NorahAlshahrani commited on
Commit
88a62cc
โ€ข
1 Parent(s): aaa45ef

Create tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +1 -0
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "max_len": 512, "do_basic_tokenize": true, "never_split": ["+ูƒ", "+ูƒู…ุง", "ูƒ+", "+ูˆุง", "+ูŠู†", "ูˆ+", "+ูƒู†", "+ุงู†", "+ู‡ู…", "+ุฉ", "[ุจุฑูŠุฏ]", "ู„ู„+", "+ูŠ", "+ุช", "+ู†", "ุณ+", "ู„+", "[ู…ุณุชุฎุฏู…]", "+ูƒู…", "+ุง", "ุจ+", "ู+", "+ู†ุง", "+ู‡ุง", "+ูˆู†", "+ู‡ู…ุง", "ุงู„+", "+ู‡", "+ู‡ู†", "+ุงุช", "[ุฑุงุจุท]"], "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-large-arabertv2"}