Initial commit

logs.txt

@@ -0,0 +1,389 @@
+/usr/bin/python3 -m mlc_llm gen_config dist/models/stablelm-2-zephyr-1_6b --quantization q4f32_1 --conv-template stablelm-2 --output /tmp/tmpt74_sq0w --context-window-size 4096
+[2024-05-24 18:29:33] INFO auto_config.py:115: Found model configuration: dist/models/stablelm-2-zephyr-1_6b/config.json
+[2024-05-24 18:29:33] INFO auto_config.py:153: Found model type: stablelm. Use `--model-type` to override.
+[2024-05-24 18:29:33] INFO stablelm_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (4096)
+[2024-05-24 18:29:33] INFO stablelm_model.py:66: prefill_chunk_size defaults to 2048
+[2024-05-24 18:29:33] INFO config.py:106: Overriding context_window_size from 4096 to 4096
+[2024-05-24 18:29:33] INFO config.py:106: Overriding max_batch_size from 1 to 80
+[2024-05-24 18:29:33] INFO gen_config.py:255: [generation_config.json] Setting bos_token_id: 100257
+[2024-05-24 18:29:33] INFO gen_config.py:255: [generation_config.json] Setting eos_token_id: 100257
+[2024-05-24 18:29:33] INFO gen_config.py:269: Not found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/tokenizer.model
+[2024-05-24 18:29:33] INFO gen_config.py:267: Found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/tokenizer.json. Copying to /tmp/tmpt74_sq0w/tokenizer.json
+[2024-05-24 18:29:33] INFO gen_config.py:267: Found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/vocab.json. Copying to /tmp/tmpt74_sq0w/vocab.json
+[2024-05-24 18:29:33] INFO gen_config.py:267: Found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/merges.txt. Copying to /tmp/tmpt74_sq0w/merges.txt
+[2024-05-24 18:29:33] INFO gen_config.py:269: Not found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/added_tokens.json
+[2024-05-24 18:29:33] INFO gen_config.py:267: Found tokenizer config: dist/models/stablelm-2-zephyr-1_6b/tokenizer_config.json. Copying to /tmp/tmpt74_sq0w/tokenizer_config.json
+[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting pad_token_id: 0
+[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting temperature: 0.7
+[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting presence_penalty: 0.0
+[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting frequency_penalty: 0.0
+[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting repetition_penalty: 1.0
+[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting top_p: 0.95
+[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting mean_gen_len: 128
+[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting max_gen_len: 512
+[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting shift_fill_factor: 0.3
+[2024-05-24 18:29:33] INFO gen_config.py:335: Dumping configuration file to: /tmp/tmpt74_sq0w/mlc-chat-config.json
+/usr/bin/python3 -m mlc_llm convert_weight dist/models/stablelm-2-zephyr-1_6b --quantization q4f32_1 --source-format auto --output /tmp/tmpt74_sq0w
+[2024-05-24 18:29:34] INFO auto_config.py:115: Found model configuration: dist/models/stablelm-2-zephyr-1_6b/config.json
+[2024-05-24 18:29:36] INFO auto_device.py:79: Found device: cuda:0
+[2024-05-24 18:29:37] INFO auto_device.py:88: Not found device: rocm:0
+[2024-05-24 18:29:38] INFO auto_device.py:88: Not found device: metal:0
+[2024-05-24 18:29:39] INFO auto_device.py:88: Not found device: vulkan:0
+[2024-05-24 18:29:40] INFO auto_device.py:88: Not found device: opencl:0
+[2024-05-24 18:29:40] INFO auto_device.py:35: Using device: cuda:0
+[2024-05-24 18:29:40] INFO auto_weight.py:70: Finding weights in: dist/models/stablelm-2-zephyr-1_6b
+[2024-05-24 18:29:40] INFO auto_weight.py:136: Not found Huggingface PyTorch
+[2024-05-24 18:29:40] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: dist/models/stablelm-2-zephyr-1_6b/model.safetensors.index.json
+[2024-05-24 18:29:40] INFO auto_weight.py:106: Using source weight configuration: dist/models/stablelm-2-zephyr-1_6b/model.safetensors.index.json. Use `--source` to override.
+[2024-05-24 18:29:40] INFO auto_weight.py:110: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
+[2024-05-24 18:29:40] INFO auto_config.py:153: Found model type: stablelm. Use `--model-type` to override.
+[2024-05-24 18:29:40] INFO stablelm_model.py:49: context_window_size not found in config.json. Falling back to max_position_embeddings (4096)
+[2024-05-24 18:29:40] INFO stablelm_model.py:66: prefill_chunk_size defaults to 2048
+Weight conversion with arguments:
+  --config          dist/models/stablelm-2-zephyr-1_6b/config.json
+  --quantization    GroupQuantize(name='q4f32_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float32', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7)
+  --model-type      stablelm
+  --device          cuda:0
+  --source          dist/models/stablelm-2-zephyr-1_6b/model.safetensors.index.json
+  --source-format   huggingface-safetensor
+  --output          /tmp/tmpt74_sq0w
+Start storing to cache /tmp/tmpt74_sq0w
+
  0%|          | 0/220 [00:00<?, ?it/s]
                                       
+
  0%|          | 0/220 [00:00<?, ?it/s]
                                       
+
  0%|          | 0/220 [00:01<?, ?it/s]
                                       
+
  0%|          | 0/220 [00:03<?, ?it/s]
                                       
+
  0%|          | 0/220 [00:03<?, ?it/s]/home/tlopex/.local/lib/python3.8/site-packages/numpy/core/getlimits.py:518: UserWarning: The value of the smallest subnormal for <class 'numpy.float32'> type is zero.
+  setattr(self, word, getattr(machar, word).flat[0])
+/home/tlopex/.local/lib/python3.8/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for <class 'numpy.float32'> type is zero.
+  return self._float_to_str(self.smallest_subnormal)
+
  0%|          | 1/220 [00:03<12:53,  3.53s/it]
                                               
+
  0%|          | 1/220 [00:04<12:53,  3.53s/it]
                                               
+
  0%|          | 1/220 [00:04<12:53,  3.53s/it]
  1%|          | 2/220 [00:04<07:50,  2.16s/it]
                                               
+
  1%|          | 2/220 [00:04<07:50,  2.16s/it]
                                               
+
  1%|          | 2/220 [00:04<07:50,  2.16s/it]
                                               
+
  1%|          | 2/220 [00:04<07:50,  2.16s/it]
                                               
+
  1%|          | 2/220 [00:05<07:50,  2.16s/it]
                                               
+
  1%|          | 2/220 [00:05<07:50,  2.16s/it]
  2%|▏         | 5/220 [00:05<02:28,  1.45it/s]
                                               
+
  2%|▏         | 5/220 [00:05<02:28,  1.45it/s]
                                               
+
  2%|▏         | 5/220 [00:05<02:28,  1.45it/s]
                                               
+
  2%|▏         | 5/220 [00:05<02:28,  1.45it/s]
  3%|▎         | 6/220 [00:05<02:09,  1.65it/s]
                                               
+
  3%|▎         | 6/220 [00:05<02:09,  1.65it/s]
                                               
+
  3%|▎         | 6/220 [00:05<02:09,  1.65it/s]
                                               
+
  3%|▎         | 6/220 [00:05<02:09,  1.65it/s]
                                               
+
  3%|▎         | 6/220 [00:05<02:09,  1.65it/s]
                                               
+
  3%|▎         | 6/220 [00:05<02:09,  1.65it/s]
                                               
+
  3%|▎         | 6/220 [00:05<02:09,  1.65it/s]
  5%|▍         | 10/220 [00:05<01:00,  3.46it/s]
                                                
+
  5%|▍         | 10/220 [00:05<01:00,  3.46it/s]
                                                
+
  5%|▍         | 10/220 [00:05<01:00,  3.46it/s]
                                                
+
  5%|▍         | 10/220 [00:05<01:00,  3.46it/s]
  5%|▌         | 11/220 [00:05<00:59,  3.54it/s]
                                                
+
  5%|▌         | 11/220 [00:05<00:59,  3.54it/s]
                                                
+
  5%|▌         | 11/220 [00:05<00:59,  3.54it/s]
                                                
+
  5%|▌         | 11/220 [00:05<00:59,  3.54it/s]
                                                
+
  5%|▌         | 11/220 [00:05<00:59,  3.54it/s]
                                                
+
  5%|▌         | 11/220 [00:06<00:59,  3.54it/s]
                                                
+
  5%|▌         | 11/220 [00:06<00:59,  3.54it/s]
  7%|▋         | 15/220 [00:06<00:32,  6.24it/s]
                                                
+
  7%|▋         | 15/220 [00:06<00:32,  6.24it/s]
                                                
+
  7%|▋         | 15/220 [00:06<00:32,  6.24it/s]
                                                
+
  7%|▋         | 15/220 [00:06<00:32,  6.24it/s]
                                                
+
  7%|▋         | 15/220 [00:06<00:32,  6.24it/s]
                                                
+
  7%|▋         | 15/220 [00:06<00:32,  6.24it/s]
                                                
+
  7%|▋         | 15/220 [00:06<00:32,  6.24it/s]
                                                
+
  7%|▋         | 15/220 [00:06<00:32,  6.24it/s]
                                                
+
  7%|▋         | 15/220 [00:06<00:32,  6.24it/s]
                                                
+
  7%|▋         | 15/220 [00:06<00:32,  6.24it/s]
                                                
+
  7%|▋         | 15/220 [00:06<00:32,  6.24it/s]
                                                
+
  7%|▋         | 15/220 [00:06<00:32,  6.24it/s]
                                                
+
  7%|▋         | 15/220 [00:06<00:32,  6.24it/s]
                                                
+
  7%|▋         | 15/220 [00:06<00:32,  6.24it/s]
 11%|█         | 24/220 [00:06<00:14, 13.50it/s]
                                                
+
 11%|█         | 24/220 [00:06<00:14, 13.50it/s]
                                                
+
 11%|█         | 24/220 [00:06<00:14, 13.50it/s]
                                                
+
 11%|█         | 24/220 [00:06<00:14, 13.50it/s]
                                                
+
 11%|█         | 24/220 [00:06<00:14, 13.50it/s]
                                                
+
 11%|█         | 24/220 [00:06<00:14, 13.50it/s]
                                                
+
 11%|█         | 24/220 [00:06<00:14, 13.50it/s]
                                                
+
 11%|█         | 24/220 [00:06<00:14, 13.50it/s]
                                                
+
 11%|█         | 24/220 [00:06<00:14, 13.50it/s]
                                                
+
 11%|█         | 24/220 [00:06<00:14, 13.50it/s]
                                                
+
 11%|█         | 24/220 [00:06<00:14, 13.50it/s]
                                                
+
 11%|█         | 24/220 [00:06<00:14, 13.50it/s]
                                                
+
 11%|█         | 24/220 [00:06<00:14, 13.50it/s]
                                                
+
 11%|█         | 24/220 [00:06<00:14, 13.50it/s]
 15%|█▌        | 33/220 [00:06<00:09, 20.58it/s]
                                                
+
 15%|█▌        | 33/220 [00:06<00:09, 20.58it/s]
                                                
+
 15%|█▌        | 33/220 [00:06<00:09, 20.58it/s]
                                                
+
 15%|█▌        | 33/220 [00:06<00:09, 20.58it/s]
                                                
+
 15%|█▌        | 33/220 [00:06<00:09, 20.58it/s]
                                                
+
 15%|█▌        | 33/220 [00:06<00:09, 20.58it/s]
                                                
+
 15%|█▌        | 33/220 [00:06<00:09, 20.58it/s]
                                                
+
 15%|█▌        | 33/220 [00:06<00:09, 20.58it/s]
                                                
+
 15%|█▌        | 33/220 [00:06<00:09, 20.58it/s]
                                                
+
 15%|█▌        | 33/220 [00:06<00:09, 20.58it/s]
                                                
+
 15%|█▌        | 33/220 [00:06<00:09, 20.58it/s]
                                                
+
 15%|█▌        | 33/220 [00:06<00:09, 20.58it/s]
                                                
+
 15%|█▌        | 33/220 [00:06<00:09, 20.58it/s]
                                                
+
 15%|█▌        | 33/220 [00:06<00:09, 20.58it/s]
 19%|█▉        | 42/220 [00:06<00:06, 27.17it/s]
                                                
+
 19%|█▉        | 42/220 [00:06<00:06, 27.17it/s]
                                                
+
 19%|█▉        | 42/220 [00:06<00:06, 27.17it/s]
                                                
+
 19%|█▉        | 42/220 [00:06<00:06, 27.17it/s]
                                                
+
 19%|█▉        | 42/220 [00:06<00:06, 27.17it/s]
                                                
+
 19%|█▉        | 42/220 [00:06<00:06, 27.17it/s]
                                                
+
 19%|█▉        | 42/220 [00:06<00:06, 27.17it/s]
                                                
+
 19%|█▉        | 42/220 [00:06<00:06, 27.17it/s]
                                                
+
 19%|█▉        | 42/220 [00:06<00:06, 27.17it/s]
                                                
+
 19%|█▉        | 42/220 [00:06<00:06, 27.17it/s]
                                                
+
 19%|█▉        | 42/220 [00:06<00:06, 27.17it/s]
                                                
+
 19%|█▉        | 42/220 [00:06<00:06, 27.17it/s]
                                                
+
 19%|█▉        | 42/220 [00:06<00:06, 27.17it/s]
                                                
+
 19%|█▉        | 42/220 [00:06<00:06, 27.17it/s]
 23%|██▎       | 51/220 [00:06<00:05, 32.93it/s]
                                                
+
 23%|██▎       | 51/220 [00:06<00:05, 32.93it/s]
                                                
+
 23%|██▎       | 51/220 [00:06<00:05, 32.93it/s]
                                                
+
 23%|██▎       | 51/220 [00:06<00:05, 32.93it/s]
                                                
+
 23%|██▎       | 51/220 [00:06<00:05, 32.93it/s]
                                                
+
 23%|██▎       | 51/220 [00:06<00:05, 32.93it/s]
                                                
+
 23%|██▎       | 51/220 [00:06<00:05, 32.93it/s]
                                                
+
 23%|██▎       | 51/220 [00:06<00:05, 32.93it/s]
                                                
+
 23%|██▎       | 51/220 [00:06<00:05, 32.93it/s]
                                                
+
 23%|██▎       | 51/220 [00:06<00:05, 32.93it/s]
                                                
+
 23%|██▎       | 51/220 [00:06<00:05, 32.93it/s]
                                                
+
 23%|██▎       | 51/220 [00:06<00:05, 32.93it/s]
                                                
+
 23%|██▎       | 51/220 [00:06<00:05, 32.93it/s]
                                                
+
 23%|██▎       | 51/220 [00:06<00:05, 32.93it/s]
 27%|██▋       | 60/220 [00:06<00:04, 37.69it/s]
                                                
+
 27%|██▋       | 60/220 [00:06<00:04, 37.69it/s]
                                                
+
 27%|██▋       | 60/220 [00:06<00:04, 37.69it/s]
                                                
+
 27%|██▋       | 60/220 [00:06<00:04, 37.69it/s]
                                                
+
 27%|██▋       | 60/220 [00:07<00:04, 37.69it/s]
                                                
+
 27%|██▋       | 60/220 [00:07<00:04, 37.69it/s]
                                                
+
 27%|██▋       | 60/220 [00:07<00:04, 37.69it/s]
                                                
+
 27%|██▋       | 60/220 [00:07<00:04, 37.69it/s]
                                                
+
 27%|██▋       | 60/220 [00:07<00:04, 37.69it/s]
                                                
+
 27%|██▋       | 60/220 [00:07<00:04, 37.69it/s]
                                                
+
 27%|██▋       | 60/220 [00:07<00:04, 37.69it/s]
                                                
+
 27%|██▋       | 60/220 [00:07<00:04, 37.69it/s]
                                                
+
 27%|██▋       | 60/220 [00:07<00:04, 37.69it/s]
                                                
+
 27%|██▋       | 60/220 [00:07<00:04, 37.69it/s]
 31%|███▏      | 69/220 [00:07<00:03, 41.52it/s]
                                                
+
 31%|███▏      | 69/220 [00:07<00:03, 41.52it/s]
                                                
+
 31%|███▏      | 69/220 [00:07<00:03, 41.52it/s]
                                                
+
 31%|███▏      | 69/220 [00:07<00:03, 41.52it/s]
                                                
+
 31%|███▏      | 69/220 [00:07<00:03, 41.52it/s]
                                                
+
 31%|███▏      | 69/220 [00:07<00:03, 41.52it/s]
                                                
+
 31%|███▏      | 69/220 [00:07<00:03, 41.52it/s]
                                                
+
 31%|███▏      | 69/220 [00:07<00:03, 41.52it/s]
                                                
+
 31%|███▏      | 69/220 [00:07<00:03, 41.52it/s]
                                                
+
 31%|███▏      | 69/220 [00:07<00:03, 41.52it/s]
                                                
+
 31%|███▏      | 69/220 [00:07<00:03, 41.52it/s]
                                                
+
 31%|███▏      | 69/220 [00:07<00:03, 41.52it/s]
                                                
+
 31%|███▏      | 69/220 [00:07<00:03, 41.52it/s]
                                                
+
 31%|███▏      | 69/220 [00:07<00:03, 41.52it/s]
 35%|███▌      | 78/220 [00:07<00:03, 44.44it/s]
                                                
+
 35%|███▌      | 78/220 [00:07<00:03, 44.44it/s]
                                                
+
 35%|███▌      | 78/220 [00:07<00:03, 44.44it/s]
                                                
+
 35%|███▌      | 78/220 [00:07<00:03, 44.44it/s]
                                                
+
 35%|███▌      | 78/220 [00:07<00:03, 44.44it/s]
                                                
+
 35%|███▌      | 78/220 [00:07<00:03, 44.44it/s]
                                                
+
 35%|███▌      | 78/220 [00:07<00:03, 44.44it/s]
                                                
+
 35%|███▌      | 78/220 [00:07<00:03, 44.44it/s]
                                                
+
 35%|███▌      | 78/220 [00:07<00:03, 44.44it/s]
                                                
+
 35%|███▌      | 78/220 [00:07<00:03, 44.44it/s]
                                                
+
 35%|███▌      | 78/220 [00:07<00:03, 44.44it/s]
                                                
+
 35%|███▌      | 78/220 [00:07<00:03, 44.44it/s]
                                                
+
 35%|███▌      | 78/220 [00:07<00:03, 44.44it/s]
                                                
+
 35%|███▌      | 78/220 [00:07<00:03, 44.44it/s]
 40%|███▉      | 87/220 [00:07<00:02, 46.64it/s]
                                                
+
 40%|███▉      | 87/220 [00:07<00:02, 46.64it/s]
                                                
+
 40%|███▉      | 87/220 [00:07<00:02, 46.64it/s]
                                                
+
 40%|███▉      | 87/220 [00:07<00:02, 46.64it/s]
                                                
+
 40%|███▉      | 87/220 [00:07<00:02, 46.64it/s]
                                                
+
 40%|███▉      | 87/220 [00:07<00:02, 46.64it/s]
                                                
+
 40%|███▉      | 87/220 [00:07<00:02, 46.64it/s]
                                                
+
 40%|███▉      | 87/220 [00:07<00:02, 46.64it/s]
                                                
+
 40%|███▉      | 87/220 [00:07<00:02, 46.64it/s]
                                                
+
 40%|███▉      | 87/220 [00:07<00:02, 46.64it/s]
                                                
+
 40%|███▉      | 87/220 [00:07<00:02, 46.64it/s]
                                                
+
 40%|███▉      | 87/220 [00:07<00:02, 46.64it/s]
                                                
+
 40%|███▉      | 87/220 [00:07<00:02, 46.64it/s]
                                                
+
 40%|███▉      | 87/220 [00:07<00:02, 46.64it/s]
 44%|████▎     | 96/220 [00:07<00:02, 48.27it/s]
                                                
+
 44%|████▎     | 96/220 [00:07<00:02, 48.27it/s]
                                                
+
 44%|████▎     | 96/220 [00:07<00:02, 48.27it/s]
                                                
+
 44%|████▎     | 96/220 [00:07<00:02, 48.27it/s]
                                                
+
 44%|████▎     | 96/220 [00:07<00:02, 48.27it/s]
                                                
+
 44%|████▎     | 96/220 [00:07<00:02, 48.27it/s]
                                                
+
 44%|████▎     | 96/220 [00:07<00:02, 48.27it/s]
                                                
+
 44%|████▎     | 96/220 [00:07<00:02, 48.27it/s]
                                                
+
 44%|████▎     | 96/220 [00:07<00:02, 48.27it/s]
                                                
+
 44%|████▎     | 96/220 [00:07<00:02, 48.27it/s]
                                                
+
 44%|████▎     | 96/220 [00:07<00:02, 48.27it/s]
                                                
+
 44%|████▎     | 96/220 [00:07<00:02, 48.27it/s]
                                                
+
 44%|████▎     | 96/220 [00:07<00:02, 48.27it/s]
                                                
+
 44%|████▎     | 96/220 [00:07<00:02, 48.27it/s]
 48%|████▊     | 105/220 [00:07<00:02, 49.46it/s]
                                                 
+
 48%|████▊     | 105/220 [00:07<00:02, 49.46it/s]
                                                 
+
 48%|████▊     | 105/220 [00:07<00:02, 49.46it/s]
                                                 
+
 48%|████▊     | 105/220 [00:07<00:02, 49.46it/s]
                                                 
+
 48%|████▊     | 105/220 [00:07<00:02, 49.46it/s]
                                                 
+
 48%|████▊     | 105/220 [00:07<00:02, 49.46it/s]
                                                 
+
 48%|████▊     | 105/220 [00:07<00:02, 49.46it/s]
                                                 
+
 48%|████▊     | 105/220 [00:07<00:02, 49.46it/s]
                                                 
+
 48%|████▊     | 105/220 [00:07<00:02, 49.46it/s]
                                                 
+
 48%|████▊     | 105/220 [00:07<00:02, 49.46it/s]
                                                 
+
 48%|████▊     | 105/220 [00:07<00:02, 49.46it/s]
                                                 
+
 48%|████▊     | 105/220 [00:07<00:02, 49.46it/s]
                                                 
+
 48%|████▊     | 105/220 [00:07<00:02, 49.46it/s]
                                                 
+
 48%|████▊     | 105/220 [00:08<00:02, 49.46it/s]
 52%|█████▏    | 114/220 [00:08<00:02, 50.30it/s]
                                                 
+
 52%|█████▏    | 114/220 [00:08<00:02, 50.30it/s]
                                                 
+
 52%|█████▏    | 114/220 [00:08<00:02, 50.30it/s]
                                                 
+
 52%|█████▏    | 114/220 [00:08<00:02, 50.30it/s]
                                                 
+
 52%|█████▏    | 114/220 [00:08<00:02, 50.30it/s]
                                                 
+
 52%|█████▏    | 114/220 [00:08<00:02, 50.30it/s]
                                                 
+
 52%|█████▏    | 114/220 [00:08<00:02, 50.30it/s]
                                                 
+
 52%|█████▏    | 114/220 [00:08<00:02, 50.30it/s]
                                                 
+
 52%|█████▏    | 114/220 [00:08<00:02, 50.30it/s]
                                                 
+
 52%|█████▏    | 114/220 [00:08<00:02, 50.30it/s]
                                                 
+
 52%|█████▏    | 114/220 [00:08<00:02, 50.30it/s]
                                                 
+
 52%|█████▏    | 114/220 [00:08<00:02, 50.30it/s]
                                                 
+
 52%|█████▏    | 114/220 [00:08<00:02, 50.30it/s]
                                                 
+
 52%|█████▏    | 114/220 [00:08<00:02, 50.30it/s]
 56%|█████▌    | 123/220 [00:08<00:01, 50.90it/s]
                                                 
+
 56%|█████▌    | 123/220 [00:08<00:01, 50.90it/s]
                                                 
+
 56%|█████▌    | 123/220 [00:08<00:01, 50.90it/s]
                                                 
+
 56%|█████▌    | 123/220 [00:08<00:01, 50.90it/s]
                                                 
+
 56%|█████▌    | 123/220 [00:08<00:01, 50.90it/s]
                                                 
+
 56%|█████▌    | 123/220 [00:08<00:01, 50.90it/s]
                                                 
+
 56%|█████▌    | 123/220 [00:08<00:01, 50.90it/s]
                                                 
+
 56%|█████▌    | 123/220 [00:08<00:01, 50.90it/s]
                                                 
+
 56%|█████▌    | 123/220 [00:08<00:01, 50.90it/s]
                                                 
+
 56%|█████▌    | 123/220 [00:08<00:01, 50.90it/s]
                                                 
+
 56%|█████▌    | 123/220 [00:08<00:01, 50.90it/s]
                                                 
+
 56%|█████▌    | 123/220 [00:08<00:01, 50.90it/s]
                                                 
+
 56%|█████▌    | 123/220 [00:08<00:01, 50.90it/s]
                                                 
+
 56%|█████▌    | 123/220 [00:08<00:01, 50.90it/s]
 60%|██████    | 132/220 [00:08<00:01, 51.32it/s]
                                                 
+
 60%|██████    | 132/220 [00:08<00:01, 51.32it/s]
                                                 
+
 60%|██████    | 132/220 [00:08<00:01, 51.32it/s]
                                                 
+
 60%|██████    | 132/220 [00:08<00:01, 51.32it/s]
                                                 
+
 60%|██████    | 132/220 [00:08<00:01, 51.32it/s]
                                                 
+
 60%|██████    | 132/220 [00:08<00:01, 51.32it/s]
                                                 
+
 60%|██████    | 132/220 [00:08<00:01, 51.32it/s]
                                                 
+
 60%|██████    | 132/220 [00:08<00:01, 51.32it/s]
                                                 
+
 60%|██████    | 132/220 [00:08<00:01, 51.32it/s]
                                                 
+
 60%|██████    | 132/220 [00:08<00:01, 51.32it/s]
                                                 
+
 60%|██████    | 132/220 [00:08<00:01, 51.32it/s]
                                                 
+
 60%|██████    | 132/220 [00:08<00:01, 51.32it/s]
                                                 
+
 60%|██████    | 132/220 [00:08<00:01, 51.32it/s]
                                                 
+
 60%|██████    | 132/220 [00:08<00:01, 51.32it/s]
 64%|██████▍   | 141/220 [00:08<00:01, 51.60it/s]
                                                 
+
 64%|██████▍   | 141/220 [00:08<00:01, 51.60it/s]
                                                 
+
 64%|██████▍   | 141/220 [00:08<00:01, 51.60it/s]
                                                 
+
 64%|██████▍   | 141/220 [00:08<00:01, 51.60it/s]
                                                 
+
 64%|██████▍   | 141/220 [00:08<00:01, 51.60it/s]
                                                 
+
 64%|██████▍   | 141/220 [00:08<00:01, 51.60it/s]
                                                 
+
 64%|██████▍   | 141/220 [00:08<00:01, 51.60it/s]
                                                 
+
 64%|██████▍   | 141/220 [00:08<00:01, 51.60it/s]
                                                 
+
 64%|██████▍   | 141/220 [00:08<00:01, 51.60it/s]
                                                 
+
 64%|██████▍   | 141/220 [00:08<00:01, 51.60it/s]
                                                 
+
 64%|██████▍   | 141/220 [00:08<00:01, 51.60it/s]
                                                 
+
 64%|██████▍   | 141/220 [00:08<00:01, 51.60it/s]
                                                 
+
 64%|██████▍   | 141/220 [00:08<00:01, 51.60it/s]
                                                 
+
 64%|██████▍   | 141/220 [00:08<00:01, 51.60it/s]
 68%|██████▊   | 150/220 [00:08<00:01, 51.82it/s]
                                                 
+
 68%|██████▊   | 150/220 [00:08<00:01, 51.82it/s]
                                                 
+
 68%|██████▊   | 150/220 [00:08<00:01, 51.82it/s]
                                                 
+
 68%|██████▊   | 150/220 [00:08<00:01, 51.82it/s]
                                                 
+
 68%|██████▊   | 150/220 [00:08<00:01, 51.82it/s]
                                                 
+
 68%|██████▊   | 150/220 [00:08<00:01, 51.82it/s]
                                                 
+
 68%|██████▊   | 150/220 [00:08<00:01, 51.82it/s]
                                                 
+
 68%|██████▊   | 150/220 [00:08<00:01, 51.82it/s]
                                                 
+
 68%|██████▊   | 150/220 [00:08<00:01, 51.82it/s]
                                                 
+
 68%|██████▊   | 150/220 [00:08<00:01, 51.82it/s]
                                                 
+
 68%|██████▊   | 150/220 [00:08<00:01, 51.82it/s]
                                                 
+
 68%|██████▊   | 150/220 [00:08<00:01, 51.82it/s]
                                                 
+
 68%|██████▊   | 150/220 [00:08<00:01, 51.82it/s]
                                                 
+
 68%|██████▊   | 150/220 [00:08<00:01, 51.82it/s]
 72%|███████▏  | 159/220 [00:08<00:01, 51.97it/s]
                                                 
+
 72%|███████▏  | 159/220 [00:08<00:01, 51.97it/s]
                                                 
+
 72%|███████▏  | 159/220 [00:08<00:01, 51.97it/s]
                                                 
+
 72%|███████▏  | 159/220 [00:08<00:01, 51.97it/s]
                                                 
+
 72%|███████▏  | 159/220 [00:08<00:01, 51.97it/s]
                                                 
+
 72%|███████▏  | 159/220 [00:08<00:01, 51.97it/s]
                                                 
+
 72%|███████▏  | 159/220 [00:08<00:01, 51.97it/s]
                                                 
+
 72%|███████▏  | 159/220 [00:08<00:01, 51.97it/s]
                                                 
+
 72%|███████▏  | 159/220 [00:08<00:01, 51.97it/s]
                                                 
+
 72%|███████▏  | 159/220 [00:08<00:01, 51.97it/s]
                                                 
+
 72%|███████▏  | 159/220 [00:08<00:01, 51.97it/s]
                                                 
+
 72%|███████▏  | 159/220 [00:08<00:01, 51.97it/s]
                                                 
+
 72%|███████▏  | 159/220 [00:08<00:01, 51.97it/s]
                                                 
+
 72%|███████▏  | 159/220 [00:09<00:01, 51.97it/s]
 76%|███████▋  | 168/220 [00:09<00:00, 52.08it/s]
                                                 
+
 76%|███████▋  | 168/220 [00:09<00:00, 52.08it/s]
                                                 
+
 76%|███████▋  | 168/220 [00:09<00:00, 52.08it/s]
                                                 
+
 76%|███████▋  | 168/220 [00:09<00:00, 52.08it/s]
                                                 
+
 76%|███████▋  | 168/220 [00:09<00:00, 52.08it/s]
                                                 
+
 76%|███████▋  | 168/220 [00:09<00:00, 52.08it/s]
                                                 
+
 76%|███████▋  | 168/220 [00:09<00:00, 52.08it/s]
                                                 
+
 76%|███████▋  | 168/220 [00:09<00:00, 52.08it/s]
                                                 
+
 76%|███████▋  | 168/220 [00:09<00:00, 52.08it/s]
                                                 
+
 76%|███████▋  | 168/220 [00:09<00:00, 52.08it/s]
                                                 
+
 76%|███████▋  | 168/220 [00:09<00:00, 52.08it/s]
                                                 
+
 76%|███████▋  | 168/220 [00:09<00:00, 52.08it/s]
                                                 
+
 76%|███████▋  | 168/220 [00:09<00:00, 52.08it/s]
                                                 
+
 76%|███████▋  | 168/220 [00:09<00:00, 52.08it/s]
 80%|████████  | 177/220 [00:09<00:00, 52.14it/s]
                                                 
+
 80%|████████  | 177/220 [00:09<00:00, 52.14it/s]
                                                 
+
 80%|████████  | 177/220 [00:09<00:00, 52.14it/s]
                                                 
+
 80%|████████  | 177/220 [00:09<00:00, 52.14it/s]
                                                 
+
 80%|████████  | 177/220 [00:09<00:00, 52.14it/s]
                                                 
+
 80%|████████  | 177/220 [00:09<00:00, 52.14it/s]
                                                 
+
 80%|████████  | 177/220 [00:09<00:00, 52.14it/s]
                                                 
+
 80%|████████  | 177/220 [00:09<00:00, 52.14it/s]
                                                 
+
 80%|████████  | 177/220 [00:09<00:00, 52.14it/s]
                                                 
+
 80%|████████  | 177/220 [00:09<00:00, 52.14it/s]
                                                 
+
 80%|████████  | 177/220 [00:09<00:00, 52.14it/s]
                                                 
+
 80%|████████  | 177/220 [00:09<00:00, 52.14it/s]
                                                 
+
 80%|████████  | 177/220 [00:09<00:00, 52.14it/s]
                                                 
+
 80%|████████  | 177/220 [00:09<00:00, 52.14it/s]
 85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
                                                 
+
 85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
                                                 
+
 85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
                                                 
+
 85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
                                                 
+
 85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
                                                 
+
 85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
                                                 
+
 85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
                                                 
+
 85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
                                                 
+
 85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
                                                 
+
 85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
                                                 
+
 85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
                                                 
+
 85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
                                                 
+
 85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
                                                 
+
 85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
 89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
                                                 
+
 89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
                                                 
+
 89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
                                                 
+
 89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
                                                 
+
 89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
                                                 
+
 89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
                                                 
+
 89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
                                                 
+
 89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
                                                 
+
 89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
                                                 
+
 89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
                                                 
+
 89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
                                                 
+
 89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
                                                 
+
 89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
                                                 
+
 89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
 93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
                                                 
+
 93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
                                                 
+
 93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
                                                 
+
 93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
                                                 
+
 93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
                                                 
+
 93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
                                                 
+
 93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
                                                 
+
 93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
                                                 
+
 93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
                                                 
+
 93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
                                                 
+
 93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
                                                 
+
 93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
                                                 
+
 93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
                                                 
+
 93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
 97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
                                                 
+
 97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
                                                 
+
 97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
                                                 
+
 97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
                                                 
+
 97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
                                                 
+
 97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
                                                 
+
 97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
                                                 
+
 97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
                                                 
+
 97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
                                                 
+
 97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
+[2024-05-24 18:29:53] INFO huggingface_loader.py:196: Unloading HF weight file: dist/models/stablelm-2-zephyr-1_6b/model.safetensors
+[2024-05-24 18:29:53] INFO stats.py:76: Time usage: HF loading: 1.007 sec; Pre-quantization mapping: 3.312 sec; Quantization: 2.344 sec
+[2024-05-24 18:29:53] INFO stats.py:90: RAM usage: Peak RAM: 3.063 GB. Total bytes loaded from disk: 3.063 GB
+[2024-05-24 18:29:53] INFO convert_weight.py:155: Parameter size after quantization: 0.958 GB
+[2024-05-24 18:29:53] INFO convert_weight.py:160: Total parameters: 1,644,515,328
+[2024-05-24 18:29:53] INFO convert_weight.py:161: Bits per parameter: 5.006
+[2024-05-24 18:29:53] INFO convert_weight.py:166: Saved to directory: /tmp/tmpt74_sq0w
+
+All finished, 27 total shards committed, record saved to /tmp/tmpt74_sq0w/ndarray-cache.json
+Also saved a bf16 record to /tmp/tmpt74_sq0w/ndarray-cache-b16.json

mlc-chat-config.json

@@ -0,0 +1,76 @@
+{
+  "model_type": "stablelm",
+  "quantization": "q4f32_1",
+  "model_config": {
+    "vocab_size": 100352,
+    "hidden_size": 2048,
+    "num_hidden_layers": 24,
+    "num_attention_heads": 32,
+    "num_key_value_heads": 32,
+    "layer_norm_eps": 1e-05,
+    "partial_rotary_factor": 0.25,
+    "rope_theta": 10000,
+    "intermediate_size": 5632,
+    "use_qkv_bias": true,
+    "head_dim": 64,
+    "context_window_size": 4096,
+    "prefill_chunk_size": 2048,
+    "tensor_parallel_shards": 1,
+    "max_batch_size": 80
+  },
+  "vocab_size": 100352,
+  "context_window_size": 4096,
+  "sliding_window_size": -1,
+  "prefill_chunk_size": 2048,
+  "attention_sink_size": -1,
+  "tensor_parallel_shards": 1,
+  "mean_gen_len": 128,
+  "max_gen_len": 512,
+  "shift_fill_factor": 0.3,
+  "temperature": 0.7,
+  "presence_penalty": 0.0,
+  "frequency_penalty": 0.0,
+  "repetition_penalty": 1.0,
+  "top_p": 0.95,
+  "conv_template": {
+    "name": "stablelm-2",
+    "system_template": "{system_message}",
+    "system_message": "",
+    "add_role_after_system_message": true,
+    "roles": {
+      "user": "<|user|>",
+      "assistant": "<|assistant|>"
+    },
+    "role_templates": {
+      "user": "{user_message}",
+      "assistant": "{assistant_message}",
+      "tool": "{tool_message}"
+    },
+    "messages": [],
+    "seps": [
+      "<|endoftext|>",
+      "<|endoftext|>"
+    ],
+    "role_content_sep": "\n",
+    "role_empty_sep": "\n",
+    "stop_str": [
+      "<|endoftext|>"
+    ],
+    "stop_token_ids": [
+      100257
+    ],
+    "function_string": "",
+    "use_function_calling": false
+  },
+  "pad_token_id": 0,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "tokenizer_files": [
+    "tokenizer.json",
+    "vocab.json",
+    "merges.txt",
+    "tokenizer_config.json"
+  ],
+  "token_table_postproc_method": "byte_level",
+  "version": "0.1.0"
+}

params_shard_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1617b247c4b4b396c7e69dc8c5d109afb9c3a9684bc29d29a4d0a725eabe5dc9
+size 102760448

params_shard_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89599ce07cec4543311ced20f84f0152f5257a3c0622a152a5444dbf7ff61374
+size 102760448

params_shard_10.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a5c2bb3f5c66ae34bdf1a362391935cea77e50b081398ba654a918bdca5af72
+size 28930048

params_shard_11.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de03c5354a4fe1db5888a0b6d9b8a9aade0c884eec650590ebc96af353698bde
+size 28930048

params_shard_12.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc129d9b4e7b88d25c66c7ffa332b96618d6643a261614a81212d65d07232ad5
+size 28930048

params_shard_13.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33bd97daf0c774ff7fc74980f3b525a52b3ed43a35bf55614fa588b9984b7399
+size 28930048

params_shard_14.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1941233e143d0f9a956a582823b1b17cdc22c037debcca9f350c47010e03f9
+size 28930048

params_shard_15.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14c485f7ddfc9ee5d2ba1fb03e40a21cfddc8a1a77a3ee1a246e6741c8594aa2
+size 28930048

params_shard_16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06ec8ca0ff79b0c0ce57eb7e0476fc55f2d8a5fda41b6beaca5fae5904b6def8
+size 28930048

params_shard_17.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a17e853fd2187493a18971c9ce60f0c95d8d655a68926e957ec58c94da147e
+size 28930048

params_shard_18.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5f9814b8e481404e1dff31fc8a08c9b81dba2ed2cbd4dff249221aa591a132
+size 28930048

params_shard_19.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3384415f23aa037954542ec2b4fc16b5ae7a1bf8915c040a1f6042fc0d4e58b6
+size 28930048

params_shard_2.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b06e2a718a4b6fe62338c5a6016a5d7832620056bd689cd0c6c51149de046f2
+size 32186368

params_shard_20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf6415b1656e8818f8aca73e05af6179d3a9a5dcf2ca5374553f6b8c06119ee3
+size 28930048

params_shard_21.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e7a26d96f831539edade13e85ad9a7c2ae3d5150144a6c38f2eeb0c1d682194
+size 28930048

params_shard_22.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:036d9b1e0085d9c6ebacba73b9254a39ff9e9ae795f3ad0c1172eaead6422cd7
+size 28930048

params_shard_23.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e876e4293cdd72fc45c8da5d1820f63d2b525f481d29def980af6c61c95283
+size 28930048

params_shard_24.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd136f6f378f25b9a56596bd59aff887eee503623cda321a5dfa708042b3222e
+size 28930048

params_shard_25.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99df061abbb88891cc21d018b65271375f79896223e76425695b489646637f1b
+size 28930048

params_shard_26.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87caf5efd3c6b2950585e685bfc518a301d3e7de9f69acd350c4c29a0b424f60
+size 22441984

params_shard_3.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:405a307a4e182d02f68deed381d031c097a10b3ffc7965b27b14cebb9d1d4b19
+size 28930048

params_shard_4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8af7a48550f50dfed538740a46fb4c26387d731dbc25df68db50278f96866af
+size 28930048

params_shard_5.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:665d35ae80255aa8ae2c470433fd2eabee34ae6a0f90ca2a6428d1d90fd21bac
+size 28930048

params_shard_6.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2b8a4edd138f9282571f246d9682276d6d4dfec33a16ce05412daa5a4fa363
+size 28930048

params_shard_7.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79575fc64fb9348c28656cf44c1d3667d268845ce9387e49ed1a565b5e2bab08
+size 28930048

params_shard_8.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:842b3e60566b3ae3e172a41697070e62b389eaca33094fccbbd281122188b29d
+size 28930048

params_shard_9.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01cd539157b69bb389d407ae98dbca8dcf64cd7b73e8505d1fa0aa8c0161dfd
+size 28930048

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "<|reg_extra|>",
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|fim_pad|>",
+    "<gh_stars>",
+    "<filename>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>",
+    "<|endofprompt|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|pause|>",
+    "<|reg0|>",
+    "<|reg1|>",
+    "<|reg2|>",
+    "<|reg3|>",
+    "<|reg4|>",
+    "<|reg5|>",
+    "<|reg6|>",
+    "<|reg7|>",
+    "<|extra0|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2TokenizerFast",
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}