dannoncaffeine commited on
Commit
a335329
·
1 Parent(s): 9238f6a

fix: update tokenizer_config

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +2 -2
tokenizer_config.json CHANGED
@@ -2,8 +2,8 @@
2
  "add_prefix_space": true,
3
  "bos_token": "<|endoftext|>",
4
  "eos_token": "<|endoftext|>",
5
- "unk_token": "<|endoftext|>",
6
- "pad_token": "<|endoftext|>",
7
  "model_max_length": 1024,
8
  "tokenizer_class": "GPT2Tokenizer",
9
  "clean_up_tokenization_spaces": true,
 
2
  "add_prefix_space": true,
3
  "bos_token": "<|endoftext|>",
4
  "eos_token": "<|endoftext|>",
5
+ "unk_token": "<|unknown|>",
6
+ "pad_token": "<|pad|>",
7
  "model_max_length": 1024,
8
  "tokenizer_class": "GPT2Tokenizer",
9
  "clean_up_tokenization_spaces": true,