{ | |
"additional_special_tokens": [ | |
"<triplet>", | |
"<relation>", | |
"el_EL", | |
"ca_XX", | |
"tp_XX", | |
"<loc>", | |
"<misc>", | |
"<per>", | |
"<num>", | |
"<time>", | |
"<org>", | |
"<date>", | |
"<eve>", | |
"<cel>", | |
"<media>", | |
"<dis>", | |
"<unk>", | |
"<concept>", | |
"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", | |
"af_ZA", | |
"az_AZ", | |
"bn_IN", | |
"fa_IR", | |
"he_IL", | |
"hr_HR", | |
"id_ID", | |
"ka_GE", | |
"km_KH", | |
"mk_MK", | |
"ml_IN", | |
"mn_MN", | |
"mr_IN", | |
"pl_PL", | |
"ps_AF", | |
"pt_XX", | |
"sv_SE", | |
"sw_KE", | |
"ta_IN", | |
"te_IN", | |
"th_TH", | |
"tl_XX", | |
"uk_UA", | |
"ur_PK", | |
"xh_ZA", | |
"gl_ES", | |
"sl_SI" | |
], | |
"bos_token": { | |
"content": "<s>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"cls_token": { | |
"content": "<s>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"eos_token": { | |
"content": "</s>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"mask_token": { | |
"content": "<mask>", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"pad_token": { | |
"content": "<pad>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"sep_token": { | |
"content": "</s>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"unk_token": { | |
"content": "<unk>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false | |
} | |
} | |