04<01:23,  1.87it/s]
                                                                                                                                                 
[2024-01-30 01:55:33] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 46%|█████████████████████████████████████████████████▏                                                        | 135/291 [01:04<01:23,  1.87it/s]
                                                                                                                                                 
[2024-01-30 01:55:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 46%|█████████████████████████████████████████████████▏                                                        | 135/291 [01:04<01:23,  1.87it/s]
                                                                                                                                                 
[2024-01-30 01:55:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 46%|█████████████████████████████████████████████████▏                                                        | 135/291 [01:04<01:23,  1.87it/s]
 47%|█████████████████████████████████████████████████▉                                                        | 137/291 [01:04<00:59,  2.60it/s]
                                                                                                                                                 
[2024-01-30 01:55:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 47%|█████████████████████████████████████████████████▉                                                        | 137/291 [01:04<00:59,  2.60it/s]
                                                                                                                                                 
[2024-01-30 01:55:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 47%|█████████████████████████████████████████████████▉                                                        | 137/291 [01:04<00:59,  2.60it/s]
 47%|██████████████████████████████████████████████████▎                                                       | 138/291 [01:04<00:52,  2.91it/s]
                                                                                                                                                 
[2024-01-30 01:55:33] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (8192,), dtype: float16
+
 47%|██████████████████████████████████████████████████▎                                                       | 138/291 [01:04<00:52,  2.91it/s]
                                                                                                                                                 
[2024-01-30 01:55:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 47%|██████████████████████████████████��███████████████▎                                                       | 138/291 [01:05<00:52,  2.91it/s]
                                                                                                                                                 
[2024-01-30 01:55:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 47%|██████████████████████████████████████████████████▎                                                       | 138/291 [01:05<00:52,  2.91it/s]
 48%|██████████████████████████████████████████████████▉                                                       | 140/291 [01:05<00:46,  3.27it/s]
                                                                                                                                                 
[2024-01-30 01:55:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 48%|██████████████████████████████████████████████████▉                                                       | 140/291 [01:06<00:46,  3.27it/s]
                                                                                                                                                 
[2024-01-30 01:55:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 48%|██████████████████████████████████████████████████▉                                                       | 140/291 [01:06<00:46,  3.27it/s]
 48%|███████████████████████████████████████████████████▎                                                      | 141/291 [01:06<01:15,  1.99it/s]
                                                                                                                                                 
[2024-01-30 01:55:35] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 48%|███████████████████████████████████████████████████▎                                                      | 141/291 [01:06<01:15,  1.99it/s]
                                                                                                                                                 
[2024-01-30 01:55:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 48%|███████████████████████████████████████████████████▎                                                      | 141/291 [01:06<01:15,  1.99it/s]
                                                                                                                                                 
[2024-01-30 01:55:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 48%|███████████████████████████████████████████████████▎                                                      | 141/291 [01:06<01:15,  1.99it/s]
 49%|████████████████████████████████████████████████████                                                      | 143/291 [01:06<00:53,  2.76it/s]
                                                                                                                                                 
[2024-01-30 01:55:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 49%|████████████████████████████████████████████████████                                                      | 143/291 [01:07<00:53,  2.76it/s]
                                                                                                                                                 
[2024-01-30 01:55:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 49%|████████████████████████████████████████████████████                                                      | 143/291 [01:07<00:53,  2.76it/s]
 49%|████████████████████████████████████████████████████▍                                                     | 144/291 [01:07<00:47,  3.08it/s]
                                                                                                                                                 
[2024-01-30 01:55:35] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (8192,), dtype: float16
+
 49%|████████████████████████████████████████████████████▍                                                     | 144/291 [01:07<00:47,  3.08it/s]
                                                                                                                                                 
[2024-01-30 01:55:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 49%|████████████████████████████████████████████████████▍                                                     | 144/291 [01:07<00:47,  3.08it/s]
                                                                                                                                                 
[2024-01-30 01:55:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 49%|████████████████████████████████████████████████████▍                                                     | 144/291 [01:07<00:47,  3.08it/s]
 50%|█████████████████████████████████████████████████████▏                                                    | 146/291 [01:07<00:42,  3.40it/s]
                                                                                                                                                 
[2024-01-30 01:55:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 50%|█████████████████████████████████████████████████████▏                                                    | 146/291 [01:08<00:42,  3.40it/s]
                                                                                                                                                 
[2024-01-30 01:55:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 50%|█████████████████████████████████████████████████████▏                                                    | 146/291 [01:08<00:42,  3.40it/s]
 51%|█████████████████████████████████████████████████████▌                                                    | 147/291 [01:08<01:11,  2.02it/s]
                                                                                                                                                 
[2024-01-30 01:55:37] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 51%|█████████████████████████████████████████████████████▌                                                    | 147/291 [01:08<01:11,  2.02it/s]
                                                                                                                                                 
[2024-01-30 01:55:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 51%|█████████████████████████████████████████████████████▌                                                    | 147/291 [01:09<01:11,  2.02it/s]
                                                                                                                                                 
[2024-01-30 01:55:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 51%|█████████████████████████████████████████████████████▌                                                    | 147/291 [01:09<01:11,  2.02it/s]
 51%|██████████████████████████████████████████████████████▎                                                   | 149/291 [01:09<00:51,  2.78it/s]
                                                                                                                                                 
[2024-01-30 01:55:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 51%|██████████████████████████████████████████████████████▎                                                   | 149/291 [01:09<00:51,  2.78it/s]
                                                                                                                                                 
[2024-01-30 01:55:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 51%|██████████████████████████████████████████████████████▎                                                   | 149/291 [01:09<00:51,  2.78it/s]
 52%|██████████████████████████████████████████████████████▋                                                   | 150/291 [01:09<00:45,  3.09it/s]
                                                                                                                                                 
[2024-01-30 01:55:38] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (8192,), dtype: float16
+
 52%|██████████████████████████████████████████████████████▋                                                   | 150/291 [01:09<00:45,  3.09it/s]
                                                                                                                                                 
[2024-01-30 01:55:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 52%|██████████████████████████████████████████████████████▋                                                   | 150/291 [01:09<00:45,  3.09it/s]
                                                                                                                                                 
[2024-01-30 01:55:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 52%|██████████████████████████████████████████████████████▋                                                   | 150/291 [01:09<00:45,  3.09it/s]
 52%|███████████████████████████████████████████████████████▎                                                  | 152/291 [01:09<00:41,  3.31it/s]
                                                                                                                                                 
[2024-01-30 01:55:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 52%|███████████████████████████████████████████████████████▎                                                  | 152/291 [01:11<00:41,  3.31it/s]
                                                                                                                                                 
[2024-01-30 01:55:39] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 52%|███████████████████████████████████████████████████████▎                                                  | 152/291 [01:11<00:41,  3.31it/s]
 53%|███████████████████████████████████████████████████████▋                                                  | 153/291 [01:11<01:11,  1.94it/s]
                                                                                                                                                 
[2024-01-30 01:55:39] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 53%|███████████████████████████████████████████████████████▋                                                  | 153/291 [01:11<01:11,  1.94it/s]
                                                                                                                                                 
[2024-01-30 01:55:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 53%|███████████████████████████████████████████████████████▋                                                  | 153/291 [01:11<01:11,  1.94it/s]
                                                                                                                                                 
[2024-01-30 01:55:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 53%|███████████████████████████████████████████████████████▋                                                  | 153/291 [01:11<01:11,  1.94it/s]
 53%|████████████████████████████████████████████████████████▍                                                 | 155/291 [01:11<00:50,  2.69it/s]
                                                                                                                                                 
[2024-01-30 01:55:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 53%|████████████████████████████████████████████████████████▍                                                 | 155/291 [01:11<00:50,  2.69it/s]
                                                                                                                                                 
[2024-01-30 01:55:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 53%|████████████████████████████████████████████████████████▍                                                 | 155/291 [01:11<00:50,  2.69it/s]
 54%|████████████████████████████████████████████████████████▊                                                 | 156/291 [01:11<00:44,  3.01it/s]
                                                                                                                                                 
[2024-01-30 01:55:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (8192,), dtype: float16
+
 54%|████████████████████████████████████████████████████████▊                                                 | 156/291 [01:11<00:44,  3.01it/s]
                                                                                                                                                 
[2024-01-30 01:55:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 54%|████████████████████████████████████████████████████████▊                                                 | 156/291 [01:12<00:44,  3.01it/s]
                                                                                                                                                 
[2024-01-30 01:55:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 54%|████████████████████████████████████████████████████████▊                                                 | 156/291 [01:12<00:44,  3.01it/s]
 54%|█████████████████████████████████████████████████████████▌                                                | 158/291 [01:12<00:41,  3.24it/s]
                                                                                                                                                 
[2024-01-30 01:55:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 54%|█████████████████████████████████████████████████████████▌                                                | 158/291 [01:13<00:41,  3.24it/s]
                                                                                                                                                 
[2024-01-30 01:55:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 54%|█████████████████████████████████████████████████████████▌                                                | 158/291 [01:13<00:41,  3.24it/s]
 55%|█████████████████████████████████████████████████████████▉                                                | 159/291 [01:13<01:10,  1.88it/s]
                                                                                                                                                 
[2024-01-30 01:55:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 55%|█████████████████████████████████████████████████████████▉                                                | 159/291 [01:13<01:10,  1.88it/s]
                                                                                                                                                 
[2024-01-30 01:55:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 55%|█████████████████████████████████████████████████████████▉                                                | 159/291 [01:13<01:10,  1.88it/s]
                                                                                                                                                 
[2024-01-30 01:55:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 55%|█████████████████████████████████████████████████████████▉                                                | 159/291 [01:13<01:10,  1.88it/s]
 55%|██████████████████████████████████████████████████████████▋                                               | 161/291 [01:13<00:49,  2.62it/s]
                                                                                                                                                 
[2024-01-30 01:55:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 55%|██████████████████████████████████████████████████████████▋                                               | 161/291 [01:13<00:49,  2.62it/s]
                                                                                                                                                 
[2024-01-30 01:55:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 55%|██████████████████████████████████████████████████████████▋                                               | 161/291 [01:13<00:49,  2.62it/s]
 56%|███████████████████████████████████████████████████████████                                               | 162/291 [01:13<00:44,  2.93it/s]
                                                                                                                                                 
[2024-01-30 01:55:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 56%|███████████████████████████████████████████████████████████                                               | 162/291 [01:15<00:44,  2.93it/s]
                                                                                                                                                 
[2024-01-30 01:55:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 56%|███████████████████████████████████████████████████████████                                               | 162/291 [01:15<00:44,  2.93it/s]
 56%|███████████████████████████████████████████████████████████▎                                              | 163/291 [01:15<01:12,  1.76it/s]
                                                                                                                                                 
[2024-01-30 01:55:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 56%|███████████████████████████████████████████████████████████▎                                              | 163/291 [01:15<01:12,  1.76it/s]
                                                                                                                                                 
[2024-01-30 01:55:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 56%|███████████████████████████████████████████████████████████▎                                              | 163/291 [01:15<01:12,  1.76it/s]
 56%|███████████████████████████████████████████████████████████▋                                              | 164/291 [01:15<01:02,  2.02it/s]
                                                                                                                                                 
[2024-01-30 01:55:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 56%|███████████████████████████████████████████████████████████▋                                              | 164/291 [01:15<01:02,  2.02it/s]
                                                                                                                                                 
[2024-01-30 01:55:44] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 56%|███████████████████████████████████████████████████████████▋                                              | 164/291 [01:15<01:02,  2.02it/s]
 57%|████████████████████████████████████████████████████████████                                              | 165/291 [01:15<00:52,  2.41it/s]
                                                                                                                                                 
[2024-01-30 01:55:44] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/pytorch_model-00003-of-00007.bin
+
 57%|████████████████████████████████████████████████████████████                                              | 165/291 [01:15<00:52,  2.41it/s]
                                                                                                                                                 
[2024-01-30 01:55:44] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/pytorch_model-00004-of-00007.bin
+
 57%|████████████████████████████████████████████████████████████                                              | 165/291 [01:15<00:52,  2.41it/s]
                                                                                                                                                 
[2024-01-30 01:55:47] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (8192,), dtype: float16
+
 57%|████████████████████████████████████████████████████████████                                              | 165/291 [01:19<00:52,  2.41it/s]
 57%|████████████████████████████████████████████████████████████▍                                             | 166/291 [01:19<02:32,  1.22s/it]
                                                                                                                                                 
[2024-01-30 01:55:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 57%|████████████████████████████████████████████████████████████▍                                             | 166/291 [01:19<02:32,  1.22s/it]
                                                                                                                                                 
[2024-01-30 01:55:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 57%|████████████████████████████████████████████████████████████▍                                             | 166/291 [01:19<02:32,  1.22s/it]
 57%|████████████████████████████████████████████████████████████▊                                             | 167/291 [01:19<02:06,  1.02s/it]
                                                                                                                                                 
[2024-01-30 01:55:48] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 57%|████████████████████████████████████████████████████████████▊                                             | 167/291 [01:19<02:06,  1.02s/it]
                                                                                                                                                 
[2024-01-30 01:55:48] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (8192,), dtype: float16
+
 57%|████████████████████████████████████████████████████████████▊                                             | 167/291 [01:19<02:06,  1.02s/it]
                                                                                                                                                 
[2024-01-30 01:55:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 57%|████████████████████████████████████████████████████████████▊                                             | 167/291 [01:20<02:06,  1.02s/it]
                                                                                                                                                 
[2024-01-30 01:55:48] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 57%|██████████████████████████████████████████████████████████��█▊                                             | 167/291 [01:20<02:06,  1.02s/it]
 58%|█████████████████████████████████████████████████████████████▉                                            | 170/291 [01:20<01:06,  1.81it/s]
                                                                                                                                                 
[2024-01-30 01:55:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 58%|█████████████████████████████████████████████████████████████▉                                            | 170/291 [01:21<01:06,  1.81it/s]
                                                                                                                                                 
[2024-01-30 01:55:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 58%|█████████████████████████████████████████████████████████████▉                                            | 170/291 [01:21<01:06,  1.81it/s]
 59%|██████████████████████████████████████████████████████████████▎                                           | 171/291 [01:21<01:25,  1.40it/s]
                                                                                                                                                 
[2024-01-30 01:55:50] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 59%|██████████████████████████████████████████████████████████████▎                                           | 171/291 [01:21<01:25,  1.40it/s]
                                                                                                                                                 
[2024-01-30 01:55:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 59%|██████████████████████████████████████████████████████████████▎                                           | 171/291 [01:21<01:25,  1.40it/s]
                                                                                                                                                 
[2024-01-30 01:55:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 59%|██████████████████████████████████████████████████████████████▎                                           | 171/291 [01:21<01:25,  1.40it/s]
 59%|███████████████████████████████████████████████████████████████                                           | 173/291 [01:21<00:58,  2.01it/s]
                                                                                                                                                 
[2024-01-30 01:55:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 59%|███████████████████████████████████████████████████████████████                                           | 173/291 [01:21<00:58,  2.01it/s]
                                                                                                                                                 
[2024-01-30 01:55:50] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 59%|███████████████████████████████████████████████████████████████                                           | 173/291 [01:21<00:58,  2.01it/s]
 60%|█████████████████████████████████████���█████████████████████████▍                                          | 174/291 [01:21<00:50,  2.32it/s]
                                                                                                                                                 
[2024-01-30 01:55:50] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.22.input_layernorm.weight", shape: (8192,), dtype: float16
+
 60%|███████████████████████████████████████████████████████████████▍                                          | 174/291 [01:21<00:50,  2.32it/s]
                                                                                                                                                 
[2024-01-30 01:55:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 60%|███████████████████████████████████████████████████████████████▍                                          | 174/291 [01:22<00:50,  2.32it/s]
                                                                                                                                                 
[2024-01-30 01:55:51] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 60%|███████████████████████████████████████████████████████████████▍                                          | 174/291 [01:22<00:50,  2.32it/s]
 60%|████████████████████████████████████████████████████████████████                                          | 176/291 [01:22<00:41,  2.76it/s]
                                                                                                                                                 
[2024-01-30 01:55:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 60%|████████████████████████████████████████████████████████████████                                          | 176/291 [01:23<00:41,  2.76it/s]
                                                                                                                                                 
[2024-01-30 01:55:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 60%|████████████████████████████████████████████████████████████████                                          | 176/291 [01:23<00:41,  2.76it/s]
 61%|████████████████████████████████████████████████████████████████▍                                         | 177/291 [01:23<01:02,  1.84it/s]
                                                                                                                                                 
[2024-01-30 01:55:52] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.22.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 61%|████████████████████████████████████████████████████████████████▍                                         | 177/291 [01:23<01:02,  1.84it/s]
                                                                                                                                                 
[2024-01-30 01:55:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 61%|████████████████████████████████████████████████████████████████▍                                         | 177/291 [01:23<01:02,  1.84it/s]
                                                                                                                                                 
[2024-01-30 01:55:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 61%|████████████████████████████████████████████████████████████████▍                                         | 177/291 [01:23<01:02,  1.84it/s]
 62%|█████████████████████████████████████████████████████████████████▏                                        | 179/291 [01:23<00:43,  2.57it/s]
                                                                                                                                                 
[2024-01-30 01:55:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 62%|█████████████████████████████████████████████████████████████████▏                                        | 179/291 [01:23<00:43,  2.57it/s]
                                                                                                                                                 
[2024-01-30 01:55:52] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.22.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 62%|█████████████████████████████████████████████████████████████████▏                                        | 179/291 [01:23<00:43,  2.57it/s]
 62%|█████████████████████████████████████████████████████████████████▌                                        | 180/291 [01:24<00:38,  2.88it/s]
                                                                                                                                                 
[2024-01-30 01:55:52] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.23.input_layernorm.weight", shape: (8192,), dtype: float16
+
 62%|█████████████████████████████████████████████████████████████████▌                                        | 180/291 [01:24<00:38,  2.88it/s]
                                                                                                                                                 
[2024-01-30 01:55:53] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 62%|█████████████████████████████████████████████████████████████████▌                                        | 180/291 [01:24<00:38,  2.88it/s]
                                                                                                                                                 
[2024-01-30 01:55:53] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 62%|█████████████████████████████████████████████████████████████████▌                                        | 180/291 [01:24<00:38,  2.88it/s]
 63%|██████████████████████████████████████████████████████████████████▎                                       | 182/291 [01:24<00:33,  3.23it/s]
                                                                                                                                                 
[2024-01-30 01:55:54] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 63%|██████████████████████████████████████████████████████████████████▎                                       | 182/291 [01:25<00:33,  3.23it/s]
                                                                                                                                                 
[2024-01-30 01:55:54] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 63%|█████████████████████████████████████████████��████████████████████▎                                       | 182/291 [01:25<00:33,  3.23it/s]
 63%|██████████████████████████████████████████████████████████████████▋                                       | 183/291 [01:25<00:54,  1.99it/s]
                                                                                                                                                 
[2024-01-30 01:55:54] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.23.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 63%|██████████████████████████████████████████████████████████████████▋                                       | 183/291 [01:25<00:54,  1.99it/s]
                                                                                                                                                 
[2024-01-30 01:55:54] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 63%|██████████████████████████████████████████████████████████████████▋                                       | 183/291 [01:25<00:54,  1.99it/s]
                                                                                                                                                 
[2024-01-30 01:55:54] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 63%|██████████████████████████████████████████████████████████████████▋                                       | 183/291 [01:25<00:54,  1.99it/s]
 64%|███████████████████████████████████████████████████████████████████▍                                      | 185/291 [01:25<00:38,  2.75it/s]
                                                                                                                                                 
[2024-01-30 01:55:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 64%|███████████████████████████████████████████████████████████████████▍                                      | 185/291 [01:26<00:38,  2.75it/s]
                                                                                                                                                 
[2024-01-30 01:55:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.23.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 64%|███████████████████████████████████████████████████████████████████▍                                      | 185/291 [01:26<00:38,  2.75it/s]
 64%|███████████████████████████████████████████████████████████████████▊                                      | 186/291 [01:26<00:34,  3.06it/s]
                                                                                                                                                 
[2024-01-30 01:55:55] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.24.input_layernorm.weight", shape: (8192,), dtype: float16
+
 64%|███████████████████████████████████████████████████████████████████▊                                      | 186/291 [01:26<00:34,  3.06it/s]
                                                                                                                                                 
[2024-01-30 01:55:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 64%|███████████████████████████████████████████████████████████████████▊                                      | 186/291 [01:26<00:34,  3.06it/s]
                                                                                                                                                 
[2024-01-30 01:55:55] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 64%|███████████████████████████████████████████████████████████████████▊                                      | 186/291 [01:26<00:34,  3.06it/s]
 65%|████████████████████████████████████████████████████████████████████▍                                     | 188/291 [01:26<00:31,  3.28it/s]
                                                                                                                                                 
[2024-01-30 01:55:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 65%|████████████████████████████████████████████████████████████████████▍                                     | 188/291 [01:27<00:31,  3.28it/s]
                                                                                                                                                 
[2024-01-30 01:55:56] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 65%|████████████████████████████████████████████████████████████████████▍                                     | 188/291 [01:27<00:31,  3.28it/s]
 65%|████████████████████████████████████████████████████████████████████▊                                     | 189/291 [01:27<00:52,  1.95it/s]
                                                                                                                                                 
[2024-01-30 01:55:56] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.24.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 65%|████████████████████████████████████████████████████████████████████▊                                     | 189/291 [01:28<00:52,  1.95it/s]
                                                                                                                                                 
[2024-01-30 01:55:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 65%|████████████████████████████████████████████████████████████████████▊                                     | 189/291 [01:28<00:52,  1.95it/s]
                                                                                                                                                 
[2024-01-30 01:55:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 65%|████████████████████████████████████████████████████████████████████▊                                     | 189/291 [01:28<00:52,  1.95it/s]
 66%|█████████████████████████████████████████████████████████████████████▌                                    | 191/291 [01:28<00:36,  2.71it/s]
                                                                                                                                                 
[2024-01-30 01:55:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 66%|█████████████████████████████████████████████████████████████████████▌                                    | 191/291 [01:28<00:36,  2.71it/s]
                                                                                                                                                 
[2024-01-30 01:55:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.24.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 66%|█████████████████████████████████████████████████████████████████████▌                                    | 191/291 [01:28<00:36,  2.71it/s]
 66%|█████████████████████████████████████████████████████████████████████▉                                    | 192/291 [01:28<00:32,  3.02it/s]
                                                                                                                                                 
[2024-01-30 01:55:57] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.25.input_layernorm.weight", shape: (8192,), dtype: float16
+
 66%|█████████████████████████████████████████████████████████████████████▉                                    | 192/291 [01:28<00:32,  3.02it/s]
                                                                                                                                                 
[2024-01-30 01:55:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 66%|█████████████████████████████████████████████████████████████████████▉                                    | 192/291 [01:28<00:32,  3.02it/s]
                                                                                                                                                 
[2024-01-30 01:55:57] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 66%|█████████████████████████████████████████████████████████████████████▉                                    | 192/291 [01:28<00:32,  3.02it/s]
 67%|██████████████████████████████████████████████████████████████████████▋                                   | 194/291 [01:28<00:29,  3.24it/s]
                                                                                                                                                 
[2024-01-30 01:55:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 67%|██████████████████████████████████████████████████████████████████████▋                                   | 194/291 [01:30<00:29,  3.24it/s]
                                                                                                                                                 
[2024-01-30 01:55:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 67%|██████████████████████████████████████████████████████████████████████▋                                   | 194/291 [01:30<00:29,  3.24it/s]
 67%|███████████████████████████████████████████████████████████████████████                                   | 195/291 [01:30<00:51,  1.88it/s]
                                                                                                                                                 
[2024-01-30 01:55:59] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.25.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 67%|███████████████████████████████████████████████████████████████████████                                   | 195/291 [01:30<00:51,  1.88it/s]
                                                                                                                                                 
[2024-01-30 01:55:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 67%|███████████████████████████████████████████████████████████████████████                                   | 195/291 [01:30<00:51,  1.88it/s]
                                                                                                                                                 
[2024-01-30 01:55:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 67%|███████████████████████████████████████████████████████████████████████                                   | 195/291 [01:30<00:51,  1.88it/s]
 68%|███████████████████████████████████████████████████████████████████████▊                                  | 197/291 [01:30<00:35,  2.61it/s]
                                                                                                                                                 
[2024-01-30 01:55:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 68%|███████████████████████████████████████████████████████████████████████▊                                  | 197/291 [01:30<00:35,  2.61it/s]
                                                                                                                                                 
[2024-01-30 01:55:59] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.25.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 68%|███████████████████████████████████████████████████████████████████████▊                                  | 197/291 [01:30<00:35,  2.61it/s]
 68%|████████████████████████████████████████████████████████████████████████                                  | 198/291 [01:30<00:31,  2.93it/s]
                                                                                                                                                 
[2024-01-30 01:55:59] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.26.input_layernorm.weight", shape: (8192,), dtype: float16
+
 68%|████████████████████████████████████████████████████████████████████████                                  | 198/291 [01:30<00:31,  2.93it/s]
                                                                                                                                                 
[2024-01-30 01:56:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 68%|████████████████████████████████████████████████████████████████████████                                  | 198/291 [01:31<00:31,  2.93it/s]
                                                                                                                                                 
[2024-01-30 01:56:00] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 68%|████████████████████████████████████████████████████████████████████████                                  | 198/291 [01:31<00:31,  2.93it/s]
 69%|████████████████████████████████████████████████████████████████████████▊                                 | 200/291 [01:31<00:28,  3.19it/s]
                                                                                                                                                 
[2024-01-30 01:56:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 69%|████████████████████████████████████████████████████████████████████████▊                                 | 200/291 [01:32<00:28,  3.19it/s]
                                                                                                                                                 
[2024-01-30 01:56:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 69%|████████████████████████████████████████████████████████████████████████▊                                 | 200/291 [01:32<00:28,  3.19it/s]
 69%|█████████████████████████████████████████████████████████████████████████▏                                | 201/291 [01:32<00:48,  1.86it/s]
                                                                                                                                                 
[2024-01-30 01:56:01] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.26.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 69%|█████████████████████████████████████████████████████████████████████████▏                                | 201/291 [01:32<00:48,  1.86it/s]
                                                                                                                                                 
[2024-01-30 01:56:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 69%|█████████████████████████████████████████████████████████████████████████▏                                | 201/291 [01:32<00:48,  1.86it/s]
                                                                                                                                                 
[2024-01-30 01:56:01] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 69%|█████████████████████████████████████████████████████████████████████████▏                                | 201/291 [01:32<00:48,  1.86it/s]
 70%|█████████████████████████████████████████████████████████████████████████▉                                | 203/291 [01:32<00:33,  2.59it/s]
                                                                                                                                                 
[2024-01-30 01:56:02] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 70%|█████████████████████████████████████████████████████████████████████████▉                                | 203/291 [01:33<00:33,  2.59it/s]
                                                                                                                                                 
[2024-01-30 01:56:02] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.26.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 70%|█████████████████████████████████████████████████████████████████████████▉                                | 203/291 [01:33<00:33,  2.59it/s]
 70%|██████████████████████████████████████████████████████████████████████████▎                               | 204/291 [01:33<00:29,  2.91it/s]
                                                                                                                                                 
[2024-01-30 01:56:03] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 70%|██████████████████████████████████████████████████████████████████████████▎                               | 204/291 [01:34<00:29,  2.91it/s]
                                                                                                                                                 
[2024-01-30 01:56:03] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 70%|██████████████████████████████████████████████████████████████████████████▎                               | 204/291 [01:34<00:29,  2.91it/s]
 70%|██████████████████████████████████████████████████████████████████████████▋                               | 205/291 [01:34<00:49,  1.74it/s]
                                                                                                                                                 
[2024-01-30 01:56:03] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 70%|██████████████████████████████████████████████████████████████████████████▋                               | 205/291 [01:34<00:49,  1.74it/s]
                                                                                                                                                 
[2024-01-30 01:56:03] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 70%|██████████████████████████████████████████████████████████████████████████▋                               | 205/291 [01:34<00:49,  1.74it/s]
 71%|███████████████████████████████████████████████████████████████████████████                               | 206/291 [01:34<00:42,  2.01it/s]
                                                                                                                                                 
[2024-01-30 01:56:03] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 71%|███████████████████████████████████████████████████████████████████████████                               | 206/291 [01:34<00:42,  2.01it/s]
                                                                                                                                                 
[2024-01-30 01:56:03] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 71%|███████████████████████████████████████████████████████████████████████████                               | 206/291 [01:34<00:42,  2.01it/s]
 71%|███████████████████████████████████████████████████████████████████████████▍                              | 207/291 [01:34<00:35,  2.40it/s]
                                                                                                                                                 
[2024-01-30 01:56:03] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/pytorch_model-00004-of-00007.bin
+
 71%|███████████████████████████████████████████████████████████████████████████▍                              | 207/291 [01:34<00:35,  2.40it/s]
                                                                                                                                                 
[2024-01-30 01:56:04] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/pytorch_model-00005-of-00007.bin
+
 71%|███████████████████████████████████████████████████████████████████████████▍                              | 207/291 [01:35<00:35,  2.40it/s]
                                                                                                                                                 
[2024-01-30 01:56:07] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.27.input_layernorm.weight", shape: (8192,), dtype: float16
+
 71%|███████████████████████████████████████████████████████████████████████████▍                              | 207/291 [01:38<00:35,  2.40it/s]
 71%|███████████████████████████████████████████████████████████████████████████▊                              | 208/291 [01:38<01:40,  1.21s/it]
                                                                                                                                                 
[2024-01-30 01:56:07] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 71%|███████████████████████████████████████████████████████████████████████████▊                              | 208/291 [01:38<01:40,  1.21s/it]
                                                                                                                                                 
[2024-01-30 01:56:07] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.27.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 71%|███████████████████████████████████████████████████████████████████████████▊                              | 208/291 [01:38<01:40,  1.21s/it]
 72%|████████████████████████████████████████████████████████████████████████████▏                             | 209/291 [01:38<01:22,  1.01s/it]
                                                                                                                                                 
[2024-01-30 01:56:07] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.27.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 72%|████████████████████████████████████████████████████████████████████████████▏                             | 209/291 [01:38<01:22,  1.01s/it]
                                                                                                                                                 
[2024-01-30 01:56:07] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.28.input_layernorm.weight", shape: (8192,), dtype: float16
+
 72%|████████████████████████████████████████████████████████████████████████████▏                             | 209/291 [01:38<01:22,  1.01s/it]
                                                                                                                                                 
[2024-01-30 01:56:08] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 72%|████████████████████████████████████████████████████████████████████████████▏                             | 209/291 [01:39<01:22,  1.01s/it]
                                                                                                                                                 
[2024-01-30 01:56:08] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 72%|████████████████████████████████████████████████████████████████████████████▏                             | 209/291 [01:39<01:22,  1.01s/it]
 73%|█████████████████████████████████████████████████████████████████████████████▏                            | 212/291 [01:39<00:43,  1.82it/s]
                                                                                                                                                 
[2024-01-30 01:56:09] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 73%|█████████████████████████████████████████████████████████████████████████████▏                            | 212/291 [01:40<00:43,  1.82it/s]
                                                                                                                                                 
[2024-01-30 01:56:09] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 73%|█████████████████████████████████████████████████████████████████████████████▏                            | 212/291 [01:40<00:43,  1.82it/s]
 73%|█████████████████████████████████████████████████████████████████████████████▌                            | 213/291 [01:40<00:55,  1.41it/s]
                                                                                                                                                 
[2024-01-30 01:56:09] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.28.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 73%|█████████████████████████████████████████████████████████████████████████████▌                            | 213/291 [01:40<00:55,  1.41it/s]
                                                                                                                                                 
[2024-01-30 01:56:09] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 73%|█████████████████████████████████████████████████████████████████████████████▌                            | 213/291 [01:40<00:55,  1.41it/s]
                                                                                                                                                 
[2024-01-30 01:56:09] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 73%|█████████████████████████████████████████████████████████████████████████████▌                            | 213/291 [01:40<00:55,  1.41it/s]
 74%|██████████████████████████████████████████████████████████████████████████████▎                           | 215/291 [01:40<00:37,  2.01it/s]
                                                                                                                                                 
[2024-01-30 01:56:09] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 74%|██████████████████████████████████████████████████████████████████████████████▎                           | 215/291 [01:41<00:37,  2.01it/s]
                                                                                                                                                 
[2024-01-30 01:56:09] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.28.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 74%|██████████████████████████████████████████████████████████████████████████████▎                           | 215/291 [01:41<00:37,  2.01it/s]
 74%|██████████████████████████████████████████████████████████████████████████████▋                           | 216/291 [01:41<00:32,  2.31it/s]
                                                                                                                                                 
[2024-01-30 01:56:09] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.29.input_layernorm.weight", shape: (8192,), dtype: float16
+
 74%|██████████████████████████████████████████████████████████████████████████████▋                           | 216/291 [01:41<00:32,  2.31it/s]
                                                                                                                                                 
[2024-01-30 01:56:10] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 74%|██████████████████████████████████████████████████████████████████████████████▋                           | 216/291 [01:41<00:32,  2.31it/s]
                                                                                                                                                 
[2024-01-30 01:56:10] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 74%|██████████████████████████████████████████████████████████████████████████████▋                           | 216/291 [01:41<00:32,  2.31it/s]
 75%|███████████████████████████████████████████████████████████████████████████████▍                          | 218/291 [01:41<00:26,  2.76it/s]
                                                                                                                                                 
[2024-01-30 01:56:11] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 75%|███████████████████████████████████████████████████████████████████████████████▍                          | 218/291 [01:42<00:26,  2.76it/s]
                                                                                                                                                 
[2024-01-30 01:56:11] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 75%|███████████████████████████████████████████████████████████████████████████████▍                          | 218/291 [01:42<00:26,  2.76it/s]
 75%|███████████████████████████████████████████████████████████████████████████████▊                          | 219/291 [01:42<00:39,  1.83it/s]
                                                                                                                                                 
[2024-01-30 01:56:11] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.29.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 75%|███████████████████████████████████████████████████████████████████████████████▊                          | 219/291 [01:42<00:39,  1.83it/s]
                                                                                                                                                 
[2024-01-30 01:56:11] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 75%|███████████████████████████████████████████████████████████████████████████████▊                          | 219/291 [01:43<00:39,  1.83it/s]
                                                                                                                                                 
[2024-01-30 01:56:11] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 75%|███████████████████████████████████████████████████████████████████████████████▊                          | 219/291 [01:43<00:39,  1.83it/s]
 76%|████████████████████████████████████████████████████████████████████████████████▌                         | 221/291 [01:43<00:27,  2.55it/s]
                                                                                                                                                 
[2024-01-30 01:56:12] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 76%|████████████████████████████████████████████████████████████████████████████████▌                         | 221/291 [01:43<00:27,  2.55it/s]
                                                                                                                                                 
[2024-01-30 01:56:12] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.29.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 76%|████████████████████████████████████████████████████████████████████████████████▌                         | 221/291 [01:43<00:27,  2.55it/s]
 76%|████████████████████████████████████████████████████████████████████████████████▊                         | 222/291 [01:43<00:24,  2.87it/s]
                                                                                                                                                 
[2024-01-30 01:56:12] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.30.input_layernorm.weight", shape: (8192,), dtype: float16
+
 76%|████████████████████████████████████████████████████████████████████████████████▊                         | 222/291 [01:43<00:24,  2.87it/s]
                                                                                                                                                 
[2024-01-30 01:56:12] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 76%|████████████████████████████████████████████████████████████████████████████████▊                         | 222/291 [01:43<00:24,  2.87it/s]
                                                                                                                                                 
[2024-01-30 01:56:12] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 76%|████████████████████████████████████████████████████████████████████████████████▊                         | 222/291 [01:43<00:24,  2.87it/s]
 77%|█████████████████████████████████████████████████████████████████████████████████▌                        | 224/291 [01:43<00:21,  3.15it/s]
                                                                                                                                                 
[2024-01-30 01:56:13] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 77%|█████████████████████████████████████████████████████████████████████████████████▌                        | 224/291 [01:44<00:21,  3.15it/s]
                                                                                                                                                 
[2024-01-30 01:56:13] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 77%|█████████████████████████████████████████████████████████████████████████████████▌                        | 224/291 [01:45<00:21,  3.15it/s]
 77%|█████████████████████████████████████████████████████████████████████████████████▉                        | 225/291 [01:45<00:33,  1.97it/s]
                                                                                                                                                 
[2024-01-30 01:56:13] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.30.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 77%|█████████████████████████████████████████████████████████████████████████████████▉                        | 225/291 [01:45<00:33,  1.97it/s]
                                                                                                                                                 
[2024-01-30 01:56:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 77%|█████████████████████████████████████████████████████████████████████████████████▉                        | 225/291 [01:45<00:33,  1.97it/s]
                                                                                                                                                 
[2024-01-30 01:56:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 77%|█████████████████████████████████████████████████████████████████████████████████▉                        | 225/291 [01:45<00:33,  1.97it/s]
 78%|██████████████████████████████████████████████████████████████████████████████████▋                       | 227/291 [01:45<00:23,  2.72it/s]
                                                                                                                                                 
[2024-01-30 01:56:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 78%|██████████████████████████████████████████████████████████████████████████████████▋                       | 227/291 [01:45<00:23,  2.72it/s]
                                                                                                                                                 
[2024-01-30 01:56:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.30.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 78%|██████████████████████████████████████████████████████████████████████████████████▋                       | 227/291 [01:45<00:23,  2.72it/s]
 78%|███████████████████████████████████████████████████████████████████████████████████                       | 228/291 [01:45<00:20,  3.03it/s]
                                                                                                                                                 
[2024-01-30 01:56:14] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.31.input_layernorm.weight", shape: (8192,), dtype: float16
+
 78%|███████████████████████████████████████████████████████████████████████████████████                       | 228/291 [01:45<00:20,  3.03it/s]
                                                                                                                                                 
[2024-01-30 01:56:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 78%|███████████████████████████████████████████████████████████████████████████████████                       | 228/291 [01:45<00:20,  3.03it/s]
                                                                                                                                                 
[2024-01-30 01:56:14] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 78%|███████████████████████████████████████████████████████████████████████████████████                       | 228/291 [01:45<00:20,  3.03it/s]
 79%|███████████████████████████████████████████████████████████████████████████████████▊                      | 230/291 [01:46<00:18,  3.27it/s]
                                                                                                                                                 
[2024-01-30 01:56:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 79%|███████████████████████████████████████████████████████████████████████████████████▊                      | 230/291 [01:47<00:18,  3.27it/s]
                                                                                                                                                 
[2024-01-30 01:56:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 79%|███████████████████████████████████████████████████████████████████████████████████▊                      | 230/291 [01:47<00:18,  3.27it/s]
 79%|████████████████████████████████████████████████████████████████████████████████████▏                     | 231/291 [01:47<00:32,  1.87it/s]
                                                                                                                                                 
[2024-01-30 01:56:16] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.31.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 79%|████████████████████████████████████████████████████████████████████████████████████▏                     | 231/291 [01:47<00:32,  1.87it/s]
                                                                                                                                                 
[2024-01-30 01:56:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 79%|██████████████████████████████████████████████████████████��█████████████████████████▏                     | 231/291 [01:47<00:32,  1.87it/s]
                                                                                                                                                 
[2024-01-30 01:56:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 79%|████████████████████████████████████████████████████████████████████████████████████▏                     | 231/291 [01:47<00:32,  1.87it/s]
 80%|████████████████████████████████████████████████████████████████████████████████████▊                     | 233/291 [01:47<00:22,  2.61it/s]
                                                                                                                                                 
[2024-01-30 01:56:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 80%|████████████████████████████████████████████████████████████████████████████████████▊                     | 233/291 [01:47<00:22,  2.61it/s]
                                                                                                                                                 
[2024-01-30 01:56:16] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.31.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 80%|████████████████████████████████████████████████████████████████████████████████████▊                     | 233/291 [01:47<00:22,  2.61it/s]
 80%|█████████████████████████████████████████████████████████████████████████████████████▏                    | 234/291 [01:47<00:19,  2.93it/s]
                                                                                                                                                 
[2024-01-30 01:56:16] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.32.input_layernorm.weight", shape: (8192,), dtype: float16
+
 80%|█████████████████████████████████████████████████████████████████████████████████████▏                    | 234/291 [01:47<00:19,  2.93it/s]
                                                                                                                                                 
[2024-01-30 01:56:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.32.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 80%|█████████████████████████████████████████████████████████████████████████████████████▏                    | 234/291 [01:48<00:19,  2.93it/s]
                                                                                                                                                 
[2024-01-30 01:56:17] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.32.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 80%|█████████████████████████████████████████████████████████████████████████████████████▏                    | 234/291 [01:48<00:19,  2.93it/s]
 81%|█████████████████████████████████████████████████████████████████████████████████████▉                    | 236/291 [01:48<00:17,  3.20it/s]
                                                                                                                                                 
[2024-01-30 01:56:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.32.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 81%|█████████████████████████████████████████████████████████████████████████████████████▉                    | 236/291 [01:49<00:17,  3.20it/s]
                                                                                                                                                 
[2024-01-30 01:56:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.32.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 81%|█████████████████████████████████████████████████████████████████████████████████████▉                    | 236/291 [01:49<00:17,  3.20it/s]
 81%|██████████████████████████████████████████████████████████████████████████████████████▎                   | 237/291 [01:49<00:28,  1.86it/s]
                                                                                                                                                 
[2024-01-30 01:56:18] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.32.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 81%|██████████████████████████████████████████████████████████████████████████████████████▎                   | 237/291 [01:49<00:28,  1.86it/s]
                                                                                                                                                 
[2024-01-30 01:56:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.32.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 81%|██████████████████████████████████████████████████████████████████████████████████████▎                   | 237/291 [01:49<00:28,  1.86it/s]
                                                                                                                                                 
[2024-01-30 01:56:18] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.32.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 81%|██████████████████████████████████████████████████████████████████████████████████████▎                   | 237/291 [01:49<00:28,  1.86it/s]
 82%|███████████████████████████████████████████████████████████████████████████████████████                   | 239/291 [01:49<00:19,  2.61it/s]
                                                                                                                                                 
[2024-01-30 01:56:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.32.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 82%|███████████████████████████████████████████████████████████████████████████████████████                   | 239/291 [01:50<00:19,  2.61it/s]
                                                                                                                                                 
[2024-01-30 01:56:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.32.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 82%|███████████████████████████████████████████████████████████████████████████████████████                   | 239/291 [01:50<00:19,  2.61it/s]
 82%|███████████████████████████████████████████████████████████████████████████████████████▍                  | 240/291 [01:50<00:17,  2.93it/s]
                                                                                                                                                 
[2024-01-30 01:56:19] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.33.input_layernorm.weight", shape: (8192,), dtype: float16
+
 82%|███████████████████████████████████████████████████████████████████████████████████████▍                  | 240/291 [01:50<00:17,  2.93it/s]
                                                                                                                                                 
[2024-01-30 01:56:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.33.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 82%|███████████████████████████████████████████████████████████████████████████████████████▍                  | 240/291 [01:50<00:17,  2.93it/s]
                                                                                                                                                 
[2024-01-30 01:56:19] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.33.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 82%|███████████████████████████████████████████████████████████████████████████████████████▍                  | 240/291 [01:50<00:17,  2.93it/s]
 83%|████████████████████████████████████████████████████████████████████████████████████████▏                 | 242/291 [01:50<00:15,  3.20it/s]
                                                                                                                                                 
[2024-01-30 01:56:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.33.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 83%|████████████████████████████████████████████████████████████████████████████████████████▏                 | 242/291 [01:52<00:15,  3.20it/s]
                                                                                                                                                 
[2024-01-30 01:56:20] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.33.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 83%|████████████████████████████████████████████████████████████████████████████████████████▏                 | 242/291 [01:52<00:15,  3.20it/s]
 84%|████████████████████████████████████████████████████████████████████████████████████████▌                 | 243/291 [01:52<00:25,  1.88it/s]
                                                                                                                                                 
[2024-01-30 01:56:20] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.33.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 84%|████████████████████████████████████████████████████████████████████████████████████████▌                 | 243/291 [01:52<00:25,  1.88it/s]
                                                                                                                                                 
[2024-01-30 01:56:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.33.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 84%|████████████████████████████████████████████████████████████████████████████████████████▌                 | 243/291 [01:52<00:25,  1.88it/s]
                                                                                                                                                 
[2024-01-30 01:56:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.33.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 84%|████████████████████████████████████████████████████████████████████████████████████████▌                 | 243/291 [01:52<00:25,  1.88it/s]
 84%|█████████████████████████████████████████████████████████████████████████████████████████▏                | 245/291 [01:52<00:17,  2.62it/s]
                                                                                                                                                 
[2024-01-30 01:56:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.33.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 84%|█████████████████████████████████████████████████████████████████████████████████████████▏                | 245/291 [01:52<00:17,  2.62it/s]
                                                                                                                                                 
[2024-01-30 01:56:21] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.33.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 84%|█████████████████████████████████████████████████████████████████████████████████████████▏                | 245/291 [01:52<00:17,  2.62it/s]
 85%|█████████████████████████████████████████████████████████████████████████████████████████▌                | 246/291 [01:52<00:15,  2.94it/s]
                                                                                                                                                 
[2024-01-30 01:56:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.34.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 85%|█████████████████████████████████████████████████████████████████████████████████████████▌                | 246/291 [01:53<00:15,  2.94it/s]
                                                                                                                                                 
[2024-01-30 01:56:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.34.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 85%|█████████████████████████████████████████████████████████████████████████████████████████▌                | 246/291 [01:53<00:15,  2.94it/s]
 85%|█████████████████████████████████████████████████████████████████████████████████████████▉                | 247/291 [01:53<00:24,  1.77it/s]
                                                                                                                                                 
[2024-01-30 01:56:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.34.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 85%|█████████████████████████████████████████████████████████████████████████████████████████▉                | 247/291 [01:54<00:24,  1.77it/s]
                                                                                                                                                 
[2024-01-30 01:56:22] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.34.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 85%|█████████████████████████████████████████████████████████████████████████████████████████▉                | 247/291 [01:54<00:24,  1.77it/s]
 85%|██████████████████████████████████████████████████████████████████████████████████████████▎               | 248/291 [01:54<00:21,  2.03it/s]
                                                                                                                                                 
[2024-01-30 01:56:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.34.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 85%|██████████████████████████████████████████████████████████████████████████████████████████▎               | 248/291 [01:54<00:21,  2.03it/s]
                                                                                                                                                 
[2024-01-30 01:56:23] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.34.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 85%|██████████████████████████████████████████████████████████████████████████████████████████▎               | 248/291 [01:54<00:21,  2.03it/s]
 86%|██████████████████████████████████████████████████████████████████████████████████████████▋               | 249/291 [01:54<00:17,  2.43it/s]
                                                                                                                                                 
[2024-01-30 01:56:23] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/pytorch_model-00005-of-00007.bin
+
 86%|██████████████████████████████████████████████████████████████████████████████████████████▋               | 249/291 [01:54<00:17,  2.43it/s]
                                                                                                                                                 
[2024-01-30 01:56:23] INFO huggingface_loader.py:169: Loading HF parameters from: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/pytorch_model-00006-of-00007.bin
+
 86%|██████████████████████████████████████████████████████████████████████████████████████████▋               | 249/291 [01:54<00:17,  2.43it/s]
                                                                                                                                                 
[2024-01-30 01:56:26] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.34.input_layernorm.weight", shape: (8192,), dtype: float16
+
 86%|██████████████████████████████████████████████████████████████████████████████████████████▋               | 249/291 [01:57<00:17,  2.43it/s]
 86%|███████████████████████████████████████████████████████████████████████████████████████████               | 250/291 [01:57<00:49,  1.20s/it]
                                                                                                                                                 
[2024-01-30 01:56:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.34.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 86%|███████████████████████████████████████████████████████████████████████████████████████████               | 250/291 [01:58<00:49,  1.20s/it]
                                                                                                                                                 
[2024-01-30 01:56:26] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.34.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 86%|███████████████████████████████████████████████████████████████████████████████████████████               | 250/291 [01:58<00:49,  1.20s/it]
 86%|███████████████████████████████████████████████████████████████████████████████████████████▍              | 251/291 [01:58<00:40,  1.00s/it]
                                                                                                                                                 
[2024-01-30 01:56:26] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.34.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 86%|███████████████████████████████████████████████████████████████████████████████████████████▍              | 251/291 [01:58<00:40,  1.00s/it]
                                                                                                                                                 
[2024-01-30 01:56:26] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.35.input_layernorm.weight", shape: (8192,), dtype: float16
+
 86%|███████████████████████████████████████████████████████████████████████████████████████████▍              | 251/291 [01:58<00:40,  1.00s/it]
                                                                                                                                                 
[2024-01-30 01:56:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.35.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 86%|███████████████████████████████████████████████████████████████████████████████████████████▍              | 251/291 [01:58<00:40,  1.00s/it]
                                                                                                                                                 
[2024-01-30 01:56:27] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.35.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 86%|███████████████████████████████████████████████████████████████████████████████████████████▍              | 251/291 [01:58<00:40,  1.00s/it]
 87%|████████████████████████████████████████████████████████████████████████████████████████████▌             | 254/291 [01:58<00:20,  1.83it/s]
                                                                                                                                                 
[2024-01-30 01:56:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.35.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 87%|████████████████████████████████████████████████████████████████████████████████████████████▌             | 254/291 [01:59<00:20,  1.83it/s]
                                                                                                                                                 
[2024-01-30 01:56:28] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.35.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 87%|█████████████████████████████████████████████████████████████████████████��██████████████████▌             | 254/291 [01:59<00:20,  1.83it/s]
 88%|████████████████████████████████████████████████████████████████████████████████████████████▉             | 255/291 [01:59<00:25,  1.41it/s]
                                                                                                                                                 
[2024-01-30 01:56:28] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.35.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 88%|████████████████████████████████████████████████████████████████████████████████████████████▉             | 255/291 [01:59<00:25,  1.41it/s]
                                                                                                                                                 
[2024-01-30 01:56:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.35.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 88%|████████████████████████████████████████████████████████████████████████████████████████████▉             | 255/291 [02:00<00:25,  1.41it/s]
                                                                                                                                                 
[2024-01-30 01:56:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.35.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 88%|████████████████████████████████████████████████████████████████████████████████████████████▉             | 255/291 [02:00<00:25,  1.41it/s]
 88%|█████████████████████████████████████████████████████████████████████████████████████████████▌            | 257/291 [02:00<00:16,  2.02it/s]
                                                                                                                                                 
[2024-01-30 01:56:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.35.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 88%|█████████████████████████████████████████████████████████████████████████████████████████████▌            | 257/291 [02:00<00:16,  2.02it/s]
                                                                                                                                                 
[2024-01-30 01:56:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.35.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 88%|█████████████████████████████████████████████████████████████████████████████████████████████▌            | 257/291 [02:00<00:16,  2.02it/s]
 89%|█████████████████████████████████████████████████████████████████████████████████████████████▉            | 258/291 [02:00<00:14,  2.32it/s]
                                                                                                                                                 
[2024-01-30 01:56:29] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.36.input_layernorm.weight", shape: (8192,), dtype: float16
+
 89%|█████████████████████████████████████████████████████████████████████████████████████████████▉            | 258/291 [02:00<00:14,  2.32it/s]
                                                                                                                                                 
[2024-01-30 01:56:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.36.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 89%|█████████████████████████████████████████████████████████████████████████████████████████████▉            | 258/291 [02:00<00:14,  2.32it/s]
                                                                                                                                                 
[2024-01-30 01:56:29] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.36.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 89%|█████████████████████████████████████████████████████████████████████████████████████████████▉            | 258/291 [02:00<00:14,  2.32it/s]
 89%|██████████████████████████████████████████████████████████████████████████████████████████████▋           | 260/291 [02:00<00:11,  2.77it/s]
                                                                                                                                                 
[2024-01-30 01:56:30] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.36.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 89%|██████████████████████████████████████████████████████████████████████████████████████████████▋           | 260/291 [02:02<00:11,  2.77it/s]
                                                                                                                                                 
[2024-01-30 01:56:30] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.36.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 89%|██████████████████████████████████████████████████████████████████████████████████████████████▋           | 260/291 [02:02<00:11,  2.77it/s]
 90%|███████████████████████████████████████████████████████████████████████████████████████████████           | 261/291 [02:02<00:16,  1.84it/s]
                                                                                                                                                 
[2024-01-30 01:56:30] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.36.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 90%|███████████████████████████████████████████████████████████████████████████████████████████████           | 261/291 [02:02<00:16,  1.84it/s]
                                                                                                                                                 
[2024-01-30 01:56:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.36.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 90%|███████████████████████████████████████████████████████████████████████████████████████████████           | 261/291 [02:02<00:16,  1.84it/s]
                                                                                                                                                 
[2024-01-30 01:56:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.36.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 90%|███████████████████████████████████████████████████████████████████████████████████████████████           | 261/291 [02:02<00:16,  1.84it/s]
 90%|███████████████████████████████████████████████████████████████████████████████████████████████▊          | 263/291 [02:02<00:10,  2.57it/s]
                                                                                                                                                 
[2024-01-30 01:56:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.36.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 90%|███████████████████████████████████████████████████████████████████████████████████████████████▊          | 263/291 [02:02<00:10,  2.57it/s]
                                                                                                                                                 
[2024-01-30 01:56:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.36.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 90%|███████████████████████████████████████████████████████████████████████████████████████████████▊          | 263/291 [02:02<00:10,  2.57it/s]
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▏         | 264/291 [02:02<00:09,  2.88it/s]
                                                                                                                                                 
[2024-01-30 01:56:31] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.37.input_layernorm.weight", shape: (8192,), dtype: float16
+
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▏         | 264/291 [02:02<00:09,  2.88it/s]
                                                                                                                                                 
[2024-01-30 01:56:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.37.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▏         | 264/291 [02:03<00:09,  2.88it/s]
                                                                                                                                                 
[2024-01-30 01:56:31] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.37.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▏         | 264/291 [02:03<00:09,  2.88it/s]
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▉         | 266/291 [02:03<00:07,  3.15it/s]
                                                                                                                                                 
[2024-01-30 01:56:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.37.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▉         | 266/291 [02:04<00:07,  3.15it/s]
                                                                                                                                                 
[2024-01-30 01:56:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.37.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 91%|████████████████████████████████████████████████████████████████████████████████████████████████▉         | 266/291 [02:04<00:07,  3.15it/s]
 92%|█████████████████████████████████████████████████████████████████████████████████████████████████▎        | 267/291 [02:04<00:12,  1.94it/s]
                                                                                                                                                 
[2024-01-30 01:56:33] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.37.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 92%|█████████████████████████████████████████████████████████████████████████████████████████████████▎        | 267/291 [02:04<00:12,  1.94it/s]
                                                                                                                                                 
[2024-01-30 01:56:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.37.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 92%|█████████████████████████████████████████████████████████████████████████████████████████████████▎        | 267/291 [02:04<00:12,  1.94it/s]
                                                                                                                                                 
[2024-01-30 01:56:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.37.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 92%|█████████████████████████████████████████████████████████████████████████████████████████████████▎        | 267/291 [02:04<00:12,  1.94it/s]
 92%|█████████████████████████████████████████████████████████████████████████████████████████████████▉        | 269/291 [02:04<00:08,  2.68it/s]
                                                                                                                                                 
[2024-01-30 01:56:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.37.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 92%|█████████████████████████████████████████████████████████████████████████████████████████████████▉        | 269/291 [02:04<00:08,  2.68it/s]
                                                                                                                                                 
[2024-01-30 01:56:33] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.37.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 92%|█████████████████████████████████████████████████████████████████████████████████████████████████▉        | 269/291 [02:04<00:08,  2.68it/s]
 93%|██████████████████████████████████████████████████████████████████████████████████████████████████▎       | 270/291 [02:04<00:07,  2.99it/s]
                                                                                                                                                 
[2024-01-30 01:56:33] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.38.input_layernorm.weight", shape: (8192,), dtype: float16
+
 93%|██████████████████████████████████████████████████████████████████████████████████████████████████▎       | 270/291 [02:04<00:07,  2.99it/s]
                                                                                                                                                 
[2024-01-30 01:56:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.38.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 93%|██████████████████████████████████████████████████████████████████████████████████████████████████▎       | 270/291 [02:05<00:07,  2.99it/s]
                                                                                                                                                 
[2024-01-30 01:56:34] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.38.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 93%|██████████████████████████████████████████████████████████████████████████████████████████████████▎       | 270/291 [02:05<00:07,  2.99it/s]
 93%|███████████████████████████████████████████████████████████████████████████████████████████████████       | 272/291 [02:05<00:05,  3.23it/s]
                                                                                                                                                 
[2024-01-30 01:56:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.38.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 93%|███████████████████████████████████████████████████████████████████████████████████████████████████       | 272/291 [02:06<00:05,  3.23it/s]
                                                                                                                                                 
[2024-01-30 01:56:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.38.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 93%|███████████████████████████████████████████████████████████████████████████████████████████████████       | 272/291 [02:06<00:05,  3.23it/s]
 94%|███████████████████████████████████████████████████████████████████████████████████████████████████▍      | 273/291 [02:06<00:09,  1.90it/s]
                                                                                                                                                 
[2024-01-30 01:56:35] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.38.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 94%|███████████████████████████████████████████████████████████████████████████████████████████████████▍      | 273/291 [02:06<00:09,  1.90it/s]
                                                                                                                                                 
[2024-01-30 01:56:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.38.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 94%|███████████████████████████████████████████████████████████████████████████████████████████████████▍      | 273/291 [02:06<00:09,  1.90it/s]
                                                                                                                                                 
[2024-01-30 01:56:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.38.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 94%|███████████████████████████████████████████████████████████████████████████████████████████████████▍      | 273/291 [02:06<00:09,  1.90it/s]
 95%|████████████████████████████████████████████████████████████████████████████████████████████████████▏     | 275/291 [02:06<00:06,  2.64it/s]
                                                                                                                                                 
[2024-01-30 01:56:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.38.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 95%|████████████████████████████████████████████████████████████████████████████████████████████████████▏     | 275/291 [02:07<00:06,  2.64it/s]
                                                                                                                                                 
[2024-01-30 01:56:35] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.38.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 95%|████████████████████████████████████████████████████████████████████████████████████████████████████▏     | 275/291 [02:07<00:06,  2.64it/s]
 95%|████████████████████████████████████████████████████████████████████████████████████████████████████▌     | 276/291 [02:07<00:05,  2.95it/s]
                                                                                                                                                 
[2024-01-30 01:56:35] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.39.input_layernorm.weight", shape: (8192,), dtype: float16
+
 95%|████████████████████████████████████████████████████████████████████████████████████████████████████▌     | 276/291 [02:07<00:05,  2.95it/s]
                                                                                                                                                 
[2024-01-30 01:56:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.39.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 95%|████████████████████████████████████████████████████████████████████████████████████████████████████▌     | 276/291 [02:07<00:05,  2.95it/s]
                                                                                                                                                 
[2024-01-30 01:56:36] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.39.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 95%|████████████████████████████████████████████████████████████████████████████████████████████████████▌     | 276/291 [02:07<00:05,  2.95it/s]
 96%|█████████████████████████████████████████████████████████████████████████████████████████████████████▎    | 278/291 [02:07<00:04,  3.21it/s]
                                                                                                                                                 
[2024-01-30 01:56:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.39.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 96%|████��████████████████████████████████████████████████████████████████████████████████████████████████▎    | 278/291 [02:08<00:04,  3.21it/s]
                                                                                                                                                 
[2024-01-30 01:56:37] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.39.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 96%|█████████████████████████████████████████████████████████████████████████████████████████████████████▎    | 278/291 [02:09<00:04,  3.21it/s]
 96%|█████████████████████████████████████████████████████████████████████████████████████████████████████▋    | 279/291 [02:09<00:06,  1.87it/s]
                                                                                                                                                 
[2024-01-30 01:56:37] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.39.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 96%|█████████████████████████████████████████████████████████████████████████████████████████████████████▋    | 279/291 [02:09<00:06,  1.87it/s]
                                                                                                                                                 
[2024-01-30 01:56:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.39.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 96%|█████████████████████████████████████████████████████████████████████████████████████████████████████▋    | 279/291 [02:09<00:06,  1.87it/s]
                                                                                                                                                 
[2024-01-30 01:56:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.39.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 96%|█████████████████████████████████████████████████████████████████████████████████████████████████████▋    | 279/291 [02:09<00:06,  1.87it/s]
 97%|██████████████████████████████████████████████████████████████████████████████████████████████████████▎   | 281/291 [02:09<00:03,  2.61it/s]
                                                                                                                                                 
[2024-01-30 01:56:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.39.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 97%|██████████████████████████████████████████████████████████████████████████████████████████████████████▎   | 281/291 [02:09<00:03,  2.61it/s]
                                                                                                                                                 
[2024-01-30 01:56:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.39.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 97%|██████████████████████████████████████████████████████████████████████████████████████████████████████▎   | 281/291 [02:09<00:03,  2.61it/s]
 97%|██████████████████████████████████████████████████████████████████████████████████████████████████████▋   | 282/291 [02:09<00:03,  2.93it/s]
                                                                                                                                                 
[2024-01-30 01:56:38] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.40.input_layernorm.weight", shape: (8192,), dtype: float16
+
 97%|██████████████████████████████████████████████████████████████████████████████████████████████████████▋   | 282/291 [02:09<00:03,  2.93it/s]
                                                                                                                                                 
[2024-01-30 01:56:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.40.mlp.down_proj.q_weight", shape: (8192, 2752), dtype: uint32
+
 97%|██████████████████████████████████████████████████████████████████████████████████████████████████████▋   | 282/291 [02:09<00:03,  2.93it/s]
                                                                                                                                                 
[2024-01-30 01:56:38] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.40.mlp.down_proj.q_scale", shape: (8192, 688), dtype: float16
+
 97%|██████████████████████████████████████████████████████████████████████████████████████████████████████▋   | 282/291 [02:09<00:03,  2.93it/s]
 98%|███████████████████████████████████████████████████████████████████████████████████████████████████████▍  | 284/291 [02:10<00:02,  3.19it/s]
                                                                                                                                                 
[2024-01-30 01:56:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.40.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 98%|███████████████████████████████████████████████████████████████████████████████████████████████████████▍  | 284/291 [02:11<00:02,  3.19it/s]
                                                                                                                                                 
[2024-01-30 01:56:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.40.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 98%|███████████████████████████████████████████████████████████████████████████████████████████████████████▍  | 284/291 [02:11<00:02,  3.19it/s]
 98%|███████████████████████████████████████████████████████████████████████████████████████████████████████▊  | 285/291 [02:11<00:03,  1.87it/s]
                                                                                                                                                 
[2024-01-30 01:56:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "model.layers.40.post_attention_layernorm.weight", shape: (8192,), dtype: float16
+
 98%|███████████████████████████████████████████████████████████████████████████████████████████████████████▊  | 285/291 [02:11<00:03,  1.87it/s]
                                                                                                                                                 
[2024-01-30 01:56:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.40.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 98%|███████████████████████████████████████████████████████████████████████████████████████████████████████▊  | 285/291 [02:11<00:03,  1.87it/s]
                                                                                                                                                 
[2024-01-30 01:56:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.40.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 98%|███████████████████████████████████████████████████████████████████████████████████████████████████████▊  | 285/291 [02:11<00:03,  1.87it/s]
 99%|████████████████████████████████████████████████████████████████████████████████████████████████████████▌ | 287/291 [02:11<00:01,  2.62it/s]
                                                                                                                                                 
[2024-01-30 01:56:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.40.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
 99%|████████████████████████████████████████████████████████████████████████████████████████████████████████▌ | 287/291 [02:11<00:01,  2.62it/s]
                                                                                                                                                 
[2024-01-30 01:56:40] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.40.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
 99%|████████████████████████████████████████████████████████████████████████████████████████████████████████▌ | 287/291 [02:11<00:01,  2.62it/s]
 99%|████████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 288/291 [02:11<00:01,  2.93it/s]
                                                                                                                                                 
[2024-01-30 01:56:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.41.mlp.gate_up_proj.q_weight", shape: (44032, 1024), dtype: uint32
+
 99%|████████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 288/291 [02:13<00:01,  2.93it/s]
                                                                                                                                                 
[2024-01-30 01:56:41] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.41.mlp.gate_up_proj.q_scale", shape: (44032, 256), dtype: float16
+
 99%|████████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 288/291 [02:13<00:01,  2.93it/s]
 99%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▎| 289/291 [02:13<00:01,  1.75it/s]
                                                                                                                                                 
[2024-01-30 01:56:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.41.self_attn.qkv_proj.q_weight", shape: (10240, 1024), dtype: uint32
+
 99%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▎| 289/291 [02:13<00:01,  1.75it/s]
                                                                                                                                                 
[2024-01-30 01:56:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.41.self_attn.qkv_proj.q_scale", shape: (10240, 256), dtype: float16
+
 99%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▎| 289/291 [02:13<00:01,  1.75it/s]
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▋| 290/291 [02:13<00:00,  2.01it/s]
                                                                                                                                                 
[2024-01-30 01:56:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.41.self_attn.o_proj.q_weight", shape: (8192, 1024), dtype: uint32
+
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▋| 290/291 [02:13<00:00,  2.01it/s]
                                                                                                                                                 
[2024-01-30 01:56:42] INFO huggingface_loader.py:121: [Quantized] Parameter: "model.layers.41.self_attn.o_proj.q_scale", shape: (8192, 256), dtype: float16
+
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▋| 290/291 [02:13<00:00,  2.01it/s]
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████| 291/291 [02:13<00:00,  2.40it/s]
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████| 291/291 [02:13<00:00,  2.18it/s]
+[2024-01-30 01:56:42] INFO huggingface_loader.py:181: Unloading HF weight file: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmp5j_y6e9a/repo/pytorch_model-00006-of-00007.bin
+[2024-01-30 01:56:42] INFO stats.py:76: Time usage: HF loading: 24.016 sec; Pre-quantization mapping: 95.771 sec; Quantization: 1.998 sec
+[2024-01-30 01:56:42] INFO stats.py:90: RAM usage: Peak RAM: 18.352 GB. Total bytes loaded from disk: 125.706 GB
+[2024-01-30 01:56:42] INFO convert_weight.py:121: Parameter size after quantization: 17.678 GB
+[2024-01-30 01:56:42] INFO convert_weight.py:126: Total parameters: 33,743,970,304
+[2024-01-30 01:56:42] INFO convert_weight.py:127: Bits per parameter: 4.500
+Start storing to cache /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpukse82wg
+

[0001/0485] saving lm_head.q_weight
                                   
[0002/0485] saving lm_head.q_scale
                                   
[0003/0485] saving model.layers.41.input_layernorm.weight
                                                         
[0004/0485] saving model.layers.41.mlp.down_proj.q_weight
                                                         
[0005/0485] saving model.layers.41.mlp.down_proj.q_scale
                                                         
[0006/0485] saving model.layers.41.post_attention_layernorm.weight
                                                                  
[0007/0485] saving model.layers.42.input_layernorm.weight
                                                                  
[0008/0485] saving model.layers.42.mlp.down_proj.q_weight
                                                                  
[0009/0485] saving model.layers.42.mlp.down_proj.q_scale
                                                                  
[0010/0485] saving model.layers.42.mlp.gate_up_proj.q_weight
                                                                  
[0011/0485] saving model.layers.42.mlp.gate_up_proj.q_scale
                                                                  
[0012/0485] saving model.layers.42.post_attention_layernorm.weight
                                                                  
[0013/0485] saving model.layers.42.self_attn.qkv_proj.q_weight
                                                                  
[0014/0485] saving model.layers.42.self_attn.qkv_proj.q_scale
                                                                  
[0015/0485] saving model.layers.42.self_attn.o_proj.q_weight
                                                                  
[0016/0485] saving model.layers.42.self_attn.o_proj.q_scale
                                                                  
[0017/0485] saving model.layers.43.input_layernorm.weight
                                                                  
[0018/0485] saving model.layers.43.mlp.down_proj.q_weight
                                                                  
[0019/0485] saving model.layers.43.mlp.down_proj.q_scale
                                                                  
[0020/0485] saving model.layers.43.mlp.gate_up_proj.q_weight
                                                                  
[0021/0485] saving model.layers.43.mlp.gate_up_proj.q_scale
                                                                  
[0022/0485] saving model.layers.43.post_attention_layernorm.weight
                                                                  
[0023/0485] saving model.layers.43.self_attn.qkv_proj.q_weight
                                                                  
[0024/0485] saving model.layers.43.self_attn.qkv_proj.q_scale
                                                                  
[0025/0485] saving model.layers.43.self_attn.o_proj.q_weight
                                                                  
[0026/0485] saving model.layers.43.self_attn.o_proj.q_scale
                                                                  
[0027/0485] saving model.layers.44.input_layernorm.weight
                                                                  
[0028/0485] saving model.layers.44.mlp.down_proj.q_weight
                                                                  
[0029/0485] saving model.layers.44.mlp.down_proj.q_scale
                                                                  
[0030/0485] saving model.layers.44.mlp.gate_up_proj.q_weight
                                                                  
[0031/0485] saving model.layers.44.mlp.gate_up_proj.q_scale
                                                                  
[0032/0485] saving model.layers.44.post_attention_layernorm.weight
                                                                  
[0033/0485] saving model.layers.44.self_attn.qkv_proj.q_weight
                                                                  
[0034/0485] saving model.layers.44.self_attn.qkv_proj.q_scale
                                                                  
[0035/0485] saving model.layers.44.self_attn.o_proj.q_weight
                                                                  
[0036/0485] saving model.layers.44.self_attn.o_proj.q_scale
                                                                  
[0037/0485] saving model.layers.45.input_layernorm.weight
                                                                  
[0038/0485] saving model.layers.45.mlp.down_proj.q_weight
                                                                  
[0039/0485] saving model.layers.45.mlp.down_proj.q_scale
                                                                  
[0040/0485] saving model.layers.45.mlp.gate_up_proj.q_weight
                                                                  
[0041/0485] saving model.layers.45.mlp.gate_up_proj.q_scale
                                                                  
[0042/0485] saving model.layers.45.post_attention_layernorm.weight
                                                                  
[0043/0485] saving model.layers.45.self_attn.qkv_proj.q_weight
                                                                  
[0044/0485] saving model.layers.45.self_attn.qkv_proj.q_scale
                                                                  
[0045/0485] saving model.layers.45.self_attn.o_proj.q_weight
                                                                  
[0046/0485] saving model.layers.45.self_attn.o_proj.q_scale
                                                                  
[0047/0485] saving model.layers.46.input_layernorm.weight
                                                                  
[0048/0485] saving model.layers.46.mlp.down_proj.q_weight
                                                                  
[0049/0485] saving model.layers.46.mlp.down_proj.q_scale
                                                                  
[0050/0485] saving model.layers.46.mlp.gate_up_proj.q_weight
                                                                  
[0051/0485] saving model.layers.46.mlp.gate_up_proj.q_scale
                                                                  
[0052/0485] saving model.layers.46.post_attention_layernorm.weight
                                                                  
[0053/0485] saving model.layers.46.self_attn.qkv_proj.q_weight
                                                                  
[0054/0485] saving model.layers.46.self_attn.qkv_proj.q_scale
                                                                  
[0055/0485] saving model.layers.46.self_attn.o_proj.q_weight
                                                                  
[0056/0485] saving model.layers.46.self_attn.o_proj.q_scale
                                                                  
[0057/0485] saving model.layers.47.input_layernorm.weight
                                                                  
[0058/0485] saving model.layers.47.mlp.down_proj.q_weight
                                                                  
[0059/0485] saving model.layers.47.mlp.down_proj.q_scale
                                                                  
[0060/0485] saving model.layers.47.mlp.gate_up_proj.q_weight
                                                                  
[0061/0485] saving model.layers.47.mlp.gate_up_proj.q_scale
                                                                  
[0062/0485] saving model.layers.47.post_attention_layernorm.weight
                                                                  
[0063/0485] saving model.layers.47.self_attn.qkv_proj.q_weight
                                                                  
[0064/0485] saving model.layers.47.self_attn.qkv_proj.q_scale
                                                                  
[0065/0485] saving model.layers.47.self_attn.o_proj.q_weight
                                                                  
[0066/0485] saving model.layers.47.self_attn.o_proj.q_scale
                                                                  
[0067/0485] saving model.norm.weight
                                                                  
[0068/0485] saving model.embed_tokens.q_weight
                                                                  
[0069/0485] saving model.embed_tokens.q_scale
                                                                  
[0070/0485] saving model.layers.0.input_layernorm.weight
                                                                  
[0071/0485] saving model.layers.0.mlp.down_proj.q_weight
                                                                  
[0072/0485] saving model.layers.0.mlp.down_proj.q_scale
                                                                  
[0073/0485] saving model.layers.0.mlp.gate_up_proj.q_weight
                                                                  
[0074/0485] saving model.layers.0.mlp.gate_up_proj.q_scale
                                                                  
[0075/0485] saving model.layers.0.post_attention_layernorm.weight
                                                                  
[0076/0485] saving model.layers.0.self_attn.qkv_proj.q_weight
                                                                  
[0077/0485] saving model.layers.0.self_attn.qkv_proj.q_scale
                                                                  
[0078/0485] saving model.layers.0.self_attn.o_proj.q_weight
                                                                  
[0079/0485] saving model.layers.0.self_attn.o_proj.q_scale
                                                                  
[0080/0485] saving model.layers.1.input_layernorm.weight
                                                                  
[0081/0485] saving model.layers.1.mlp.down_proj.q_weight
                                                                  
[0082/0485] saving model.layers.1.mlp.down_proj.q_scale
                                                                  
[0083/0485] saving model.layers.1.mlp.gate_up_proj.q_weight
                                                                  
[0084/0485] saving model.layers.1.mlp.gate_up_proj.q_scale
                                                                  
[0085/0485] saving model.layers.1.post_attention_layernorm.weight
                                                                  
[0086/0485] saving model.layers.1.self_attn.qkv_proj.q_weight
                                                                  
[0087/0485] saving model.layers.1.self_attn.qkv_proj.q_scale
                                                                  
[0088/0485] saving model.layers.1.self_attn.o_proj.q_weight
                                                                  
[0089/0485] saving model.layers.1.self_attn.o_proj.q_scale
                                                                  
[0090/0485] saving model.layers.2.input_layernorm.weight
                                                                  
[0091/0485] saving model.layers.2.mlp.down_proj.q_weight
                                                                  
[0092/0485] saving model.layers.2.mlp.down_proj.q_scale
                                                                  
[0093/0485] saving model.layers.2.mlp.gate_up_proj.q_weight
                                                                  
[0094/0485] saving model.layers.2.mlp.gate_up_proj.q_scale
                                                                  
[0095/0485] saving model.layers.2.post_attention_layernorm.weight
                                                                  
[0096/0485] saving model.layers.2.self_attn.qkv_proj.q_weight
                                                                  
[0097/0485] saving model.layers.2.self_attn.qkv_proj.q_scale
                                                                  
[0098/0485] saving model.layers.2.self_attn.o_proj.q_weight
                                                                  
[0099/0485] saving model.layers.2.self_attn.o_proj.q_scale
                                                                  
[0100/0485] saving model.layers.3.input_layernorm.weight
                                                                  
[0101/0485] saving model.layers.3.mlp.down_proj.q_weight
                                                                  
[0102/0485] saving model.layers.3.mlp.down_proj.q_scale
                                                                  
[0103/0485] saving model.layers.3.mlp.gate_up_proj.q_weight
                                                                  
[0104/0485] saving model.layers.3.mlp.gate_up_proj.q_scale
                                                                  
[0105/0485] saving model.layers.3.post_attention_layernorm.weight
                                                                  
[0106/0485] saving model.layers.3.self_attn.qkv_proj.q_weight
                                                                  
[0107/0485] saving model.layers.3.self_attn.qkv_proj.q_scale
                                                                  
[0108/0485] saving model.layers.3.self_attn.o_proj.q_weight
                                                                  
[0109/0485] saving model.layers.3.self_attn.o_proj.q_scale
                                                                  
[0110/0485] saving model.layers.4.input_layernorm.weight
                                                                  
[0111/0485] saving model.layers.4.mlp.down_proj.q_weight
                                                                  
[0112/0485] saving model.layers.4.mlp.down_proj.q_scale
                                                                  
[0113/0485] saving model.layers.4.mlp.gate_up_proj.q_weight
                                                                  
[0114/0485] saving model.layers.4.mlp.gate_up_proj.q_scale
                                                                  
[0115/0485] saving model.layers.4.post_attention_layernorm.weight
                                                                  
[0116/0485] saving model.layers.4.self_attn.qkv_proj.q_weight
                                                                  
[0117/0485] saving model.layers.4.self_attn.qkv_proj.q_scale
                                                                  
[0118/0485] saving model.layers.4.self_attn.o_proj.q_weight
                                                                  
[0119/0485] saving model.layers.4.self_attn.o_proj.q_scale
                                                                  
[0120/0485] saving model.layers.5.input_layernorm.weight
                                                                  
[0121/0485] saving model.layers.5.mlp.down_proj.q_weight
                                                                  
[0122/0485] saving model.layers.5.mlp.down_proj.q_scale
                                                                  
[0123/0485] saving model.layers.5.mlp.gate_up_proj.q_weight
                                                                  
[0124/0485] saving model.layers.5.mlp.gate_up_proj.q_scale
                                                                  
[0125/0485] saving model.layers.5.post_attention_layernorm.weight
                                                                  
[0126/0485] saving model.layers.5.self_attn.qkv_proj.q_weight
                                                                  
[0127/0485] saving model.layers.5.self_attn.qkv_proj.q_scale
                                                                  
[0128/0485] saving model.layers.5.self_attn.o_proj.q_weight
                                                                  
[0129/0485] saving model.layers.5.self_attn.o_proj.q_scale
                                                                  
[0130/0485] saving model.layers.6.mlp.gate_up_proj.q_weight
                                                                  
[0131/0485] saving model.layers.6.mlp.gate_up_proj.q_scale
                                                                  
[0132/0485] saving model.layers.6.self_attn.qkv_proj.q_weight
                                                                  
[0133/0485] saving model.layers.6.self_attn.qkv_proj.q_scale
                                                                  
[0134/0485] saving model.layers.6.self_attn.o_proj.q_weight
                                                                  
[0135/0485] saving model.layers.6.self_attn.o_proj.q_scale
                                                                  
[0136/0485] saving model.layers.10.input_layernorm.weight
                                                                  
[0137/0485] saving model.layers.10.mlp.down_proj.q_weight
                                                                  
[0138/0485] saving model.layers.10.mlp.down_proj.q_scale
                                                                  
[0139/0485] saving model.layers.10.mlp.gate_up_proj.q_weight
                                                                  
[0140/0485] saving model.layers.10.mlp.gate_up_proj.q_scale
                                                                  
[0141/0485] saving model.layers.10.post_attention_layernorm.weight
                                                                  
[0142/0485] saving model.layers.10.self_attn.qkv_proj.q_weight
                                                                  
[0143/0485] saving model.layers.10.self_attn.qkv_proj.q_scale
                                                                  
[0144/0485] saving model.layers.10.self_attn.o_proj.q_weight
                                                                  
[0145/0485] saving model.layers.10.self_attn.o_proj.q_scale
                                                                  
[0146/0485] saving model.layers.11.input_layernorm.weight
                                                                  
[0147/0485] saving model.layers.11.mlp.down_proj.q_weight
                                                                  
[0148/0485] saving model.layers.11.mlp.down_proj.q_scale
                                                                  
[0149/0485] saving model.layers.11.mlp.gate_up_proj.q_weight
                                                                  
[0150/0485] saving model.layers.11.mlp.gate_up_proj.q_scale
                                                                  
[0151/0485] saving model.layers.11.post_attention_layernorm.weight
                                                                  
[0152/0485] saving model.layers.11.self_attn.qkv_proj.q_weight
                                                                  
[0153/0485] saving model.layers.11.self_attn.qkv_proj.q_scale
                                                                  
[0154/0485] saving model.layers.11.self_attn.o_proj.q_weight
                                                                  
[0155/0485] saving model.layers.11.self_attn.o_proj.q_scale
                                                                  
[0156/0485] saving model.layers.12.input_layernorm.weight
                                                                  
[0157/0485] saving model.layers.12.mlp.down_proj.q_weight
                                                                  
[0158/0485] saving model.layers.12.mlp.down_proj.q_scale
                                                                  
[0159/0485] saving model.layers.12.mlp.gate_up_proj.q_weight
                                                                  
[0160/0485] saving model.layers.12.mlp.gate_up_proj.q_scale
                                                                  
[0161/0485] saving model.layers.12.post_attention_layernorm.weight
                                                                  
[0162/0485] saving model.layers.12.self_attn.qkv_proj.q_weight
                                                                  
[0163/0485] saving model.layers.12.self_attn.qkv_proj.q_scale
                                                                  
[0164/0485] saving model.layers.12.self_attn.o_proj.q_weight
                                                                  
[0165/0485] saving model.layers.12.self_attn.o_proj.q_scale
                                                                  
[0166/0485] saving model.layers.13.mlp.gate_up_proj.q_weight
                                                                  
[0167/0485] saving model.layers.13.mlp.gate_up_proj.q_scale
                                                                  
[0168/0485] saving model.layers.13.self_attn.qkv_proj.q_weight
                                                                  
[0169/0485] saving model.layers.13.self_attn.qkv_proj.q_scale
                                                                  
[0170/0485] saving model.layers.13.self_attn.o_proj.q_weight
                                                                  
[0171/0485] saving model.layers.13.self_attn.o_proj.q_scale
                                                                  
[0172/0485] saving model.layers.6.input_layernorm.weight
                                                                  
[0173/0485] saving model.layers.6.mlp.down_proj.q_weight
                                                                  
[0174/0485] saving model.layers.6.mlp.down_proj.q_scale
                                                                  
[0175/0485] saving model.layers.6.post_attention_layernorm.weight
                                                                  
[0176/0485] saving model.layers.7.input_layernorm.weight
                                                                  
[0177/0485] saving model.layers.7.mlp.down_proj.q_weight
                                                                  
[0178/0485] saving model.layers.7.mlp.down_proj.q_scale
                                                                  
[0179/0485] saving model.layers.7.mlp.gate_up_proj.q_weight
                                                                  
[0180/0485] saving model.layers.7.mlp.gate_up_proj.q_scale
                                                                  
[0181/0485] saving model.layers.7.post_attention_layernorm.weight
                                                                  
[0182/0485] saving model.layers.7.self_attn.qkv_proj.q_weight
                                                                  
[0183/0485] saving model.layers.7.self_attn.qkv_proj.q_scale
                                                                  
[0184/0485] saving model.layers.7.self_attn.o_proj.q_weight
                                                                  
[0185/0485] saving model.layers.7.self_attn.o_proj.q_scale
                                                                  
[0186/0485] saving model.layers.8.input_layernorm.weight
                                                                  
[0187/0485] saving model.layers.8.mlp.down_proj.q_weight
                                                                  
[0188/0485] saving model.layers.8.mlp.down_proj.q_scale
                                                                  
[0189/0485] saving model.layers.8.mlp.gate_up_proj.q_weight
                                                                  
[0190/0485] saving model.layers.8.mlp.gate_up_proj.q_scale
                                                                  
[0191/0485] saving model.layers.8.post_attention_layernorm.weight
                                                                  
[0192/0485] saving model.layers.8.self_attn.qkv_proj.q_weight
                                                                  
[0193/0485] saving model.layers.8.self_attn.qkv_proj.q_scale
                                                                  
[0194/0485] saving model.layers.8.self_attn.o_proj.q_weight
                                                                  
[0195/0485] saving model.layers.8.self_attn.o_proj.q_scale
                                                                  
[0196/0485] saving model.layers.9.input_layernorm.weight
                                                                  
[0197/0485] saving model.layers.9.mlp.down_proj.q_weight
                                                                  
[0198/0485] saving model.layers.9.mlp.down_proj.q_scale
                                                                  
[0199/0485] saving model.layers.9.mlp.gate_up_proj.q_weight
                                                                  
[0200/0485] saving model.layers.9.mlp.gate_up_proj.q_scale
                                                                  
[0201/0485] saving model.layers.9.post_attention_layernorm.weight
                                                                  
[0202/0485] saving model.layers.9.self_attn.qkv_proj.q_weight
                                                                  
[0203/0485] saving model.layers.9.self_attn.qkv_proj.q_scale
                                                                  
[0204/0485] saving model.layers.9.self_attn.o_proj.q_weight
                                                                  
[0205/0485] saving model.layers.9.self_attn.o_proj.q_scale
                                                                  
[0206/0485] saving model.layers.13.input_layernorm.weight
                                                                  
[0207/0485] saving model.layers.13.mlp.down_proj.q_weight
                                                                  
[0208/0485] saving model.layers.13.mlp.down_proj.q_scale
                                                                  
[0209/0485] saving model.layers.13.post_attention_layernorm.weight
                                                                  
[0210/0485] saving model.layers.14.input_layernorm.weight
                                                                  
[0211/0485] saving model.layers.14.mlp.down_proj.q_weight
                                                                  
[0212/0485] saving model.layers.14.mlp.down_proj.q_scale
                                                                  
[0213/0485] saving model.layers.14.mlp.gate_up_proj.q_weight
                                                                  
[0214/0485] saving model.layers.14.mlp.gate_up_proj.q_scale
                                                                  
[0215/0485] saving model.layers.14.post_attention_layernorm.weight
                                                                  
[0216/0485] saving model.layers.14.self_attn.qkv_proj.q_weight
                                                                  
[0217/0485] saving model.layers.14.self_attn.qkv_proj.q_scale
                                                                  
[0218/0485] saving model.layers.14.self_attn.o_proj.q_weight
                                                                  
[0219/0485] saving model.layers.14.self_attn.o_proj.q_scale
                                                                  
[0220/0485] saving model.layers.15.input_layernorm.weight
                                                                  
[0221/0485] saving model.layers.15.mlp.down_proj.q_weight
                                                                  
[0222/0485] saving model.layers.15.mlp.down_proj.q_scale
                                                                  
[0223/0485] saving model.layers.15.mlp.gate_up_proj.q_weight
                                                                  
[0224/0485] saving model.layers.15.mlp.gate_up_proj.q_scale
                                                                  
[0225/0485] saving model.layers.15.post_attention_layernorm.weight
                                                                  
[0226/0485] saving model.layers.15.self_attn.qkv_proj.q_weight
                                                                  
[0227/0485] saving model.layers.15.self_attn.qkv_proj.q_scale
                                                                  
[0228/0485] saving model.layers.15.self_attn.o_proj.q_weight
                                                                  
[0229/0485] saving model.layers.15.self_attn.o_proj.q_scale
                                                                  
[0230/0485] saving model.layers.16.input_layernorm.weight
                                                                  
[0231/0485] saving model.layers.16.mlp.down_proj.q_weight
                                                                  
[0232/0485] saving model.layers.16.mlp.down_proj.q_scale
                                                                  
[0233/0485] saving model.layers.16.mlp.gate_up_proj.q_weight
                                                                  
[0234/0485] saving model.layers.16.mlp.gate_up_proj.q_scale
                                                                  
[0235/0485] saving model.layers.16.post_attention_layernorm.weight
                                                                  
[0236/0485] saving model.layers.16.self_attn.qkv_proj.q_weight
                                                                  
[0237/0485] saving model.layers.16.self_attn.qkv_proj.q_scale
                                                                  
[0238/0485] saving model.layers.16.self_attn.o_proj.q_weight
                                                                  
[0239/0485] saving model.layers.16.self_attn.o_proj.q_scale
                                                                  
[0240/0485] saving model.layers.17.input_layernorm.weight
                                                                  
[0241/0485] saving model.layers.17.mlp.down_proj.q_weight
                                                                  
[0242/0485] saving model.layers.17.mlp.down_proj.q_scale
                                                                  
[0243/0485] saving model.layers.17.mlp.gate_up_proj.q_weight
                                                                  
[0244/0485] saving model.layers.17.mlp.gate_up_proj.q_scale
                                                                  
[0245/0485] saving model.layers.17.post_attention_layernorm.weight
                                                                  
[0246/0485] saving model.layers.17.self_attn.qkv_proj.q_weight
                                                                  
[0247/0485] saving model.layers.17.self_attn.qkv_proj.q_scale
                                                                  
[0248/0485] saving model.layers.17.self_attn.o_proj.q_weight
                                                                  
[0249/0485] saving model.layers.17.self_attn.o_proj.q_scale
                                                                  
[0250/0485] saving model.layers.18.input_layernorm.weight
                                                                  
[0251/0485] saving model.layers.18.mlp.down_proj.q_weight
                                                                  
[0252/0485] saving model.layers.18.mlp.down_proj.q_scale
                                                                  
[0253/0485] saving model.layers.18.mlp.gate_up_proj.q_weight
                                                                  
[0254/0485] saving model.layers.18.mlp.gate_up_proj.q_scale
                                                                  
[0255/0485] saving model.layers.18.post_attention_layernorm.weight
                                                                  
[0256/0485] saving model.layers.18.self_attn.qkv_proj.q_weight
                                                                  
[0257/0485] saving model.layers.18.self_attn.qkv_proj.q_scale
                                                                  
[0258/0485] saving model.layers.18.self_attn.o_proj.q_weight
                                                                  
[0259/0485] saving model.layers.18.self_attn.o_proj.q_scale
                                                                  
[0260/0485] saving model.layers.19.input_layernorm.weight
                                                                  
[0261/0485] saving model.layers.19.mlp.down_proj.q_weight
                                                                  
[0262/0485] saving model.layers.19.mlp.down_proj.q_scale
                                                                  
[0263/0485] saving model.layers.19.mlp.gate_up_proj.q_weight
                                                                  
[0264/0485] saving model.layers.19.mlp.gate_up_proj.q_scale
                                                                  
[0265/0485] saving model.layers.19.post_attention_layernorm.weight
                                                                  
[0266/0485] saving model.layers.19.self_attn.qkv_proj.q_weight
                                                                  
[0267/0485] saving model.layers.19.self_attn.qkv_proj.q_scale
                                                                  
[0268/0485] saving model.layers.19.self_attn.o_proj.q_weight
                                                                  
[0269/0485] saving model.layers.19.self_attn.o_proj.q_scale
                                                                  
[0270/0485] saving model.layers.20.mlp.gate_up_proj.q_weight
                                                                  
[0271/0485] saving model.layers.20.mlp.gate_up_proj.q_scale
                                                                  
[0272/0485] saving model.layers.20.self_attn.qkv_proj.q_weight
                                                                  
[0273/0485] saving model.layers.20.self_attn.qkv_proj.q_scale
                                                                  
[0274/0485] saving model.layers.20.self_attn.o_proj.q_weight
                                                                  
[0275/0485] saving model.layers.20.self_attn.o_proj.q_scale
                                                                  
[0276/0485] saving model.layers.20.input_layernorm.weight
                                                                  
[0277/0485] saving model.layers.20.mlp.down_proj.q_weight
                                                                  
[0278/0485] saving model.layers.20.mlp.down_proj.q_scale
                                                                  
[0279/0485] saving model.layers.20.post_attention_layernorm.weight
                                                                  
[0280/0485] saving model.layers.21.input_layernorm.weight
                                                                  
[0281/0485] saving model.layers.21.mlp.down_proj.q_weight
                                                                  
[0282/0485] saving model.layers.21.mlp.down_proj.q_scale
                                                                  
[0283/0485] saving model.layers.21.mlp.gate_up_proj.q_weight
                                                                  
[0284/0485] saving model.layers.21.mlp.gate_up_proj.q_scale
                                                                  
[0285/0485] saving model.layers.21.post_attention_layernorm.weight
                                                                  
[0286/0485] saving model.layers.21.self_attn.qkv_proj.q_weight
                                                                  
[0287/0485] saving model.layers.21.self_attn.qkv_proj.q_scale
                                                                  
[0288/0485] saving model.layers.21.self_attn.o_proj.q_weight
                                                                  
[0289/0485] saving model.layers.21.self_attn.o_proj.q_scale
                                                                  
[0290/0485] saving model.layers.22.input_layernorm.weight
                                                                  
[0291/0485] saving model.layers.22.mlp.down_proj.q_weight
                                                                  
[0292/0485] saving model.layers.22.mlp.down_proj.q_scale
                                                                  
[0293/0485] saving model.layers.22.mlp.gate_up_proj.q_weight
                                                                  
[0294/0485] saving model.layers.22.mlp.gate_up_proj.q_scale
                                                                  
[0295/0485] saving model.layers.22.post_attention_layernorm.weight
                                                                  
[0296/0485] saving model.layers.22.self_attn.qkv_proj.q_weight
                                                                  
[0297/0485] saving model.layers.22.self_attn.qkv_proj.q_scale
                                                                  
[0298/0485] saving model.layers.22.self_attn.o_proj.q_weight
                                                                  
[0299/0485] saving model.layers.22.self_attn.o_proj.q_scale
                                                                  
[0300/0485] saving model.layers.23.input_layernorm.weight
                                                                  
[0301/0485] saving model.layers.23.mlp.down_proj.q_weight
                                                                  
[0302/0485] saving model.layers.23.mlp.down_proj.q_scale
                                                                  
[0303/0485] saving model.layers.23.mlp.gate_up_proj.q_weight
                                                                  
[0304/0485] saving model.layers.23.mlp.gate_up_proj.q_scale
                                                                  
[0305/0485] saving model.layers.23.post_attention_layernorm.weight
                                                                  
[0306/0485] saving model.layers.23.self_attn.qkv_proj.q_weight
                                                                  
[0307/0485] saving model.layers.23.self_attn.qkv_proj.q_scale
                                                                  
[0308/0485] saving model.layers.23.self_attn.o_proj.q_weight
                                                                  
[0309/0485] saving model.layers.23.self_attn.o_proj.q_scale
                                                                  
[0310/0485] saving model.layers.24.input_layernorm.weight
                                                                  
[0311/0485] saving model.layers.24.mlp.down_proj.q_weight
                                                                  
[0312/0485] saving model.layers.24.mlp.down_proj.q_scale
                                                                  
[0313/0485] saving model.layers.24.mlp.gate_up_proj.q_weight
                                                                  
[0314/0485] saving model.layers.24.mlp.gate_up_proj.q_scale
                                                                  
[0315/0485] saving model.layers.24.post_attention_layernorm.weight
                                                                  
[0316/0485] saving model.layers.24.self_attn.qkv_proj.q_weight
                                                                  
[0317/0485] saving model.layers.24.self_attn.qkv_proj.q_scale
                                                                  
[0318/0485] saving model.layers.24.self_attn.o_proj.q_weight
                                                                  
[0319/0485] saving model.layers.24.self_attn.o_proj.q_scale
                                                                  
[0320/0485] saving model.layers.25.input_layernorm.weight
                                                                  
[0321/0485] saving model.layers.25.mlp.down_proj.q_weight
                                                                  
[0322/0485] saving model.layers.25.mlp.down_proj.q_scale
                                                                  
[0323/0485] saving model.layers.25.mlp.gate_up_proj.q_weight
                                                                  
[0324/0485] saving model.layers.25.mlp.gate_up_proj.q_scale
                                                                  
[0325/0485] saving model.layers.25.post_attention_layernorm.weight
                                                                  
[0326/0485] saving model.layers.25.self_attn.qkv_proj.q_weight
                                                                  
[0327/0485] saving model.layers.25.self_attn.qkv_proj.q_scale
                                                                  
[0328/0485] saving model.layers.25.self_attn.o_proj.q_weight
                                                                  
[0329/0485] saving model.layers.25.self_attn.o_proj.q_scale
                                                                  
[0330/0485] saving model.layers.26.input_layernorm.weight
                                                                  
[0331/0485] saving model.layers.26.mlp.down_proj.q_weight
                                                                  
[0332/0485] saving model.layers.26.mlp.down_proj.q_scale
                                                                  
[0333/0485] saving model.layers.26.mlp.gate_up_proj.q_weight
                                                                  
[0334/0485] saving model.layers.26.mlp.gate_up_proj.q_scale
                                                                  
[0335/0485] saving model.layers.26.post_attention_layernorm.weight
                                                                  
[0336/0485] saving model.layers.26.self_attn.qkv_proj.q_weight
                                                                  
[0337/0485] saving model.layers.26.self_attn.qkv_proj.q_scale
                                                                  
[0338/0485] saving model.layers.26.self_attn.o_proj.q_weight
                                                                  
[0339/0485] saving model.layers.26.self_attn.o_proj.q_scale
                                                                  
[0340/0485] saving model.layers.27.mlp.gate_up_proj.q_weight
                                                                  
[0341/0485] saving model.layers.27.mlp.gate_up_proj.q_scale
                                                                  
[0342/0485] saving model.layers.27.self_attn.qkv_proj.q_weight
                                                                  
[0343/0485] saving model.layers.27.self_attn.qkv_proj.q_scale
                                                                  
[0344/0485] saving model.layers.27.self_attn.o_proj.q_weight
                                                                  
[0345/0485] saving model.layers.27.self_attn.o_proj.q_scale
                                                                  
[0346/0485] saving model.layers.27.input_layernorm.weight
                                                                  
[0347/0485] saving model.layers.27.mlp.down_proj.q_weight
                                                                  
[0348/0485] saving model.layers.27.mlp.down_proj.q_scale
                                                                  
[0349/0485] saving model.layers.27.post_attention_layernorm.weight
                                                                  
[0350/0485] saving model.layers.28.input_layernorm.weight
                                                                  
[0351/0485] saving model.layers.28.mlp.down_proj.q_weight
                                                                  
[0352/0485] saving model.layers.28.mlp.down_proj.q_scale
                                                                  
[0353/0485] saving model.layers.28.mlp.gate_up_proj.q_weight
                                                                  
[0354/0485] saving model.layers.28.mlp.gate_up_proj.q_scale
                                                                  
[0355/0485] saving model.layers.28.post_attention_layernorm.weight
                                                                  
[0356/0485] saving model.layers.28.self_attn.qkv_proj.q_weight
                                                                  
[0357/0485] saving model.layers.28.self_attn.qkv_proj.q_scale
                                                                  
[0358/0485] saving model.layers.28.self_attn.o_proj.q_weight
                                                                  
[0359/0485] saving model.layers.28.self_attn.o_proj.q_scale
                                                                  
[0360/0485] saving model.layers.29.input_layernorm.weight
                                                                  
[0361/0485] saving model.layers.29.mlp.down_proj.q_weight
                                                                  
[0362/0485] saving model.layers.29.mlp.down_proj.q_scale
                                                                  
[0363/0485] saving model.layers.29.mlp.gate_up_proj.q_weight
                                                                  
[0364/0485] saving model.layers.29.mlp.gate_up_proj.q_scale
                                                                  
[0365/0485] saving model.layers.29.post_attention_layernorm.weight
                                                                  
[0366/0485] saving model.layers.29.self_attn.qkv_proj.q_weight
                                                                  
[0367/0485] saving model.layers.29.self_attn.qkv_proj.q_scale
                                                                  
[0368/0485] saving model.layers.29.self_attn.o_proj.q_weight
                                                                  
[0369/0485] saving model.layers.29.self_attn.o_proj.q_scale
                                                                  
[0370/0485] saving model.layers.30.input_layernorm.weight
                                                                  
[0371/0485] saving model.layers.30.mlp.down_proj.q_weight
                                                                  
[0372/0485] saving model.layers.30.mlp.down_proj.q_scale
                                                                  
[0373/0485] saving model.layers.30.mlp.gate_up_proj.q_weight
                                                                  
[0374/0485] saving model.layers.30.mlp.gate_up_proj.q_scale
                                                                  
[0375/0485] saving model.layers.30.post_attention_layernorm.weight
                                                                  
[0376/0485] saving model.layers.30.self_attn.qkv_proj.q_weight
                                                                  
[0377/0485] saving model.layers.30.self_attn.qkv_proj.q_scale
                                                                  
[0378/0485] saving model.layers.30.self_attn.o_proj.q_weight
                                                                  
[0379/0485] saving model.layers.30.self_attn.o_proj.q_scale
                                                                  
[0380/0485] saving model.layers.31.input_layernorm.weight
                                                                  
[0381/0485] saving model.layers.31.mlp.down_proj.q_weight
                                                                  
[0382/0485] saving model.layers.31.mlp.down_proj.q_scale
                                                                  
[0383/0485] saving model.layers.31.mlp.gate_up_proj.q_weight
                                                                  
[0384/0485] saving model.layers.31.mlp.gate_up_proj.q_scale
                                                                  
[0385/0485] saving model.layers.31.post_attention_layernorm.weight
                                                                  
[0386/0485] saving model.layers.31.self_attn.qkv_proj.q_weight
                                                                  
[0387/0485] saving model.layers.31.self_attn.qkv_proj.q_scale
                                                                  
[0388/0485] saving model.layers.31.self_attn.o_proj.q_weight
                                                                  
[0389/0485] saving model.layers.31.self_attn.o_proj.q_scale
                                                                  
[0390/0485] saving model.layers.32.input_layernorm.weight
                                                                  
[0391/0485] saving model.layers.32.mlp.down_proj.q_weight
                                                                  
[0392/0485] saving model.layers.32.mlp.down_proj.q_scale
                                                                  
[0393/0485] saving model.layers.32.mlp.gate_up_proj.q_weight
                                                                  
[0394/0485] saving model.layers.32.mlp.gate_up_proj.q_scale
                                                                  
[0395/0485] saving model.layers.32.post_attention_layernorm.weight
                                                                  
[0396/0485] saving model.layers.32.self_attn.qkv_proj.q_weight
                                                                  
[0397/0485] saving model.layers.32.self_attn.qkv_proj.q_scale
                                                                  
[0398/0485] saving model.layers.32.self_attn.o_proj.q_weight
                                                                  
[0399/0485] saving model.layers.32.self_attn.o_proj.q_scale
                                                                  
[0400/0485] saving model.layers.33.input_layernorm.weight
                                                                  
[0401/0485] saving model.layers.33.mlp.down_proj.q_weight
                                                                  
[0402/0485] saving model.layers.33.mlp.down_proj.q_scale
                                                                  
[0403/0485] saving model.layers.33.mlp.gate_up_proj.q_weight
                                                                  
[0404/0485] saving model.layers.33.mlp.gate_up_proj.q_scale
                                                                  
[0405/0485] saving model.layers.33.post_attention_layernorm.weight
                                                                  
[0406/0485] saving model.layers.33.self_attn.qkv_proj.q_weight
                                                                  
[0407/0485] saving model.layers.33.self_attn.qkv_proj.q_scale
                                                                  
[0408/0485] saving model.layers.33.self_attn.o_proj.q_weight
                                                                  
[0409/0485] saving model.layers.33.self_attn.o_proj.q_scale
                                                                  
[0410/0485] saving model.layers.34.mlp.gate_up_proj.q_weight
                                                                  
[0411/0485] saving model.layers.34.mlp.gate_up_proj.q_scale
                                                                  
[0412/0485] saving model.layers.34.self_attn.qkv_proj.q_weight
                                                                  
[0413/0485] saving model.layers.34.self_attn.qkv_proj.q_scale
                                                                  
[0414/0485] saving model.layers.34.self_attn.o_proj.q_weight
                                                                  
[0415/0485] saving model.layers.34.self_attn.o_proj.q_scale
                                                                  
[0416/0485] saving model.layers.34.input_layernorm.weight
                                                                  
[0417/0485] saving model.layers.34.mlp.down_proj.q_weight
                                                                  
[0418/0485] saving model.layers.34.mlp.down_proj.q_scale
                                                                  
[0419/0485] saving model.layers.34.post_attention_layernorm.weight
                                                                  
[0420/0485] saving model.layers.35.input_layernorm.weight
                                                                  
[0421/0485] saving model.layers.35.mlp.down_proj.q_weight
                                                                  
[0422/0485] saving model.layers.35.mlp.down_proj.q_scale
                                                                  
[0423/0485] saving model.layers.35.mlp.gate_up_proj.q_weight
                                                                  
[0424/0485] saving model.layers.35.mlp.gate_up_proj.q_scale
                                                                  
[0425/0485] saving model.layers.35.post_attention_layernorm.weight
                                                                  
[0426/0485] saving model.layers.35.self_attn.qkv_proj.q_weight
                                                                  
[0427/0485] saving model.layers.35.self_attn.qkv_proj.q_scale
                                                                  
[0428/0485] saving model.layers.35.self_attn.o_proj.q_weight
                                                                  
[0429/0485] saving model.layers.35.self_attn.o_proj.q_scale
                                                                  
[0430/0485] saving model.layers.36.input_layernorm.weight
                                                                  
[0431/0485] saving model.layers.36.mlp.down_proj.q_weight
                                                                  
[0432/0485] saving model.layers.36.mlp.down_proj.q_scale
                                                                  
[0433/0485] saving model.layers.36.mlp.gate_up_proj.q_weight
                                                                  
[0434/0485] saving model.layers.36.mlp.gate_up_proj.q_scale
                                                                  
[0435/0485] saving model.layers.36.post_attention_layernorm.weight
                                                                  
[0436/0485] saving model.layers.36.self_attn.qkv_proj.q_weight
                                                                  
[0437/0485] saving model.layers.36.self_attn.qkv_proj.q_scale
                                                                  
[0438/0485] saving model.layers.36.self_attn.o_proj.q_weight
                                                                  
[0439/0485] saving model.layers.36.self_attn.o_proj.q_scale
                                                                  
[0440/0485] saving model.layers.37.input_layernorm.weight
                                                                  
[0441/0485] saving model.layers.37.mlp.down_proj.q_weight
                                                                  
[0442/0485] saving model.layers.37.mlp.down_proj.q_scale
                                                                  
[0443/0485] saving model.layers.37.mlp.gate_up_proj.q_weight
                                                                  
[0444/0485] saving model.layers.37.mlp.gate_up_proj.q_scale
                                                                  
[0445/0485] saving model.layers.37.post_attention_layernorm.weight
                                                                  
[0446/0485] saving model.layers.37.self_attn.qkv_proj.q_weight
                                                                  
[0447/0485] saving model.layers.37.self_attn.qkv_proj.q_scale
                                                                  
[0448/0485] saving model.layers.37.self_attn.o_proj.q_weight
                                                                  
[0449/0485] saving model.layers.37.self_attn.o_proj.q_scale
                                                                  
[0450/0485] saving model.layers.38.input_layernorm.weight[2024-01-30 01:57:17] INFO convert_weight.py:143: Saved to directory: /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpukse82wg
+
                                                                  
[0451/0485] saving model.layers.38.mlp.down_proj.q_weight
                                                                  
[0452/0485] saving model.layers.38.mlp.down_proj.q_scale
                                                                  
[0453/0485] saving model.layers.38.mlp.gate_up_proj.q_weight
                                                                  
[0454/0485] saving model.layers.38.mlp.gate_up_proj.q_scale
                                                                  
[0455/0485] saving model.layers.38.post_attention_layernorm.weight
                                                                  
[0456/0485] saving model.layers.38.self_attn.qkv_proj.q_weight
                                                                  
[0457/0485] saving model.layers.38.self_attn.qkv_proj.q_scale
                                                                  
[0458/0485] saving model.layers.38.self_attn.o_proj.q_weight
                                                                  
[0459/0485] saving model.layers.38.self_attn.o_proj.q_scale
                                                                  
[0460/0485] saving model.layers.39.input_layernorm.weight
                                                                  
[0461/0485] saving model.layers.39.mlp.down_proj.q_weight
                                                                  
[0462/0485] saving model.layers.39.mlp.down_proj.q_scale
                                                                  
[0463/0485] saving model.layers.39.mlp.gate_up_proj.q_weight
                                                                  
[0464/0485] saving model.layers.39.mlp.gate_up_proj.q_scale
                                                                  
[0465/0485] saving model.layers.39.post_attention_layernorm.weight
                                                                  
[0466/0485] saving model.layers.39.self_attn.qkv_proj.q_weight
                                                                  
[0467/0485] saving model.layers.39.self_attn.qkv_proj.q_scale
                                                                  
[0468/0485] saving model.layers.39.self_attn.o_proj.q_weight
                                                                  
[0469/0485] saving model.layers.39.self_attn.o_proj.q_scale
                                                                  
[0470/0485] saving model.layers.40.input_layernorm.weight
                                                                  
[0471/0485] saving model.layers.40.mlp.down_proj.q_weight
                                                                  
[0472/0485] saving model.layers.40.mlp.down_proj.q_scale
                                                                  
[0473/0485] saving model.layers.40.mlp.gate_up_proj.q_weight
                                                                  
[0474/0485] saving model.layers.40.mlp.gate_up_proj.q_scale
                                                                  
[0475/0485] saving model.layers.40.post_attention_layernorm.weight
                                                                  
[0476/0485] saving model.layers.40.self_attn.qkv_proj.q_weight
                                                                  
[0477/0485] saving model.layers.40.self_attn.qkv_proj.q_scale
                                                                  
[0478/0485] saving model.layers.40.self_attn.o_proj.q_weight
                                                                  
[0479/0485] saving model.layers.40.self_attn.o_proj.q_scale
                                                                  
[0480/0485] saving model.layers.41.mlp.gate_up_proj.q_weight
                                                                  
[0481/0485] saving model.layers.41.mlp.gate_up_proj.q_scale
                                                                  
[0482/0485] saving model.layers.41.self_attn.qkv_proj.q_weight
                                                                  
[0483/0485] saving model.layers.41.self_attn.qkv_proj.q_scale
                                                                  
[0484/0485] saving model.layers.41.self_attn.o_proj.q_weight
                                                                  
[0485/0485] saving model.layers.41.self_attn.o_proj.q_scale
+All finished, 275 total shards committed, record saved to /var/folders/50/mzqbqxqj5fddcby2mg3h334c0000gp/T/tmpukse82wg/ndarray-cache.json