Tobi-Bueck commited on
Commit
33c8c8d
·
verified ·
1 Parent(s): e817c87

Upload tokenizer

Browse files
Files changed (3) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +5 -2
  3. vocab.txt +0 -0
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -43,13 +43,16 @@
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
- "do_lower_case": false,
 
47
  "mask_token": "[MASK]",
 
48
  "model_max_length": 512,
 
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
- "tokenizer_class": "DistilBertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
 
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
  "mask_token": "[MASK]",
49
+ "max_len": 512,
50
  "model_max_length": 512,
51
+ "never_split": null,
52
  "pad_token": "[PAD]",
53
  "sep_token": "[SEP]",
54
  "strip_accents": null,
55
  "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
  "unk_token": "[UNK]"
58
  }
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff