{ | |
"additional_special_tokens": [ | |
"ar_AR", | |
"cs_CZ", | |
"de_DE", | |
"en_XX", | |
"es_XX", | |
"et_EE", | |
"fi_FI", | |
"fr_XX", | |
"gu_IN", | |
"hi_IN", | |
"it_IT", | |
"ja_XX", | |
"kk_KZ", | |
"ko_KR", | |
"lt_LT", | |
"lv_LV", | |
"my_MM", | |
"ne_NP", | |
"nl_XX", | |
"ro_RO", | |
"ru_RU", | |
"si_LK", | |
"tr_TR", | |
"vi_VN", | |
"zh_CN" | |
], | |
"bos_token": { | |
"content": "<s>", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"cls_token": { | |
"content": "<s>", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"eos_token": { | |
"content": "</s>", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"mask_token": { | |
"content": "<mask>", | |
"lstrip": true, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"pad_token": { | |
"content": "<pad>", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"sep_token": { | |
"content": "</s>", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"unk_token": { | |
"content": "<unk>", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false | |
} | |
} | |