| { |
| "added_tokens_decoder": { |
| "0": { |
| "content": "[PAD]", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "100": { |
| "content": "[UNK]", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "101": { |
| "content": "[CLS]", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "102": { |
| "content": "[SEP]", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "103": { |
| "content": "[MASK]", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "119547": { |
| "content": "ҥ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "119548": { |
| "content": "ӧ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "119549": { |
| "content": "ӱ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "119550": { |
| "content": "ӹ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "119551": { |
| "content": "ӓ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "119552": { |
| "content": "ӆ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "119553": { |
| "content": "ӊ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "119554": { |
| "content": "Ҥ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "119555": { |
| "content": "Ӧ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "119556": { |
| "content": "Ӱ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "119557": { |
| "content": "Ӓ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "119558": { |
| "content": "Ӝ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "119559": { |
| "content": "Ӹ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| } |
| }, |
| "clean_up_tokenization_spaces": true, |
| "cls_token": "[CLS]", |
| "do_lower_case": false, |
| "mask_token": "[MASK]", |
| "model_max_length": 512, |
| "pad_token": "[PAD]", |
| "sep_token": "[SEP]", |
| "strip_accents": null, |
| "tokenize_chinese_chars": true, |
| "tokenizer_class": "BertTokenizer", |
| "unk_token": "[UNK]" |
| } |
|
|
