| { |
| "added_tokens_decoder": { |
| "0": { |
| "content": "<s>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "1": { |
| "content": "<pad>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "3": { |
| "content": "<unk>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "4": { |
| "content": "</s>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "6": { |
| "content": "௦", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "7": { |
| "content": "௧", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "8": { |
| "content": "௨", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "9": { |
| "content": "௩", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "10": { |
| "content": "௪", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "11": { |
| "content": "௫", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "12": { |
| "content": "௬", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "13": { |
| "content": "௭", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "14": { |
| "content": "௮", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "15": { |
| "content": "௯", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "16": { |
| "content": "௰", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "17": { |
| "content": "௱", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "18": { |
| "content": "௲", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "19": { |
| "content": "।", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "20": { |
| "content": "॥", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "32001": { |
| "content": "<mask>", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| } |
| }, |
| "bos_token": "<s>", |
| "clean_up_tokenization_spaces": false, |
| "cls_token": "<s>", |
| "do_lower_case": false, |
| "eos_token": "</s>", |
| "extra_special_tokens": {}, |
| "mask_token": "<mask>", |
| "model_max_length": 512, |
| "pad_token": "<pad>", |
| "sep_token": "</s>", |
| "sp_model_kwargs": {}, |
| "tokenizer_class": "XLMRobertaTokenizer", |
| "unk_token": "<unk>", |
| "vocab_size": 32002 |
| } |
|
|
