aubmindlab commited on
Commit
c2c49ea
1 Parent(s): 6b78a01

Added fast tokenizer files

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +1 -1
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"do_lower_case": false, "do_basic_tokenize": true, "never_split": ["+وا", "س+", "[مستخدم]", "+ك", "+هم", "+ة", "+ن", "لل+", "[بريد]", "[رابط]", "+ه", "+كن", "+ا", "+ات", "+ي", "ب+", "+نا", "+هن", "+كم", "ك+", "+ين", "+هما", "و+", "+كما", "+ان", "+ت", "+ون", "ل+", "+ها", "ال+", "ف+"], "special_tokens_map_file": null, "full_tokenizer_file": null}
 
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, "do_basic_tokenize": true, "never_split": ["+وا", "س+", "[مستخدم]", "+ك", "+هم", "+ة", "+ن", "لل+", "[بريد]", "[رابط]", "+ه", "+كن", "+ا", "+ات", "+ي", "ب+", "+نا", "+هن", "+كم", "ك+", "+ين", "+هما", "و+", "+كما", "+ان", "+ت", "+ون", "ل+", "+ها", "ال+", "ف+"], "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "aubmindlab/bert-base-arabert"}