| { | |
| "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 | |
| }, | |
| "2": { | |
| "content": "</s>", | |
| "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 | |
| }, | |
| "269195": { | |
| "content": "ace_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269196": { | |
| "content": "ace_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269197": { | |
| "content": "acm_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269198": { | |
| "content": "acq_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269199": { | |
| "content": "aeb_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269200": { | |
| "content": "afr_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269201": { | |
| "content": "ajp_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269202": { | |
| "content": "aka_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269203": { | |
| "content": "amh_Ethi", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269204": { | |
| "content": "apc_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269205": { | |
| "content": "arb_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269206": { | |
| "content": "ars_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269207": { | |
| "content": "ary_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269208": { | |
| "content": "arz_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269209": { | |
| "content": "asm_Beng", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269210": { | |
| "content": "ast_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269211": { | |
| "content": "awa_Deva", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269212": { | |
| "content": "ayr_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269213": { | |
| "content": "azb_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269214": { | |
| "content": "azj_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269215": { | |
| "content": "bak_Cyrl", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269216": { | |
| "content": "bam_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269217": { | |
| "content": "ban_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269218": { | |
| "content": "bel_Cyrl", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269219": { | |
| "content": "bem_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269220": { | |
| "content": "ben_Beng", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269221": { | |
| "content": "bho_Deva", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269222": { | |
| "content": "bjn_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269223": { | |
| "content": "bjn_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269224": { | |
| "content": "bod_Tibt", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269225": { | |
| "content": "bos_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269226": { | |
| "content": "bug_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269227": { | |
| "content": "bul_Cyrl", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269228": { | |
| "content": "cat_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269229": { | |
| "content": "ceb_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269230": { | |
| "content": "ces_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269231": { | |
| "content": "cjk_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269232": { | |
| "content": "ckb_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269233": { | |
| "content": "crh_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269234": { | |
| "content": "cym_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269235": { | |
| "content": "dan_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269236": { | |
| "content": "deu_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269237": { | |
| "content": "dik_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269238": { | |
| "content": "dyu_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269239": { | |
| "content": "dzo_Tibt", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269240": { | |
| "content": "ell_Grek", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269241": { | |
| "content": "eng_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269242": { | |
| "content": "epo_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269243": { | |
| "content": "est_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269244": { | |
| "content": "eus_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269245": { | |
| "content": "ewe_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269246": { | |
| "content": "fao_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269247": { | |
| "content": "pes_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269248": { | |
| "content": "fij_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269249": { | |
| "content": "fin_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269250": { | |
| "content": "fon_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269251": { | |
| "content": "fra_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269252": { | |
| "content": "fur_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269253": { | |
| "content": "fuv_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269254": { | |
| "content": "gla_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269255": { | |
| "content": "gle_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269256": { | |
| "content": "glg_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269257": { | |
| "content": "grn_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269258": { | |
| "content": "guj_Gujr", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269259": { | |
| "content": "hat_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269260": { | |
| "content": "hau_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269261": { | |
| "content": "heb_Hebr", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269262": { | |
| "content": "hin_Deva", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269263": { | |
| "content": "hne_Deva", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269264": { | |
| "content": "hrv_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269265": { | |
| "content": "hun_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269266": { | |
| "content": "hye_Armn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269267": { | |
| "content": "ibo_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269268": { | |
| "content": "ilo_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269269": { | |
| "content": "ind_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269270": { | |
| "content": "isl_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269271": { | |
| "content": "ita_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269272": { | |
| "content": "jav_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269273": { | |
| "content": "jpn_Jpan", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269274": { | |
| "content": "kab_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269275": { | |
| "content": "kac_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269276": { | |
| "content": "kam_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269277": { | |
| "content": "kan_Knda", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269278": { | |
| "content": "kas_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269279": { | |
| "content": "kas_Deva", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269280": { | |
| "content": "kat_Geor", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269281": { | |
| "content": "knc_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269282": { | |
| "content": "knc_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269283": { | |
| "content": "kaz_Cyrl", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269284": { | |
| "content": "kbp_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269285": { | |
| "content": "kea_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269286": { | |
| "content": "khm_Khmr", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269287": { | |
| "content": "kik_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269288": { | |
| "content": "kin_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269289": { | |
| "content": "kir_Cyrl", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269290": { | |
| "content": "kmb_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269291": { | |
| "content": "kon_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269292": { | |
| "content": "kor_Hang", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269293": { | |
| "content": "kmr_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269294": { | |
| "content": "lao_Laoo", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269295": { | |
| "content": "lvs_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269296": { | |
| "content": "lij_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269297": { | |
| "content": "lim_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269298": { | |
| "content": "lin_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269299": { | |
| "content": "lit_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269300": { | |
| "content": "lmo_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269301": { | |
| "content": "ltg_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269302": { | |
| "content": "ltz_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269303": { | |
| "content": "lua_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269304": { | |
| "content": "lug_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269305": { | |
| "content": "luo_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269306": { | |
| "content": "lus_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269307": { | |
| "content": "mag_Deva", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269308": { | |
| "content": "mai_Deva", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269309": { | |
| "content": "mal_Mlym", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269310": { | |
| "content": "mar_Deva", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269311": { | |
| "content": "min_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269312": { | |
| "content": "mkd_Cyrl", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269313": { | |
| "content": "plt_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269314": { | |
| "content": "mlt_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269315": { | |
| "content": "mni_Beng", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269316": { | |
| "content": "khk_Cyrl", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269317": { | |
| "content": "mos_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269318": { | |
| "content": "mri_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269319": { | |
| "content": "zsm_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269320": { | |
| "content": "mya_Mymr", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269321": { | |
| "content": "nld_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269322": { | |
| "content": "nno_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269323": { | |
| "content": "nob_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269324": { | |
| "content": "npi_Deva", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269325": { | |
| "content": "nso_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269326": { | |
| "content": "nus_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269327": { | |
| "content": "nya_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269328": { | |
| "content": "oci_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269329": { | |
| "content": "gaz_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269330": { | |
| "content": "ory_Orya", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269331": { | |
| "content": "pag_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269332": { | |
| "content": "pan_Guru", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269333": { | |
| "content": "pap_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269334": { | |
| "content": "pol_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269335": { | |
| "content": "por_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269336": { | |
| "content": "prs_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269337": { | |
| "content": "pbt_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269338": { | |
| "content": "quy_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269339": { | |
| "content": "ron_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269340": { | |
| "content": "run_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269341": { | |
| "content": "rus_Cyrl", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269342": { | |
| "content": "sag_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269343": { | |
| "content": "san_Deva", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269344": { | |
| "content": "sat_Beng", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269345": { | |
| "content": "scn_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269346": { | |
| "content": "shn_Mymr", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269347": { | |
| "content": "sin_Sinh", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269348": { | |
| "content": "slk_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269349": { | |
| "content": "slv_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269350": { | |
| "content": "smo_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269351": { | |
| "content": "sna_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269352": { | |
| "content": "snd_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269353": { | |
| "content": "som_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269354": { | |
| "content": "sot_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269355": { | |
| "content": "spa_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269356": { | |
| "content": "als_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269357": { | |
| "content": "srd_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269358": { | |
| "content": "srp_Cyrl", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269359": { | |
| "content": "ssw_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269360": { | |
| "content": "sun_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269361": { | |
| "content": "swe_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269362": { | |
| "content": "swh_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269363": { | |
| "content": "szl_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269364": { | |
| "content": "tam_Taml", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269365": { | |
| "content": "tat_Cyrl", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269366": { | |
| "content": "tel_Telu", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269367": { | |
| "content": "tgk_Cyrl", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269368": { | |
| "content": "tgl_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269369": { | |
| "content": "tha_Thai", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269370": { | |
| "content": "tir_Ethi", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269371": { | |
| "content": "taq_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269372": { | |
| "content": "taq_Tfng", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269373": { | |
| "content": "tpi_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269374": { | |
| "content": "tsn_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269375": { | |
| "content": "tso_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269376": { | |
| "content": "tuk_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269377": { | |
| "content": "tum_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269378": { | |
| "content": "tur_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269379": { | |
| "content": "twi_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269380": { | |
| "content": "tzm_Tfng", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269381": { | |
| "content": "uig_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269382": { | |
| "content": "ukr_Cyrl", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269383": { | |
| "content": "umb_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269384": { | |
| "content": "urd_Arab", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269385": { | |
| "content": "uzn_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269386": { | |
| "content": "vec_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269387": { | |
| "content": "vie_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269388": { | |
| "content": "war_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269389": { | |
| "content": "wol_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269390": { | |
| "content": "xho_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269391": { | |
| "content": "ydd_Hebr", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269392": { | |
| "content": "yor_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269393": { | |
| "content": "yue_Hant", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269394": { | |
| "content": "zho_Hans", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269395": { | |
| "content": "zho_Hant", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269396": { | |
| "content": "zul_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269397": { | |
| "content": "<mask>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "269398": { | |
| "content": "kaa_Latn", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "additional_special_tokens": [ | |
| "ace_Arab", | |
| "ace_Latn", | |
| "acm_Arab", | |
| "acq_Arab", | |
| "aeb_Arab", | |
| "afr_Latn", | |
| "ajp_Arab", | |
| "aka_Latn", | |
| "amh_Ethi", | |
| "apc_Arab", | |
| "arb_Arab", | |
| "ars_Arab", | |
| "ary_Arab", | |
| "arz_Arab", | |
| "asm_Beng", | |
| "ast_Latn", | |
| "awa_Deva", | |
| "ayr_Latn", | |
| "azb_Arab", | |
| "azj_Latn", | |
| "bak_Cyrl", | |
| "bam_Latn", | |
| "ban_Latn", | |
| "bel_Cyrl", | |
| "bem_Latn", | |
| "ben_Beng", | |
| "bho_Deva", | |
| "bjn_Arab", | |
| "bjn_Latn", | |
| "bod_Tibt", | |
| "bos_Latn", | |
| "bug_Latn", | |
| "bul_Cyrl", | |
| "cat_Latn", | |
| "ceb_Latn", | |
| "ces_Latn", | |
| "cjk_Latn", | |
| "ckb_Arab", | |
| "crh_Latn", | |
| "cym_Latn", | |
| "dan_Latn", | |
| "deu_Latn", | |
| "dik_Latn", | |
| "dyu_Latn", | |
| "dzo_Tibt", | |
| "ell_Grek", | |
| "eng_Latn", | |
| "epo_Latn", | |
| "est_Latn", | |
| "eus_Latn", | |
| "ewe_Latn", | |
| "fao_Latn", | |
| "pes_Arab", | |
| "fij_Latn", | |
| "fin_Latn", | |
| "fon_Latn", | |
| "fra_Latn", | |
| "fur_Latn", | |
| "fuv_Latn", | |
| "gla_Latn", | |
| "gle_Latn", | |
| "glg_Latn", | |
| "grn_Latn", | |
| "guj_Gujr", | |
| "hat_Latn", | |
| "hau_Latn", | |
| "heb_Hebr", | |
| "hin_Deva", | |
| "hne_Deva", | |
| "hrv_Latn", | |
| "hun_Latn", | |
| "hye_Armn", | |
| "ibo_Latn", | |
| "ilo_Latn", | |
| "ind_Latn", | |
| "isl_Latn", | |
| "ita_Latn", | |
| "jav_Latn", | |
| "jpn_Jpan", | |
| "kab_Latn", | |
| "kac_Latn", | |
| "kam_Latn", | |
| "kan_Knda", | |
| "kas_Arab", | |
| "kas_Deva", | |
| "kat_Geor", | |
| "knc_Arab", | |
| "knc_Latn", | |
| "kaz_Cyrl", | |
| "kbp_Latn", | |
| "kea_Latn", | |
| "khm_Khmr", | |
| "kik_Latn", | |
| "kin_Latn", | |
| "kir_Cyrl", | |
| "kmb_Latn", | |
| "kon_Latn", | |
| "kor_Hang", | |
| "kmr_Latn", | |
| "lao_Laoo", | |
| "lvs_Latn", | |
| "lij_Latn", | |
| "lim_Latn", | |
| "lin_Latn", | |
| "lit_Latn", | |
| "lmo_Latn", | |
| "ltg_Latn", | |
| "ltz_Latn", | |
| "lua_Latn", | |
| "lug_Latn", | |
| "luo_Latn", | |
| "lus_Latn", | |
| "mag_Deva", | |
| "mai_Deva", | |
| "mal_Mlym", | |
| "mar_Deva", | |
| "min_Latn", | |
| "mkd_Cyrl", | |
| "plt_Latn", | |
| "mlt_Latn", | |
| "mni_Beng", | |
| "khk_Cyrl", | |
| "mos_Latn", | |
| "mri_Latn", | |
| "zsm_Latn", | |
| "mya_Mymr", | |
| "nld_Latn", | |
| "nno_Latn", | |
| "nob_Latn", | |
| "npi_Deva", | |
| "nso_Latn", | |
| "nus_Latn", | |
| "nya_Latn", | |
| "oci_Latn", | |
| "gaz_Latn", | |
| "ory_Orya", | |
| "pag_Latn", | |
| "pan_Guru", | |
| "pap_Latn", | |
| "pol_Latn", | |
| "por_Latn", | |
| "prs_Arab", | |
| "pbt_Arab", | |
| "quy_Latn", | |
| "ron_Latn", | |
| "run_Latn", | |
| "rus_Cyrl", | |
| "sag_Latn", | |
| "san_Deva", | |
| "sat_Beng", | |
| "scn_Latn", | |
| "shn_Mymr", | |
| "sin_Sinh", | |
| "slk_Latn", | |
| "slv_Latn", | |
| "smo_Latn", | |
| "sna_Latn", | |
| "snd_Arab", | |
| "som_Latn", | |
| "sot_Latn", | |
| "spa_Latn", | |
| "als_Latn", | |
| "srd_Latn", | |
| "srp_Cyrl", | |
| "ssw_Latn", | |
| "sun_Latn", | |
| "swe_Latn", | |
| "swh_Latn", | |
| "szl_Latn", | |
| "tam_Taml", | |
| "tat_Cyrl", | |
| "tel_Telu", | |
| "tgk_Cyrl", | |
| "tgl_Latn", | |
| "tha_Thai", | |
| "tir_Ethi", | |
| "taq_Latn", | |
| "taq_Tfng", | |
| "tpi_Latn", | |
| "tsn_Latn", | |
| "tso_Latn", | |
| "tuk_Latn", | |
| "tum_Latn", | |
| "tur_Latn", | |
| "twi_Latn", | |
| "tzm_Tfng", | |
| "uig_Arab", | |
| "ukr_Cyrl", | |
| "umb_Latn", | |
| "urd_Arab", | |
| "uzn_Latn", | |
| "vec_Latn", | |
| "vie_Latn", | |
| "war_Latn", | |
| "wol_Latn", | |
| "xho_Latn", | |
| "ydd_Hebr", | |
| "yor_Latn", | |
| "yue_Hant", | |
| "zho_Hans", | |
| "zho_Hant", | |
| "zul_Latn", | |
| "kaa_Latn" | |
| ], | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "<s>", | |
| "eos_token": "</s>", | |
| "legacy_behaviour": false, | |
| "mask_token": "<mask>", | |
| "model_max_length": 1024, | |
| "pad_token": "<pad>", | |
| "sep_token": "</s>", | |
| "sp_model_kwargs": {}, | |
| "src_lang": "kaa_Latn", | |
| "tgt_lang": "eng_Latn", | |
| "tokenizer_class": "NllbTokenizer", | |
| "unk_token": "<unk>" | |
| } | |