lionelsh commited on
Commit
ebce12a
1 Parent(s): 0e46725

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +1 -1
tokenizer_config.json CHANGED
@@ -9,6 +9,7 @@
9
  "rstrip": false,
10
  "single_word": false
11
  },
 
12
  "eos_token": {
13
  "__type": "AddedToken",
14
  "content": "</s>",
@@ -27,7 +28,6 @@
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
- "special_tokens_map_file": null,
31
  "tokenizer_class": "GPT2Tokenizer",
32
  "unk_token": {
33
  "__type": "AddedToken",
 
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
+ "clean_up_tokenization_spaces": true,
13
  "eos_token": {
14
  "__type": "AddedToken",
15
  "content": "</s>",
 
28
  "rstrip": false,
29
  "single_word": false
30
  },
 
31
  "tokenizer_class": "GPT2Tokenizer",
32
  "unk_token": {
33
  "__type": "AddedToken",