Lanni-ni commited on
Commit
7f3aee6
·
verified ·
1 Parent(s): 1ffacc6

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +2 -2
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -205,9 +205,9 @@
205
  }
206
  },
207
  "bos_token": "<|endoftext|>",
208
- "clean_up_tokenization_spaces": true,
209
  "eos_token": "<|endoftext|>",
210
- "model_max_length": 2048,
211
  "pad_token": null,
212
  "tokenizer_class": "GPTNeoXTokenizer",
213
  "unk_token": "<|endoftext|>"
 
205
  }
206
  },
207
  "bos_token": "<|endoftext|>",
208
+ "clean_up_tokenization_spaces": false,
209
  "eos_token": "<|endoftext|>",
210
+ "model_max_length": 1024,
211
  "pad_token": null,
212
  "tokenizer_class": "GPTNeoXTokenizer",
213
  "unk_token": "<|endoftext|>"