artarif commited on
Commit
c799555
·
verified ·
1 Parent(s): 4d2ab38

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +2 -2
tokenizer_config.json CHANGED
@@ -151,11 +151,11 @@
151
  "<|im_end|>"
152
  ],
153
  "bos_token": "<|im_start|>",
154
- "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
155
  "clean_up_tokenization_spaces": false,
156
  "eos_token": "<|im_end|>",
157
  "extra_special_tokens": {},
158
- "model_max_length": 8192,
159
  "pad_token": "[PAD]",
160
  "padding_side": "left",
161
  "tokenizer_class": "GPT2Tokenizer",
 
151
  "<|im_end|>"
152
  ],
153
  "bos_token": "<|im_start|>",
154
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
155
  "clean_up_tokenization_spaces": false,
156
  "eos_token": "<|im_end|>",
157
  "extra_special_tokens": {},
158
+ "model_max_length": 2048,
159
  "pad_token": "[PAD]",
160
  "padding_side": "left",
161
  "tokenizer_class": "GPT2Tokenizer",