lucyknada djuna commited on
Commit
0f3dc7a
1 Parent(s): 887148e

Set eos token in tokenizer_config into <|im_end|> (#3)

Browse files

- Set eos token in tokenizer_config into <|im_end|> (d15530c05807ba1afdc0a006a6a44e78933365e6)


Co-authored-by: Djuunaa <djuna@users.noreply.huggingface.co>

Files changed (1) hide show
  1. tokenizer_config.json +1 -1
tokenizer_config.json CHANGED
@@ -30,7 +30,7 @@
30
  "bos_token": null,
31
  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
32
  "clean_up_tokenization_spaces": false,
33
- "eos_token": "<|endoftext|>",
34
  "errors": "replace",
35
  "model_max_length": 32768,
36
  "pad_token": "<|endoftext|>",
 
30
  "bos_token": null,
31
  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
32
  "clean_up_tokenization_spaces": false,
33
+ "eos_token": "<|im_end|>",
34
  "errors": "replace",
35
  "model_max_length": 32768,
36
  "pad_token": "<|endoftext|>",