{ "added_tokens_decoder": { "0": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "1": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "2": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "3": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40181": { "content": "", "lstrip": true, "normalized": true, "rstrip": false, "single_word": false, "special": true }, "40182": { "content": "ace_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40183": { "content": "ace_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40184": { "content": "acm_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40185": { "content": "acq_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40186": { "content": "aeb_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40187": { "content": "afr_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40188": { "content": "ajp_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40189": { "content": "aka_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40190": { "content": "als_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40191": { "content": "amh_Ethi", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40192": { "content": "apc_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40193": { "content": "aran_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40194": { "content": "arb_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40195": { "content": "arg_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40196": { "content": "ars_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40197": { "content": "ary_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40198": { "content": "arz_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40199": { "content": "asm_Beng", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40200": { "content": "ast_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40201": { "content": "awa_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40202": { "content": "ayr_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40203": { "content": "azb_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40204": { "content": "azj_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40205": { "content": "bak_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40206": { "content": "bam_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40207": { "content": "ban_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40208": { "content": "bel_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40209": { "content": "bem_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40210": { "content": "ben_Beng", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40211": { "content": "bho_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40212": { "content": "bjn_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40213": { "content": "bjn_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40214": { "content": "bod_Tibt", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40215": { "content": "bos_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40216": { "content": "bug_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40217": { "content": "bul_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40218": { "content": "cat_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40219": { "content": "ceb_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40220": { "content": "ces_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40221": { "content": "cjk_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40222": { "content": "ckb_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40223": { "content": "crh_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40224": { "content": "cym_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40225": { "content": "dan_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40226": { "content": "deu_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40227": { "content": "dik_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40228": { "content": "dyu_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40229": { "content": "dzo_Tibt", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40230": { "content": "ell_Grek", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40231": { "content": "eng_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40232": { "content": "epo_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40233": { "content": "est_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40234": { "content": "eus_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40235": { "content": "ewe_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40236": { "content": "fao_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40237": { "content": "fij_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40238": { "content": "fin_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40239": { "content": "fon_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40240": { "content": "fra_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40241": { "content": "fur_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40242": { "content": "fuv_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40243": { "content": "gaz_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40244": { "content": "gla_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40245": { "content": "gle_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40246": { "content": "glg_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40247": { "content": "grn_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40248": { "content": "guj_Gujr", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40249": { "content": "hat_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40250": { "content": "hau_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40251": { "content": "heb_Hebr", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40252": { "content": "hin_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40253": { "content": "hne_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40254": { "content": "hrv_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40255": { "content": "hun_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40256": { "content": "hye_Armn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40257": { "content": "ibo_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40258": { "content": "ilo_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40259": { "content": "ind_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40260": { "content": "isl_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40261": { "content": "ita_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40262": { "content": "jav_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40263": { "content": "jpn_Jpan", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40264": { "content": "kab_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40265": { "content": "kac_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40266": { "content": "kam_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40267": { "content": "kan_Knda", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40268": { "content": "kas_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40269": { "content": "kas_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40270": { "content": "kat_Geor", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40271": { "content": "kaz_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40272": { "content": "kbp_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40273": { "content": "kea_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40274": { "content": "khk_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40275": { "content": "khm_Khmr", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40276": { "content": "kik_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40277": { "content": "kin_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40278": { "content": "kir_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40279": { "content": "kmb_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40280": { "content": "kmr_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40281": { "content": "knc_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40282": { "content": "knc_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40283": { "content": "kon_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40284": { "content": "kor_Hang", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40285": { "content": "lao_Laoo", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40286": { "content": "lij_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40287": { "content": "lim_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40288": { "content": "lin_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40289": { "content": "lit_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40290": { "content": "lmo_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40291": { "content": "ltg_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40292": { "content": "ltz_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40293": { "content": "lua_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40294": { "content": "lug_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40295": { "content": "luo_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40296": { "content": "lus_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40297": { "content": "lvs_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40298": { "content": "mag_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40299": { "content": "mai_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40300": { "content": "mal_Mlym", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40301": { "content": "mar_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40302": { "content": "min_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40303": { "content": "mkd_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40304": { "content": "mlt_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40305": { "content": "mni_Beng", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40306": { "content": "mos_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40307": { "content": "mri_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40308": { "content": "mya_Mymr", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40309": { "content": "nld_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40310": { "content": "nno_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40311": { "content": "nob_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40312": { "content": "npi_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40313": { "content": "nso_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40314": { "content": "nus_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40315": { "content": "nya_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40316": { "content": "oci_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40317": { "content": "ory_Orya", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40318": { "content": "pag_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40319": { "content": "pan_Guru", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40320": { "content": "pap_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40321": { "content": "pbt_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40322": { "content": "pes_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40323": { "content": "plt_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40324": { "content": "pol_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40325": { "content": "por_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40326": { "content": "prs_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40327": { "content": "quy_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40328": { "content": "ron_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40329": { "content": "run_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40330": { "content": "rus_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40331": { "content": "sag_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40332": { "content": "san_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40333": { "content": "sat_Beng", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40334": { "content": "scn_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40335": { "content": "shn_Mymr", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40336": { "content": "sin_Sinh", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40337": { "content": "slk_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40338": { "content": "slv_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40339": { "content": "smo_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40340": { "content": "sna_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40341": { "content": "snd_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40342": { "content": "som_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40343": { "content": "sot_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40344": { "content": "spa_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40345": { "content": "srd_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40346": { "content": "srp_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40347": { "content": "ssw_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40348": { "content": "sun_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40349": { "content": "swe_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40350": { "content": "swh_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40351": { "content": "szl_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40352": { "content": "tam_Taml", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40353": { "content": "taq_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40354": { "content": "taq_Tfng", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40355": { "content": "tat_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40356": { "content": "tel_Telu", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40357": { "content": "tgk_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40358": { "content": "tgl_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40359": { "content": "tha_Thai", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40360": { "content": "tir_Ethi", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40361": { "content": "tpi_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40362": { "content": "tsn_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40363": { "content": "tso_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40364": { "content": "tuk_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40365": { "content": "tum_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40366": { "content": "tur_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40367": { "content": "twi_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40368": { "content": "tzm_Tfng", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40369": { "content": "uig_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40370": { "content": "ukr_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40371": { "content": "umb_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40372": { "content": "urd_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40373": { "content": "uzn_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40374": { "content": "vec_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40375": { "content": "vie_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40376": { "content": "war_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40377": { "content": "wol_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40378": { "content": "xho_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40379": { "content": "ydd_Hebr", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40380": { "content": "yor_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40381": { "content": "yue_Hant", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40382": { "content": "zho_Hans", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40383": { "content": "zho_Hant", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40384": { "content": "zsm_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40385": { "content": "zul_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", "als_Latn", "amh_Ethi", "apc_Arab", "aran_Latn", "arb_Arab", "arg_Latn", "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", "fij_Latn", "fin_Latn", "fon_Latn", "fra_Latn", "fur_Latn", "fuv_Latn", "gaz_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", "kaz_Cyrl", "kbp_Latn", "kea_Latn", "khk_Cyrl", "khm_Khmr", "kik_Latn", "kin_Latn", "kir_Cyrl", "kmb_Latn", "kmr_Latn", "knc_Arab", "knc_Latn", "kon_Latn", "kor_Hang", "lao_Laoo", "lij_Latn", "lim_Latn", "lin_Latn", "lit_Latn", "lmo_Latn", "ltg_Latn", "ltz_Latn", "lua_Latn", "lug_Latn", "luo_Latn", "lus_Latn", "lvs_Latn", "mag_Deva", "mai_Deva", "mal_Mlym", "mar_Deva", "min_Latn", "mkd_Cyrl", "mlt_Latn", "mni_Beng", "mos_Latn", "mri_Latn", "mya_Mymr", "nld_Latn", "nno_Latn", "nob_Latn", "npi_Deva", "nso_Latn", "nus_Latn", "nya_Latn", "oci_Latn", "ory_Orya", "pag_Latn", "pan_Guru", "pap_Latn", "pbt_Arab", "pes_Arab", "plt_Latn", "pol_Latn", "por_Latn", "prs_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", "srd_Latn", "srp_Cyrl", "ssw_Latn", "sun_Latn", "swe_Latn", "swh_Latn", "szl_Latn", "tam_Taml", "taq_Latn", "taq_Tfng", "tat_Cyrl", "tel_Telu", "tgk_Cyrl", "tgl_Latn", "tha_Thai", "tir_Ethi", "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", "zsm_Latn", "zul_Latn" ], "bos_token": "", "clean_up_tokenization_spaces": true, "cls_token": "", "eos_token": "", "extra_ids": 0, "legacy_behaviour": false, "mask_token": "", "model_max_length": 1000000000000000019884624838656, "pad_token": "", "sep_token": "", "sp_model_kwargs": {}, "src_lang": "eng_Latn", "tgt_lang": null, "tokenizer_class": "NllbTokenizer", "unk_token": "" }