mzbac commited on
Commit
8679699
1 Parent(s): 0c52d95

fix the bos and eos token

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +2 -2
tokenizer_config.json CHANGED
@@ -56,10 +56,10 @@
56
  "<|im_end|>",
57
  "<|im_sep|>"
58
  ],
59
- "bos_token": "<|startoftext|>",
60
  "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 %}",
61
  "clean_up_tokenization_spaces": false,
62
- "eos_token": "<|endoftext|>",
63
  "legacy": true,
64
  "model_max_length": 4096,
65
  "pad_token": "<unk>",
 
56
  "<|im_end|>",
57
  "<|im_sep|>"
58
  ],
59
+ "bos_token": "<|im_start|>",
60
  "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 %}",
61
  "clean_up_tokenization_spaces": false,
62
+ "eos_token": "<|im_end|>",
63
  "legacy": true,
64
  "model_max_length": 4096,
65
  "pad_token": "<unk>",