| { | |
| "cls_token": "[CLS]", | |
| "do_basic_tokenize": true, | |
| "do_lower_case": false, | |
| "full_tokenizer_file": null, | |
| "mask_token": "[MASK]", | |
| "max_len": 512, | |
| "model_max_length": 512, | |
| "never_split": [ | |
| "+ูุง", | |
| "ุณ+", | |
| "[ู ุณุชุฎุฏู ]", | |
| "+ู", | |
| "+ูู ", | |
| "+ุฉ", | |
| "+ู", | |
| "ูู+", | |
| "[ุจุฑูุฏ]", | |
| "[ุฑุงุจุท]", | |
| "+ู", | |
| "+ูู", | |
| "+ุง", | |
| "+ุงุช", | |
| "+ู", | |
| "ุจ+", | |
| "+ูุง", | |
| "+ูู", | |
| "+ูู ", | |
| "ู+", | |
| "+ูู", | |
| "+ูู ุง", | |
| "ู+", | |
| "+ูู ุง", | |
| "+ุงู", | |
| "+ุช", | |
| "+ูู", | |
| "ู+", | |
| "+ูุง", | |
| "ุงู+", | |
| "ู+" | |
| ], | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "special_tokens_map_file": null, | |
| "strip_accents": null, | |
| "tokenize_chinese_chars": true, | |
| "tokenizer_class": "BertTokenizer", | |
| "unk_token": "[UNK]", | |
| "use_fast": true | |
| } | |