keemeng commited on
Commit
b8d4d55
1 Parent(s): f7ef553

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +1 -1
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -11,7 +11,7 @@
11
  }
12
  },
13
  "bos_token": "<|endoftext|>",
14
- "clean_up_tokenization_spaces": false,
15
  "eos_token": "<|endoftext|>",
16
  "model_max_length": 1024,
17
  "pad_token": "<|endoftext|>",
 
11
  }
12
  },
13
  "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
  "eos_token": "<|endoftext|>",
16
  "model_max_length": 1024,
17
  "pad_token": "<|endoftext|>",