| { |
| "add_prefix_space": false, |
| "added_tokens_decoder": { |
| "0": { |
| "content": "<s>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "1": { |
| "content": "<pad>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "2": { |
| "content": "</s>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "3": { |
| "content": "<unk>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50264": { |
| "content": "<mask>", |
| "lstrip": true, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50265": { |
| "content": "រ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50266": { |
| "content": "៛", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50267": { |
| "content": "ី", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50268": { |
| "content": "ឃ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50269": { |
| "content": "ទ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50270": { |
| "content": "្", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50271": { |
| "content": "ឦ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50272": { |
| "content": "ៗ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50273": { |
| "content": "៌", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50274": { |
| "content": "័", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50275": { |
| "content": "ឆ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50276": { |
| "content": "ឪ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50277": { |
| "content": "ិ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50278": { |
| "content": "ឱ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50279": { |
| "content": "ផ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50280": { |
| "content": "ក", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50281": { |
| "content": "ៃ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50282": { |
| "content": "វ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50283": { |
| "content": "ួ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50284": { |
| "content": "ឥ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50285": { |
| "content": "២", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50286": { |
| "content": "ស", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50287": { |
| "content": "ថ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50288": { |
| "content": "ដ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50289": { |
| "content": "០", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50290": { |
| "content": "់", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50291": { |
| "content": "ើ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50292": { |
| "content": "ច", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50293": { |
| "content": "ឮ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50294": { |
| "content": "ុ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50295": { |
| "content": "ា", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50296": { |
| "content": "៉", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50297": { |
| "content": "៍", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50298": { |
| "content": "ឹ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50299": { |
| "content": "ព", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50300": { |
| "content": "៨", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50301": { |
| "content": "ឋ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50302": { |
| "content": "៖", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50303": { |
| "content": "ឭ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50304": { |
| "content": "អ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50305": { |
| "content": "ញ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50306": { |
| "content": "ៈ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50307": { |
| "content": "៊", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50308": { |
| "content": "៩", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50309": { |
| "content": "យ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50310": { |
| "content": "េ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50311": { |
| "content": "ឬ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50312": { |
| "content": "ឧ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50313": { |
| "content": "ះ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50314": { |
| "content": "ឍ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50315": { |
| "content": "ន", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50316": { |
| "content": "ឯ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50317": { |
| "content": "ឺ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50318": { |
| "content": "១", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50319": { |
| "content": "ឈ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50320": { |
| "content": "ជ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50321": { |
| "content": "ត", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50322": { |
| "content": "៧", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50323": { |
| "content": "៦", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50324": { |
| "content": "ៀ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50325": { |
| "content": "ឫ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50326": { |
| "content": "ឲ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50327": { |
| "content": "៤", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50328": { |
| "content": "ោ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50329": { |
| "content": "ខ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50330": { |
| "content": "៥", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50331": { |
| "content": "៏", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50332": { |
| "content": "ង", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50333": { |
| "content": "ឌ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50334": { |
| "content": "ធ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50335": { |
| "content": "ឿ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50336": { |
| "content": "ល", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50337": { |
| "content": "ូ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50338": { |
| "content": "ប", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50339": { |
| "content": "ម", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50340": { |
| "content": "ឳ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50341": { |
| "content": "ណ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50342": { |
| "content": "ឡ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50343": { |
| "content": "ំ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50344": { |
| "content": "ភ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50345": { |
| "content": "៣", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50346": { |
| "content": "ៅ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50347": { |
| "content": "។", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50348": { |
| "content": "ហ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50349": { |
| "content": "ែ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50350": { |
| "content": "គ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| } |
| }, |
| "bos_token": "<s>", |
| "clean_up_tokenization_spaces": true, |
| "cls_token": "<s>", |
| "eos_token": "</s>", |
| "errors": "replace", |
| "mask_token": "<mask>", |
| "model_max_length": 512, |
| "pad_token": "<pad>", |
| "sep_token": "</s>", |
| "tokenizer_class": "RobertaTokenizer", |
| "trim_offsets": true, |
| "unk_token": "<unk>" |
| } |
|
|
