{ "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 }, "260984": { "content": "<mask>", "lstrip": true, "normalized": true, "rstrip": false, "single_word": false, "special": true }, "260985": { "content": "ace_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "260986": { "content": "ace_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "260987": { "content": "acm_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "260988": { "content": "acq_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "260989": { "content": "aeb_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "260990": { "content": "afr_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "260991": { "content": "ajp_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "260992": { "content": "aka_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "260993": { "content": "als_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "260994": { "content": "amh_Ethi", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "260995": { "content": "apc_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "260996": { "content": "arb_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "260997": { "content": "ars_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "260998": { "content": "ary_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "260999": { "content": "arz_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261000": { "content": "asm_Beng", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261001": { "content": "ast_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261002": { "content": "awa_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261003": { "content": "ayr_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261004": { "content": "azb_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261005": { "content": "azj_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261006": { "content": "bak_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261007": { "content": "bam_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261008": { "content": "ban_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261009": { "content": "bel_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261010": { "content": "bem_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261011": { "content": "ben_Beng", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261012": { "content": "bho_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261013": { "content": "bjn_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261014": { "content": "bjn_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261015": { "content": "bod_Tibt", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261016": { "content": "bos_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261017": { "content": "bug_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261018": { "content": "bul_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261019": { "content": "bxr_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261020": { "content": "cat_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261021": { "content": "ceb_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261022": { "content": "ces_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261023": { "content": "cjk_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261024": { "content": "ckb_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261025": { "content": "crh_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261026": { "content": "cym_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261027": { "content": "dan_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261028": { "content": "deu_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261029": { "content": "dik_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261030": { "content": "dyu_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261031": { "content": "dzo_Tibt", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261032": { "content": "ell_Grek", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261033": { "content": "eng_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261034": { "content": "epo_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261035": { "content": "est_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261036": { "content": "eus_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261037": { "content": "ewe_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261038": { "content": "fao_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261039": { "content": "fij_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261040": { "content": "fin_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261041": { "content": "fon_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261042": { "content": "fra_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261043": { "content": "fur_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261044": { "content": "fuv_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261045": { "content": "gaz_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261046": { "content": "gla_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261047": { "content": "gle_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261048": { "content": "glg_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261049": { "content": "grn_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261050": { "content": "guj_Gujr", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261051": { "content": "hat_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261052": { "content": "hau_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261053": { "content": "heb_Hebr", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261054": { "content": "hin_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261055": { "content": "hne_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261056": { "content": "hrv_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261057": { "content": "hun_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261058": { "content": "hye_Armn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261059": { "content": "ibo_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261060": { "content": "ilo_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261061": { "content": "ind_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261062": { "content": "isl_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261063": { "content": "ita_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261064": { "content": "jav_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261065": { "content": "jpn_Jpan", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261066": { "content": "kab_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261067": { "content": "kac_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261068": { "content": "kam_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261069": { "content": "kan_Knda", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261070": { "content": "kas_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261071": { "content": "kas_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261072": { "content": "kat_Geor", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261073": { "content": "kaz_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261074": { "content": "kbp_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261075": { "content": "kea_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261076": { "content": "khk_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261077": { "content": "khm_Khmr", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261078": { "content": "kik_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261079": { "content": "kin_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261080": { "content": "kir_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261081": { "content": "kmb_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261082": { "content": "kmr_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261083": { "content": "knc_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261084": { "content": "knc_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261085": { "content": "kon_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261086": { "content": "kor_Hang", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261087": { "content": "lao_Laoo", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261088": { "content": "lij_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261089": { "content": "lim_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261090": { "content": "lin_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261091": { "content": "lit_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261092": { "content": "lmo_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261093": { "content": "ltg_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261094": { "content": "ltz_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261095": { "content": "lua_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261096": { "content": "lug_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261097": { "content": "luo_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261098": { "content": "lus_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261099": { "content": "lvs_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261100": { "content": "mag_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261101": { "content": "mai_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261102": { "content": "mal_Mlym", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261103": { "content": "mar_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261104": { "content": "min_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261105": { "content": "mkd_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261106": { "content": "mlt_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261107": { "content": "mni_Beng", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261108": { "content": "mos_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261109": { "content": "mri_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261110": { "content": "mya_Mymr", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261111": { "content": "nld_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261112": { "content": "nno_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261113": { "content": "nob_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261114": { "content": "npi_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261115": { "content": "nso_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261116": { "content": "nus_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261117": { "content": "nya_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261118": { "content": "oci_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261119": { "content": "ory_Orya", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261120": { "content": "pag_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261121": { "content": "pan_Guru", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261122": { "content": "pap_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261123": { "content": "pbt_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261124": { "content": "pes_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261125": { "content": "plt_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261126": { "content": "pol_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261127": { "content": "por_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261128": { "content": "prs_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261129": { "content": "quy_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261130": { "content": "ron_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261131": { "content": "run_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261132": { "content": "rus_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261133": { "content": "sag_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261134": { "content": "san_Deva", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261135": { "content": "sat_Beng", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261136": { "content": "scn_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261137": { "content": "shn_Mymr", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261138": { "content": "sin_Sinh", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261139": { "content": "slk_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261140": { "content": "slv_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261141": { "content": "smo_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261142": { "content": "sna_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261143": { "content": "snd_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261144": { "content": "som_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261145": { "content": "sot_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261146": { "content": "spa_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261147": { "content": "srd_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261148": { "content": "srp_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261149": { "content": "ssw_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261150": { "content": "sun_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261151": { "content": "swe_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261152": { "content": "swh_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261153": { "content": "szl_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261154": { "content": "tam_Taml", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261155": { "content": "taq_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261156": { "content": "taq_Tfng", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261157": { "content": "tat_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261158": { "content": "tel_Telu", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261159": { "content": "tgk_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261160": { "content": "tgl_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261161": { "content": "tha_Thai", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261162": { "content": "tir_Ethi", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261163": { "content": "tpi_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261164": { "content": "tsn_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261165": { "content": "tso_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261166": { "content": "tuk_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261167": { "content": "tum_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261168": { "content": "tur_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261169": { "content": "twi_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261170": { "content": "tzm_Tfng", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261171": { "content": "uig_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261172": { "content": "ukr_Cyrl", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261173": { "content": "umb_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261174": { "content": "urd_Arab", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261175": { "content": "uzn_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261176": { "content": "vec_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261177": { "content": "vie_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261178": { "content": "war_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261179": { "content": "wol_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261180": { "content": "xho_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261181": { "content": "ydd_Hebr", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261182": { "content": "yor_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261183": { "content": "yue_Hant", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261184": { "content": "zho_Hans", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261185": { "content": "zho_Hant", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261186": { "content": "zsm_Latn", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "261187": { "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", "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", "bxr_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": "<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": "bxr_Cyrl", "tgt_lang": "rus_Cyrl", "tokenizer_class": "NllbTokenizer", "unk_token": "<unk>" }