Hugging Face's logo

dot-ammar
/
AR-dotted-tokenizer

Model card Files Community
dot-ammar commited on
Commit
6b37742
·
1 Parent(s): d39aeb2

Upload tokenizer

Browse files
Files changed (3) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +3 -3
  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 +43,13 @@
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
- "do_lower_case": true,
47
  "mask_token": "[MASK]",
48
- "model_max_length": 1000000000000000019884624838656,
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
- "tokenizer_class": "MobileBertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
 
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
  }
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff