aubmindlab commited on
Commit
3b5808c
1 Parent(s): b949401

fixed all tokenizer files

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "aubmindlab/bert-base-arabertv01", "do_basic_tokenize": true, "never_split": ["[بريد]","[مستخدم]","[رابط]"]}
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "aubmindlab/bert-base-arabertv01", "do_basic_tokenize": true, "never_split": ["[بريد]","[مستخدم]","[رابط]"]}
vocab.txt CHANGED
@@ -60121,9 +60121,9 @@ Arabic
60121
  ##International
60122
  والبتروكيماويات
60123
  [UNK]
60124
- [UNUSED_1]
60125
- [UNUSED_2]
60126
- [UNUSED_3]
60127
  [UNUSED_4]
60128
  [UNUSED_5]
60129
  [UNUSED_6]
60121
  ##International
60122
  والبتروكيماويات
60123
  [UNK]
60124
+ [بريد]
60125
+ [مستخدم]
60126
+ [رابط]
60127
  [UNUSED_4]
60128
  [UNUSED_5]
60129
  [UNUSED_6]