diff --git "a/logs.txt" "b/logs.txt"
new file mode 100644--- /dev/null
+++ "b/logs.txt"
@@ -0,0 +1,389 @@
+/home/msyu/workspace/venv/bin/python -m mlc_llm gen_config /tmp/tmpom_oz7t5/repo --quantization q4f16_2 --conv-template phi-3 --output /tmp/tmpn0y_4cix
+[2024-05-08 13:48:47] INFO auto_config.py:115: Found model configuration: /tmp/tmpom_oz7t5/repo/config.json
+[2024-05-08 13:48:47] INFO auto_config.py:153: Found model type: phi3. Use `--model-type` to override.
+[2024-05-08 13:48:47] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (131072)
+[2024-05-08 13:48:47] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048
+[2024-05-08 13:48:47] INFO config.py:106: Overriding max_batch_size from 1 to 80
+[2024-05-08 13:48:47] INFO gen_config.py:255: [generation_config.json] Setting bos_token_id: 1
+[2024-05-08 13:48:47] INFO gen_config.py:255: [generation_config.json] Setting eos_token_id: [32000, 32001, 32007]
+[2024-05-08 13:48:47] INFO gen_config.py:255: [generation_config.json] Setting pad_token_id: 32000
+[2024-05-08 13:48:47] INFO gen_config.py:267: Found tokenizer config: /tmp/tmpom_oz7t5/repo/tokenizer.model. Copying to /tmp/tmpn0y_4cix/tokenizer.model
+[2024-05-08 13:48:47] INFO gen_config.py:267: Found tokenizer config: /tmp/tmpom_oz7t5/repo/tokenizer.json. Copying to /tmp/tmpn0y_4cix/tokenizer.json
+[2024-05-08 13:48:47] INFO gen_config.py:269: Not found tokenizer config: /tmp/tmpom_oz7t5/repo/vocab.json
+[2024-05-08 13:48:47] INFO gen_config.py:269: Not found tokenizer config: /tmp/tmpom_oz7t5/repo/merges.txt
+[2024-05-08 13:48:47] INFO gen_config.py:267: Found tokenizer config: /tmp/tmpom_oz7t5/repo/added_tokens.json. Copying to /tmp/tmpn0y_4cix/added_tokens.json
+[2024-05-08 13:48:47] INFO gen_config.py:267: Found tokenizer config: /tmp/tmpom_oz7t5/repo/tokenizer_config.json. Copying to /tmp/tmpn0y_4cix/tokenizer_config.json
+[2024-05-08 13:48:47] INFO gen_config.py:80: [System default] Setting temperature: 0.7
+[2024-05-08 13:48:47] INFO gen_config.py:80: [System default] Setting presence_penalty: 0.0
+[2024-05-08 13:48:47] INFO gen_config.py:80: [System default] Setting frequency_penalty: 0.0
+[2024-05-08 13:48:47] INFO gen_config.py:80: [System default] Setting repetition_penalty: 1.0
+[2024-05-08 13:48:47] INFO gen_config.py:80: [System default] Setting top_p: 0.95
+[2024-05-08 13:48:47] INFO gen_config.py:80: [System default] Setting mean_gen_len: 128
+[2024-05-08 13:48:47] INFO gen_config.py:80: [System default] Setting max_gen_len: 512
+[2024-05-08 13:48:47] INFO gen_config.py:80: [System default] Setting shift_fill_factor: 0.3
+[2024-05-08 13:48:47] INFO gen_config.py:335: Dumping configuration file to: /tmp/tmpn0y_4cix/mlc-chat-config.json
+/home/msyu/workspace/venv/bin/python -m mlc_llm convert_weight /tmp/tmpom_oz7t5/repo --quantization q4f16_2 --source-format auto --output /tmp/tmpn0y_4cix
+[2024-05-08 13:48:47] INFO auto_config.py:115: Found model configuration: /tmp/tmpom_oz7t5/repo/config.json
+[2024-05-08 13:48:48] INFO auto_device.py:79: Found device: cuda:0
+[2024-05-08 13:48:49] INFO auto_device.py:88: Not found device: rocm:0
+[2024-05-08 13:48:49] INFO auto_device.py:88: Not found device: metal:0
+[2024-05-08 13:48:50] INFO auto_device.py:88: Not found device: vulkan:0
+[2024-05-08 13:48:51] INFO auto_device.py:79: Found device: opencl:0
+[2024-05-08 13:48:51] INFO auto_device.py:35: Using device: cuda:0
+[2024-05-08 13:48:51] INFO auto_weight.py:70: Finding weights in: /tmp/tmpom_oz7t5/repo
+[2024-05-08 13:48:51] INFO auto_weight.py:136: Not found Huggingface PyTorch
+[2024-05-08 13:48:51] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: /tmp/tmpom_oz7t5/repo/model.safetensors.index.json
+[2024-05-08 13:48:51] INFO auto_weight.py:106: Using source weight configuration: /tmp/tmpom_oz7t5/repo/model.safetensors.index.json. Use `--source` to override.
+[2024-05-08 13:48:51] INFO auto_weight.py:110: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
+[2024-05-08 13:48:51] INFO auto_config.py:153: Found model type: phi3. Use `--model-type` to override.
+[2024-05-08 13:48:51] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (131072)
+[2024-05-08 13:48:51] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048
+Weight conversion with arguments:
+  --config          /tmp/tmpom_oz7t5/repo/config.json
+  --quantization    GroupQuantize(name='q4f16_2', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float16', linear_weight_layout='NK', quantize_embedding=False, quantize_final_fc=False, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7)
+  --model-type      phi3
+  --device          cuda:0
+  --source          /tmp/tmpom_oz7t5/repo/model.safetensors.index.json
+  --source-format   huggingface-safetensor
+  --output          /tmp/tmpn0y_4cix
+Start storing to cache /tmp/tmpn0y_4cix
+
  0%|          | 0/195 [00:00<?, ?it/s]
                                       
[2024-05-08 13:48:53] INFO huggingface_loader.py:184: Loading HF parameters from: /tmp/tmpom_oz7t5/repo/model-00002-of-00002.safetensors
+
  0%|          | 0/195 [00:00<?, ?it/s]
                                       
[2024-05-08 13:48:54] INFO huggingface_loader.py:174: [Not quantized] Parameter: "lm_head.weight", shape: (32064, 3072), dtype: float16
+
  0%|          | 0/195 [00:00<?, ?it/s]
  1%|          | 1/195 [00:01<04:14,  1.31s/it]
                                               
[2024-05-08 13:48:54] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.ln.weight", shape: (3072,), dtype: float16
+
  1%|          | 1/195 [00:01<04:14,  1.31s/it]
                                               
[2024-05-08 13:48:54] INFO group_quantization.py:217: Compiling quantize function for key: ((3072, 8192), float16, cuda, axis=1, output_transpose=False)
+
  1%|          | 1/195 [00:01<04:14,  1.31s/it]
                                               
[2024-05-08 13:48:55] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
  1%|          | 1/195 [00:02<04:14,  1.31s/it]
                                               
[2024-05-08 13:48:55] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
  1%|          | 1/195 [00:02<04:14,  1.31s/it]
  2%|▏         | 3/195 [00:02<01:55,  1.67it/s]
                                               
[2024-05-08 13:48:55] INFO group_quantization.py:217: Compiling quantize function for key: ((16384, 3072), float16, cuda, axis=1, output_transpose=False)
+
  2%|▏         | 3/195 [00:02<01:55,  1.67it/s]
                                               
[2024-05-08 13:48:55] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
  2%|▏         | 3/195 [00:02<01:55,  1.67it/s]
                                               
[2024-05-08 13:48:55] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
  2%|▏         | 3/195 [00:02<01:55,  1.67it/s]
  2%|▏         | 4/195 [00:02<01:40,  1.89it/s]
                                               
[2024-05-08 13:48:55] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
  2%|▏         | 4/195 [00:02<01:40,  1.89it/s]
                                               
[2024-05-08 13:48:55] INFO group_quantization.py:217: Compiling quantize function for key: ((9216, 3072), float16, cuda, axis=1, output_transpose=False)
+
  2%|▏         | 4/195 [00:02<01:40,  1.89it/s]
                                               
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
  2%|▏         | 4/195 [00:02<01:40,  1.89it/s]
                                               
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
  2%|▏         | 4/195 [00:02<01:40,  1.89it/s]
  3%|▎         | 6/195 [00:02<01:04,  2.91it/s]
                                               
[2024-05-08 13:48:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.ln.weight", shape: (3072,), dtype: float16
+
  3%|▎         | 6/195 [00:02<01:04,  2.91it/s]
                                               
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
  3%|▎         | 6/195 [00:02<01:04,  2.91it/s]
                                               
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
  3%|▎         | 6/195 [00:02<01:04,  2.91it/s]
                                               
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
  3%|▎         | 6/195 [00:02<01:04,  2.91it/s]
                                               
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
  3%|▎         | 6/195 [00:02<01:04,  2.91it/s]
  5%|▍         | 9/195 [00:02<00:38,  4.88it/s]
                                               
[2024-05-08 13:48:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
  5%|▍         | 9/195 [00:02<00:38,  4.88it/s]
                                               
[2024-05-08 13:48:56] INFO group_quantization.py:217: Compiling quantize function for key: ((3072, 3072), float16, cuda, axis=1, output_transpose=False)
+
  5%|▍         | 9/195 [00:02<00:38,  4.88it/s]
                                               
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
  5%|▍         | 9/195 [00:03<00:38,  4.88it/s]
                                               
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
  5%|▍         | 9/195 [00:03<00:38,  4.88it/s]
  6%|▌         | 11/195 [00:03<00:33,  5.49it/s]
                                                
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
  6%|▌         | 11/195 [00:03<00:33,  5.49it/s]
                                                
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
  6%|▌         | 11/195 [00:03<00:33,  5.49it/s]
                                                
[2024-05-08 13:48:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.ln.weight", shape: (3072,), dtype: float16
+
  6%|▌         | 11/195 [00:03<00:33,  5.49it/s]
                                                
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
  6%|▌         | 11/195 [00:03<00:33,  5.49it/s]
                                                
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
  6%|▌         | 11/195 [00:03<00:33,  5.49it/s]
  7%|▋         | 14/195 [00:03<00:22,  7.88it/s]
                                                
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
  7%|▋         | 14/195 [00:03<00:22,  7.88it/s]
                                                
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
  7%|▋         | 14/195 [00:03<00:22,  7.88it/s]
                                                
[2024-05-08 13:48:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
  7%|▋         | 14/195 [00:03<00:22,  7.88it/s]
  8%|▊         | 16/195 [00:03<00:19,  9.09it/s]
                                                
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
  8%|▊         | 16/195 [00:03<00:19,  9.09it/s]
                                                
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
  8%|▊         | 16/195 [00:03<00:19,  9.09it/s]
                                                
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
  8%|▊         | 16/195 [00:03<00:19,  9.09it/s]
                                                
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
  8%|▊         | 16/195 [00:03<00:19,  9.09it/s]
  9%|▉         | 18/195 [00:03<00:16, 10.45it/s]
                                                
[2024-05-08 13:48:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.ln.weight", shape: (3072,), dtype: float16
+
  9%|▉         | 18/195 [00:03<00:16, 10.45it/s]
                                                
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
  9%|▉         | 18/195 [00:03<00:16, 10.45it/s]
                                                
[2024-05-08 13:48:56] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
  9%|▉         | 18/195 [00:03<00:16, 10.45it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
  9%|▉         | 18/195 [00:03<00:16, 10.45it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
  9%|▉         | 18/195 [00:03<00:16, 10.45it/s]
 11%|█         | 21/195 [00:03<00:15, 11.57it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 11%|█         | 21/195 [00:03<00:15, 11.57it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 11%|█         | 21/195 [00:03<00:15, 11.57it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 11%|█         | 21/195 [00:03<00:15, 11.57it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 11%|█         | 21/195 [00:03<00:15, 11.57it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 11%|█         | 21/195 [00:03<00:15, 11.57it/s]
 12%|█▏        | 24/195 [00:03<00:11, 14.72it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.ln.weight", shape: (3072,), dtype: float16
+
 12%|█▏        | 24/195 [00:03<00:11, 14.72it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 12%|█▏        | 24/195 [00:03<00:11, 14.72it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 12%|█▏        | 24/195 [00:03<00:11, 14.72it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 12%|█▏        | 24/195 [00:04<00:11, 14.72it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 12%|█▏        | 24/195 [00:04<00:11, 14.72it/s]
 14%|█▍        | 27/195 [00:04<00:11, 15.13it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 14%|█▍        | 27/195 [00:04<00:11, 15.13it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 14%|█▍        | 27/195 [00:04<00:11, 15.13it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 14%|█▍        | 27/195 [00:04<00:11, 15.13it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 14%|█▍        | 27/195 [00:04<00:11, 15.13it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 14%|█▍        | 27/195 [00:04<00:11, 15.13it/s]
 15%|█▌        | 30/195 [00:04<00:09, 17.51it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.ln.weight", shape: (3072,), dtype: float16
+
 15%|█▌        | 30/195 [00:04<00:09, 17.51it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 15%|█▌        | 30/195 [00:04<00:09, 17.51it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 15%|█▌        | 30/195 [00:04<00:09, 17.51it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 15%|█▌        | 30/195 [00:04<00:09, 17.51it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 15%|█▌        | 30/195 [00:04<00:09, 17.51it/s]
 17%|█▋        | 33/195 [00:04<00:09, 16.37it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 17%|█▋        | 33/195 [00:04<00:09, 16.37it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 17%|█▋        | 33/195 [00:04<00:09, 16.37it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 17%|█▋        | 33/195 [00:04<00:09, 16.37it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 17%|█▋        | 33/195 [00:04<00:09, 16.37it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 17%|█▋        | 33/195 [00:04<00:09, 16.37it/s]
 18%|█▊        | 36/195 [00:04<00:08, 19.06it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.ln.weight", shape: (3072,), dtype: float16
+
 18%|█▊        | 36/195 [00:04<00:08, 19.06it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 18%|█▊        | 36/195 [00:04<00:08, 19.06it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 18%|█▊        | 36/195 [00:04<00:08, 19.06it/s]
                                                
[2024-05-08 13:48:57] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 18%|█▊        | 36/195 [00:04<00:08, 19.06it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 18%|█▊        | 36/195 [00:04<00:08, 19.06it/s]
 20%|██        | 39/195 [00:04<00:08, 18.39it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 20%|██        | 39/195 [00:04<00:08, 18.39it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 20%|██        | 39/195 [00:04<00:08, 18.39it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 20%|██        | 39/195 [00:04<00:08, 18.39it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 20%|██        | 39/195 [00:04<00:08, 18.39it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 20%|██        | 39/195 [00:04<00:08, 18.39it/s]
 22%|██▏       | 42/195 [00:04<00:07, 20.28it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.ln.weight", shape: (3072,), dtype: float16
+
 22%|██▏       | 42/195 [00:04<00:07, 20.28it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 22%|██▏       | 42/195 [00:04<00:07, 20.28it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 22%|██▏       | 42/195 [00:04<00:07, 20.28it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 22%|██▏       | 42/195 [00:04<00:07, 20.28it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 22%|██▏       | 42/195 [00:05<00:07, 20.28it/s]
 23%|██▎       | 45/195 [00:05<00:08, 18.31it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 23%|██▎       | 45/195 [00:05<00:08, 18.31it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 23%|██▎       | 45/195 [00:05<00:08, 18.31it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 23%|██▎       | 45/195 [00:05<00:08, 18.31it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 23%|██▎       | 45/195 [00:05<00:08, 18.31it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 23%|██▎       | 45/195 [00:05<00:08, 18.31it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.ln.weight", shape: (3072,), dtype: float16
+
 23%|██▎       | 45/195 [00:05<00:08, 18.31it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 23%|██▎       | 45/195 [00:05<00:08, 18.31it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 23%|██▎       | 45/195 [00:05<00:08, 18.31it/s]
 26%|██▌       | 50/195 [00:05<00:06, 23.07it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 26%|██▌       | 50/195 [00:05<00:06, 23.07it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 26%|██▌       | 50/195 [00:05<00:06, 23.07it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 26%|██▌       | 50/195 [00:05<00:06, 23.07it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 26%|██▌       | 50/195 [00:05<00:06, 23.07it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 26%|██▌       | 50/195 [00:05<00:06, 23.07it/s]
 27%|██▋       | 53/195 [00:05<00:06, 20.72it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 27%|██▋       | 53/195 [00:05<00:06, 20.72it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 27%|██▋       | 53/195 [00:05<00:06, 20.72it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.ln.weight", shape: (3072,), dtype: float16
+
 27%|██▋       | 53/195 [00:05<00:06, 20.72it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 27%|██▋       | 53/195 [00:05<00:06, 20.72it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 27%|██▋       | 53/195 [00:05<00:06, 20.72it/s]
 29%|██▊       | 56/195 [00:05<00:06, 21.59it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 29%|██▊       | 56/195 [00:05<00:06, 21.59it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 29%|██▊       | 56/195 [00:05<00:06, 21.59it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 29%|██▊       | 56/195 [00:05<00:06, 21.59it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 29%|██▊       | 56/195 [00:05<00:06, 21.59it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 29%|██▊       | 56/195 [00:05<00:06, 21.59it/s]
 30%|███       | 59/195 [00:05<00:06, 21.36it/s]
                                                
[2024-05-08 13:48:58] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 30%|███       | 59/195 [00:05<00:06, 21.36it/s]
                                                
[2024-05-08 13:48:59] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 30%|███       | 59/195 [00:05<00:06, 21.36it/s]
                                                
[2024-05-08 13:48:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.ln.weight", shape: (3072,), dtype: float16
+
 30%|███       | 59/195 [00:05<00:06, 21.36it/s]
                                                
[2024-05-08 13:48:59] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 30%|███       | 59/195 [00:05<00:06, 21.36it/s]
                                                
[2024-05-08 13:48:59] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 30%|███       | 59/195 [00:05<00:06, 21.36it/s]
 32%|███▏      | 62/195 [00:05<00:05, 22.18it/s]
                                                
[2024-05-08 13:48:59] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 32%|███▏      | 62/195 [00:05<00:05, 22.18it/s]
                                                
[2024-05-08 13:48:59] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 32%|███▏      | 62/195 [00:05<00:05, 22.18it/s]
                                                
[2024-05-08 13:48:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 32%|███▏      | 62/195 [00:05<00:05, 22.18it/s]
                                                
[2024-05-08 13:48:59] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 32%|███▏      | 62/195 [00:05<00:05, 22.18it/s]
                                                
[2024-05-08 13:48:59] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 32%|███▏      | 62/195 [00:05<00:05, 22.18it/s]
 33%|███▎      | 65/195 [00:05<00:06, 20.01it/s]
                                                
[2024-05-08 13:48:59] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 33%|███▎      | 65/195 [00:05<00:06, 20.01it/s]
                                                
[2024-05-08 13:48:59] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 33%|███▎      | 65/195 [00:05<00:06, 20.01it/s]
                                                
[2024-05-08 13:48:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.norm.weight", shape: (3072,), dtype: float16
+
 33%|███▎      | 65/195 [00:05<00:06, 20.01it/s]
                                                
[2024-05-08 13:48:59] INFO huggingface_loader.py:196: Unloading HF weight file: /tmp/tmpom_oz7t5/repo/model-00002-of-00002.safetensors
+
 33%|███▎      | 65/195 [00:05<00:06, 20.01it/s]
                                                
[2024-05-08 13:48:59] INFO huggingface_loader.py:184: Loading HF parameters from: /tmp/tmpom_oz7t5/repo/model-00001-of-00002.safetensors
+
 33%|███▎      | 65/195 [00:06<00:06, 20.01it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.embd.weight", shape: (32064, 3072), dtype: float16
+
 33%|███▎      | 65/195 [00:06<00:06, 20.01it/s]
 35%|███▍      | 68/195 [00:07<00:18,  6.74it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.ln.weight", shape: (3072,), dtype: float16
+
 35%|███▍      | 68/195 [00:07<00:18,  6.74it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 35%|███▍      | 68/195 [00:07<00:18,  6.74it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 35%|███▍      | 68/195 [00:07<00:18,  6.74it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 35%|███▍      | 68/195 [00:07<00:18,  6.74it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 35%|███▍      | 68/195 [00:07<00:18,  6.74it/s]
 36%|███▋      | 71/195 [00:07<00:15,  7.96it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 36%|███▋      | 71/195 [00:07<00:15,  7.96it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 36%|███▋      | 71/195 [00:07<00:15,  7.96it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 36%|███▋      | 71/195 [00:07<00:15,  7.96it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 36%|███▋      | 71/195 [00:07<00:15,  7.96it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 36%|███▋      | 71/195 [00:07<00:15,  7.96it/s]
 38%|███▊      | 74/195 [00:07<00:11, 10.10it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.ln.weight", shape: (3072,), dtype: float16
+
 38%|███▊      | 74/195 [00:07<00:11, 10.10it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 38%|███▊      | 74/195 [00:07<00:11, 10.10it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 38%|███▊      | 74/195 [00:07<00:11, 10.10it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 38%|███▊      | 74/195 [00:07<00:11, 10.10it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 38%|███▊      | 74/195 [00:07<00:11, 10.10it/s]
 39%|███▉      | 77/195 [00:07<00:10, 11.50it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 39%|███▉      | 77/195 [00:07<00:10, 11.50it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 39%|███▉      | 77/195 [00:07<00:10, 11.50it/s]
                                                
[2024-05-08 13:49:00] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 39%|███▉      | 77/195 [00:07<00:10, 11.50it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 39%|███▉      | 77/195 [00:07<00:10, 11.50it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 39%|███▉      | 77/195 [00:07<00:10, 11.50it/s]
 41%|████      | 80/195 [00:07<00:08, 13.85it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.ln.weight", shape: (3072,), dtype: float16
+
 41%|████      | 80/195 [00:07<00:08, 13.85it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 41%|████      | 80/195 [00:07<00:08, 13.85it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 41%|████      | 80/195 [00:07<00:08, 13.85it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 41%|████      | 80/195 [00:07<00:08, 13.85it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 41%|████      | 80/195 [00:07<00:08, 13.85it/s]
 43%|████▎     | 83/195 [00:07<00:07, 14.14it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 43%|████▎     | 83/195 [00:07<00:07, 14.14it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 43%|████▎     | 83/195 [00:07<00:07, 14.14it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 43%|████▎     | 83/195 [00:07<00:07, 14.14it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 43%|████▎     | 83/195 [00:07<00:07, 14.14it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 43%|████▎     | 83/195 [00:07<00:07, 14.14it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.ln.weight", shape: (3072,), dtype: float16
+
 43%|████▎     | 83/195 [00:08<00:07, 14.14it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 43%|████▎     | 83/195 [00:08<00:07, 14.14it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 43%|████▎     | 83/195 [00:08<00:07, 14.14it/s]
 45%|████▌     | 88/195 [00:08<00:05, 18.86it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 45%|████▌     | 88/195 [00:08<00:05, 18.86it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 45%|████▌     | 88/195 [00:08<00:05, 18.86it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 45%|████▌     | 88/195 [00:08<00:05, 18.86it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 45%|████▌     | 88/195 [00:08<00:05, 18.86it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 45%|████▌     | 88/195 [00:08<00:05, 18.86it/s]
 47%|████▋     | 91/195 [00:08<00:05, 18.04it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 47%|████▋     | 91/195 [00:08<00:05, 18.04it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 47%|████▋     | 91/195 [00:08<00:05, 18.04it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.ln.weight", shape: (3072,), dtype: float16
+
 47%|████▋     | 91/195 [00:08<00:05, 18.04it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 47%|████▋     | 91/195 [00:08<00:05, 18.04it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 47%|████▋     | 91/195 [00:08<00:05, 18.04it/s]
 48%|████▊     | 94/195 [00:08<00:05, 19.32it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 48%|████▊     | 94/195 [00:08<00:05, 19.32it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 48%|████▊     | 94/195 [00:08<00:05, 19.32it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 48%|████▊     | 94/195 [00:08<00:05, 19.32it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 48%|████▊     | 94/195 [00:08<00:05, 19.32it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 48%|████▊     | 94/195 [00:08<00:05, 19.32it/s]
 50%|████▉     | 97/195 [00:08<00:04, 19.68it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 50%|████▉     | 97/195 [00:08<00:04, 19.68it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 50%|████▉     | 97/195 [00:08<00:04, 19.68it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.ln.weight", shape: (3072,), dtype: float16
+
 50%|████▉     | 97/195 [00:08<00:04, 19.68it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 50%|████▉     | 97/195 [00:08<00:04, 19.68it/s]
                                                
[2024-05-08 13:49:01] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 50%|████▉     | 97/195 [00:08<00:04, 19.68it/s]
 51%|█████▏    | 100/195 [00:08<00:04, 20.86it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 51%|█████▏    | 100/195 [00:08<00:04, 20.86it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 51%|█████▏    | 100/195 [00:08<00:04, 20.86it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 51%|█████▏    | 100/195 [00:08<00:04, 20.86it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 51%|█████▏    | 100/195 [00:08<00:04, 20.86it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 51%|█████▏    | 100/195 [00:08<00:04, 20.86it/s]
 53%|█████▎    | 103/195 [00:08<00:04, 19.21it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 53%|█████▎    | 103/195 [00:08<00:04, 19.21it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 53%|█████▎    | 103/195 [00:08<00:04, 19.21it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.ln.weight", shape: (3072,), dtype: float16
+
 53%|█████▎    | 103/195 [00:08<00:04, 19.21it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 53%|█████▎    | 103/195 [00:08<00:04, 19.21it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 53%|█████▎    | 103/195 [00:08<00:04, 19.21it/s]
 54%|█████▍    | 106/195 [00:08<00:04, 20.28it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 54%|█████▍    | 106/195 [00:09<00:04, 20.28it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 54%|█████▍    | 106/195 [00:09<00:04, 20.28it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 54%|█████▍    | 106/195 [00:09<00:04, 20.28it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 54%|█████▍    | 106/195 [00:09<00:04, 20.28it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 54%|█████▍    | 106/195 [00:09<00:04, 20.28it/s]
 56%|█████▌    | 109/195 [00:09<00:04, 20.13it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 56%|█████▌    | 109/195 [00:09<00:04, 20.13it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 56%|█████▌    | 109/195 [00:09<00:04, 20.13it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.ln.weight", shape: (3072,), dtype: float16
+
 56%|█████▌    | 109/195 [00:09<00:04, 20.13it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 56%|█████▌    | 109/195 [00:09<00:04, 20.13it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 56%|█████▌    | 109/195 [00:09<00:04, 20.13it/s]
 57%|█████▋    | 112/195 [00:09<00:03, 21.02it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 57%|█████▋    | 112/195 [00:09<00:03, 21.02it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 57%|█████▋    | 112/195 [00:09<00:03, 21.02it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 57%|█████▋    | 112/195 [00:09<00:03, 21.02it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 57%|█████▋    | 112/195 [00:09<00:03, 21.02it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 57%|█████▋    | 112/195 [00:09<00:03, 21.02it/s]
 59%|█████▉    | 115/195 [00:09<00:04, 19.05it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 59%|█████▉    | 115/195 [00:09<00:04, 19.05it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 59%|█████▉    | 115/195 [00:09<00:04, 19.05it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.ln.weight", shape: (3072,), dtype: float16
+
 59%|█████▉    | 115/195 [00:09<00:04, 19.05it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 59%|█████▉    | 115/195 [00:09<00:04, 19.05it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 59%|█████▉    | 115/195 [00:09<00:04, 19.05it/s]
 61%|██████    | 118/195 [00:09<00:03, 20.04it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 61%|██████    | 118/195 [00:09<00:03, 20.04it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 61%|██████    | 118/195 [00:09<00:03, 20.04it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 61%|██████    | 118/195 [00:09<00:03, 20.04it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 61%|██████    | 118/195 [00:09<00:03, 20.04it/s]
                                                 
[2024-05-08 13:49:02] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 61%|██████    | 118/195 [00:09<00:03, 20.04it/s]
 62%|██████▏   | 121/195 [00:09<00:03, 19.93it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 62%|██████▏   | 121/195 [00:09<00:03, 19.93it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 62%|██████▏   | 121/195 [00:09<00:03, 19.93it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.ln.weight", shape: (3072,), dtype: float16
+
 62%|██████▏   | 121/195 [00:09<00:03, 19.93it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 62%|██████▏   | 121/195 [00:09<00:03, 19.93it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 62%|██████▏   | 121/195 [00:09<00:03, 19.93it/s]
 64%|██████▎   | 124/195 [00:09<00:03, 20.99it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 64%|██████▎   | 124/195 [00:09<00:03, 20.99it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 64%|██████▎   | 124/195 [00:09<00:03, 20.99it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 64%|██████▎   | 124/195 [00:09<00:03, 20.99it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 64%|██████▎   | 124/195 [00:09<00:03, 20.99it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 64%|██████▎   | 124/195 [00:10<00:03, 20.99it/s]
 65%|██████▌   | 127/195 [00:10<00:03, 19.24it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 65%|██████▌   | 127/195 [00:10<00:03, 19.24it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 65%|██���███▌   | 127/195 [00:10<00:03, 19.24it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.ln.weight", shape: (3072,), dtype: float16
+
 65%|██████▌   | 127/195 [00:10<00:03, 19.24it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 65%|██████▌   | 127/195 [00:10<00:03, 19.24it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 65%|██████▌   | 127/195 [00:10<00:03, 19.24it/s]
 67%|██████▋   | 130/195 [00:10<00:03, 20.20it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 67%|██████▋   | 130/195 [00:10<00:03, 20.20it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 67%|██████▋   | 130/195 [00:10<00:03, 20.20it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 67%|██████▋   | 130/195 [00:10<00:03, 20.20it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 67%|██████▋   | 130/195 [00:10<00:03, 20.20it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 67%|██████▋   | 130/195 [00:10<00:03, 20.20it/s]
 68%|██████▊   | 133/195 [00:10<00:03, 20.06it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 68%|██████▊   | 133/195 [00:10<00:03, 20.06it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 68%|██████▊   | 133/195 [00:10<00:03, 20.06it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.ln.weight", shape: (3072,), dtype: float16
+
 68%|██████▊   | 133/195 [00:10<00:03, 20.06it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 68%|██████▊   | 133/195 [00:10<00:03, 20.06it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 68%|██████▊   | 133/195 [00:10<00:03, 20.06it/s]
 70%|██████▉   | 136/195 [00:10<00:02, 20.95it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 70%|██████▉   | 136/195 [00:10<00:02, 20.95it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 70%|██████▉   | 136/195 [00:10<00:02, 20.95it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 70%|██████▉   | 136/195 [00:10<00:02, 20.95it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 70%|██████▉   | 136/195 [00:10<00:02, 20.95it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 70%|██████▉   | 136/195 [00:10<00:02, 20.95it/s]
 71%|███████▏  | 139/195 [00:10<00:02, 18.99it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 71%|███████▏  | 139/195 [00:10<00:02, 18.99it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 71%|███████▏  | 139/195 [00:10<00:02, 18.99it/s]
                                                 
[2024-05-08 13:49:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.ln.weight", shape: (3072,), dtype: float16
+
 71%|███████▏  | 139/195 [00:10<00:02, 18.99it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 71%|███████▏  | 139/195 [00:10<00:02, 18.99it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 71%|███████▏  | 139/195 [00:10<00:02, 18.99it/s]
 73%|███████▎  | 142/195 [00:10<00:02, 19.99it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 73%|███████▎  | 142/195 [00:10<00:02, 19.99it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 73%|███████▎  | 142/195 [00:10<00:02, 19.99it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 73%|███████▎  | 142/195 [00:10<00:02, 19.99it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 73%|███████▎  | 142/195 [00:10<00:02, 19.99it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 73%|███████▎  | 142/195 [00:10<00:02, 19.99it/s]
 74%|███████▍  | 145/195 [00:10<00:02, 19.97it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 74%|███████▍  | 145/195 [00:10<00:02, 19.97it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 74%|███████▍  | 145/195 [00:11<00:02, 19.97it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.ln.weight", shape: (3072,), dtype: float16
+
 74%|███████▍  | 145/195 [00:11<00:02, 19.97it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 74%|███████▍  | 145/195 [00:11<00:02, 19.97it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 74%|███████▍  | 145/195 [00:11<00:02, 19.97it/s]
 76%|███████▌  | 148/195 [00:11<00:02, 19.56it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 76%|███████▌  | 148/195 [00:11<00:02, 19.56it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 76%|██████���▌  | 148/195 [00:11<00:02, 19.56it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 76%|███████▌  | 148/195 [00:11<00:02, 19.56it/s]
 77%|███████▋  | 150/195 [00:11<00:02, 18.57it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 77%|███████▋  | 150/195 [00:11<00:02, 18.57it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 77%|███████▋  | 150/195 [00:11<00:02, 18.57it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 77%|███████▋  | 150/195 [00:11<00:02, 18.57it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 77%|███████▋  | 150/195 [00:11<00:02, 18.57it/s]
 78%|███████▊  | 152/195 [00:11<00:02, 18.42it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 78%|███████▊  | 152/195 [00:11<00:02, 18.42it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 78%|███████▊  | 152/195 [00:11<00:02, 18.42it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.ln.weight", shape: (3072,), dtype: float16
+
 78%|███████▊  | 152/195 [00:11<00:02, 18.42it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 78%|███████▊  | 152/195 [00:11<00:02, 18.42it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 78%|███████▊  | 152/195 [00:11<00:02, 18.42it/s]
 79%|███████▉  | 155/195 [00:11<00:01, 21.00it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 79%|███████▉  | 155/195 [00:11<00:01, 21.00it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 79%|███████▉  | 155/195 [00:11<00:01, 21.00it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 79%|███████▉  | 155/195 [00:11<00:01, 21.00it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 79%|███████▉  | 155/195 [00:11<00:01, 21.00it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 79%|███████▉  | 155/195 [00:11<00:01, 21.00it/s]
 81%|████████  | 158/195 [00:11<00:01, 20.89it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 81%|████████  | 158/195 [00:11<00:01, 20.89it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 81%|████████  | 158/195 [00:11<00:01, 20.89it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.ln.weight", shape: (3072,), dtype: float16
+
 81%|████████  | 158/195 [00:11<00:01, 20.89it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 81%|████████  | 158/195 [00:11<00:01, 20.89it/s]
                                                 
[2024-05-08 13:49:04] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 81%|████████  | 158/195 [00:11<00:01, 20.89it/s]
 83%|████████▎ | 161/195 [00:11<00:01, 21.94it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 83%|████████▎ | 161/195 [00:11<00:01, 21.94it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 83%|████████▎ | 161/195 [00:11<00:01, 21.94it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 83%|████████▎ | 161/195 [00:11<00:01, 21.94it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 83%|████████▎ | 161/195 [00:11<00:01, 21.94it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 83%|████████▎ | 161/195 [00:11<00:01, 21.94it/s]
 84%|████████▍ | 164/195 [00:11<00:01, 19.70it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 84%|████████▍ | 164/195 [00:11<00:01, 19.70it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 84%|████████▍ | 164/195 [00:11<00:01, 19.70it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.ln.weight", shape: (3072,), dtype: float16
+
 84%|████████▍ | 164/195 [00:11<00:01, 19.70it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 84%|████████▍ | 164/195 [00:11<00:01, 19.70it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 84%|████████▍ | 164/195 [00:11<00:01, 19.70it/s]
 86%|████████▌ | 167/195 [00:11<00:01, 20.83it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 86%|████████▌ | 167/195 [00:12<00:01, 20.83it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 86%|████████▌ | 167/195 [00:12<00:01, 20.83it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 86%|████████▌ | 167/195 [00:12<00:01, 20.83it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 86%|████████▌ | 167/195 [00:12<00:01, 20.83it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 86%|████████▌ | 167/195 [00:12<00:01, 20.83it/s]
 87%|████████▋ | 170/195 [00:12<00:01, 20.76it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 87%|████████▋ | 170/195 [00:12<00:01, 20.76it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 87%|████████▋ | 170/195 [00:12<00:01, 20.76it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.ln.weight", shape: (3072,), dtype: float16
+
 87%|████████▋ | 170/195 [00:12<00:01, 20.76it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 87%|████████▋ | 170/195 [00:12<00:01, 20.76it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 87%|████████▋ | 170/195 [00:12<00:01, 20.76it/s]
 89%|████████▊ | 173/195 [00:12<00:01, 21.77it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 89%|████████▊ | 173/195 [00:12<00:01, 21.77it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 89%|████████▊ | 173/195 [00:12<00:01, 21.77it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 89%|████████▊ | 173/195 [00:12<00:01, 21.77it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 89%|████████▊ | 173/195 [00:12<00:01, 21.77it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 89%|████████▊ | 173/195 [00:12<00:01, 21.77it/s]
 90%|█████████ | 176/195 [00:12<00:00, 19.72it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 90%|█████████ | 176/195 [00:12<00:00, 19.72it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 90%|█████████ | 176/195 [00:12<00:00, 19.72it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.ln.weight", shape: (3072,), dtype: float16
+
 90%|█████████ | 176/195 [00:12<00:00, 19.72it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 90%|█████████ | 176/195 [00:12<00:00, 19.72it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 90%|█████████ | 176/195 [00:12<00:00, 19.72it/s]
 92%|█████████▏| 179/195 [00:12<00:00, 20.82it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 92%|█████████▏| 179/195 [00:12<00:00, 20.82it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 92%|█████��███▏| 179/195 [00:12<00:00, 20.82it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 92%|█████████▏| 179/195 [00:12<00:00, 20.82it/s]
                                                 
[2024-05-08 13:49:05] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 92%|█████████▏| 179/195 [00:12<00:00, 20.82it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 92%|█████████▏| 179/195 [00:12<00:00, 20.82it/s]
 93%|█████████▎| 182/195 [00:12<00:00, 20.78it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 93%|█████████▎| 182/195 [00:12<00:00, 20.78it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 93%|█████████▎| 182/195 [00:12<00:00, 20.78it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.ln.weight", shape: (3072,), dtype: float16
+
 93%|█████████▎| 182/195 [00:12<00:00, 20.78it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 93%|█████████▎| 182/195 [00:12<00:00, 20.78it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 93%|█████████▎| 182/195 [00:12<00:00, 20.78it/s]
 95%|█████████▍| 185/195 [00:12<00:00, 21.81it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 95%|█████████▍| 185/195 [00:12<00:00, 21.81it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 95%|█████████▍| 185/195 [00:12<00:00, 21.81it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 95%|█████████▍| 185/195 [00:12<00:00, 21.81it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 95%|█████████▍| 185/195 [00:12<00:00, 21.81it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 95%|█████████▍| 185/195 [00:13<00:00, 21.81it/s]
 96%|█████████▋| 188/195 [00:13<00:00, 19.75it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 96%|█████████▋| 188/195 [00:13<00:00, 19.75it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 96%|█████████▋| 188/195 [00:13<00:00, 19.75it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.ln.weight", shape: (3072,), dtype: float16
+
 96%|█████████▋| 188/195 [00:13<00:00, 19.75it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
+
 96%|█████████▋| 188/195 [00:13<00:00, 19.75it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float16
+
 96%|█████████▋| 188/195 [00:13<00:00, 19.75it/s]
 98%|█████████▊| 191/195 [00:13<00:00, 20.86it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
+
 98%|█████████▊| 191/195 [00:13<00:00, 20.86it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float16
+
 98%|█████████▊| 191/195 [00:13<00:00, 20.86it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.post_attention_layernorm.weight", shape: (3072,), dtype: float16
+
 98%|█████████▊| 191/195 [00:13<00:00, 20.86it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
+
 98%|█████████▊| 191/195 [00:13<00:00, 20.86it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float16
+
 98%|█████████▊| 191/195 [00:13<00:00, 20.86it/s]
 99%|█████████▉| 194/195 [00:13<00:00, 20.80it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
+
 99%|█████████▉| 194/195 [00:13<00:00, 20.80it/s]
                                                 
[2024-05-08 13:49:06] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float16
+
 99%|█████████▉| 194/195 [00:13<00:00, 20.80it/s]
100%|██████████| 195/195 [00:13<00:00, 14.60it/s]
+[2024-05-08 13:49:06] INFO huggingface_loader.py:196: Unloading HF weight file: /tmp/tmpom_oz7t5/repo/model-00001-of-00002.safetensors
+[2024-05-08 13:49:06] INFO stats.py:76: Time usage: HF loading: 1.482 sec; Pre-quantization mapping: 5.765 sec; Quantization: 1.437 sec
+[2024-05-08 13:49:06] INFO stats.py:90: RAM usage: Peak RAM: 9.262 GB. Total bytes loaded from disk: 14.235 GB
+[2024-05-08 13:49:06] INFO convert_weight.py:155: Parameter size after quantization: 2.266 GB
+[2024-05-08 13:49:06] INFO convert_weight.py:160: Total parameters: 3,821,079,552
+[2024-05-08 13:49:06] INFO convert_weight.py:161: Bits per parameter: 5.093
+[2024-05-08 13:49:06] INFO convert_weight.py:166: Saved to directory: /tmp/tmpn0y_4cix
+
+All finished, 82 total shards committed, record saved to /tmp/tmpn0y_4cix/ndarray-cache.json