| { |
| "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 |
| }, |
| "271020": { |
| "content": "<mask>", |
| "lstrip": true, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271021": { |
| "content": "ace_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271022": { |
| "content": "ace_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271023": { |
| "content": "acm_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271024": { |
| "content": "acq_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271025": { |
| "content": "aeb_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271026": { |
| "content": "afr_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271027": { |
| "content": "ajp_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271028": { |
| "content": "aka_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271029": { |
| "content": "als_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271030": { |
| "content": "amh_Ethi", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271031": { |
| "content": "apc_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271032": { |
| "content": "arb_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271033": { |
| "content": "ars_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271034": { |
| "content": "ary_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271035": { |
| "content": "arz_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271036": { |
| "content": "asm_Beng", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271037": { |
| "content": "ast_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271038": { |
| "content": "awa_Deva", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271039": { |
| "content": "ayr_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271040": { |
| "content": "azb_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271041": { |
| "content": "azj_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271042": { |
| "content": "bak_Cyrl", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271043": { |
| "content": "bam_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271044": { |
| "content": "ban_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271045": { |
| "content": "bel_Cyrl", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271046": { |
| "content": "bem_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271047": { |
| "content": "ben_Beng", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271048": { |
| "content": "bho_Deva", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271049": { |
| "content": "bjn_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271050": { |
| "content": "bjn_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271051": { |
| "content": "bod_Tibt", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271052": { |
| "content": "bos_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271053": { |
| "content": "bug_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271054": { |
| "content": "bul_Cyrl", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271055": { |
| "content": "cat_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271056": { |
| "content": "ceb_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271057": { |
| "content": "ces_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271058": { |
| "content": "cjk_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271059": { |
| "content": "ckb_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271060": { |
| "content": "crh_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271061": { |
| "content": "cym_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271062": { |
| "content": "dan_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271063": { |
| "content": "deu_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271064": { |
| "content": "dik_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271065": { |
| "content": "dyu_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271066": { |
| "content": "dzo_Tibt", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271067": { |
| "content": "ell_Grek", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271068": { |
| "content": "eng_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271069": { |
| "content": "epo_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271070": { |
| "content": "est_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271071": { |
| "content": "eus_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271072": { |
| "content": "ewe_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271073": { |
| "content": "fao_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271074": { |
| "content": "fij_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271075": { |
| "content": "fin_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271076": { |
| "content": "fon_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271077": { |
| "content": "fra_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271078": { |
| "content": "fur_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271079": { |
| "content": "fuv_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271080": { |
| "content": "gaz_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271081": { |
| "content": "gla_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271082": { |
| "content": "gle_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271083": { |
| "content": "glg_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271084": { |
| "content": "grn_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271085": { |
| "content": "guj_Gujr", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271086": { |
| "content": "hat_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271087": { |
| "content": "hau_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271088": { |
| "content": "heb_Hebr", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271089": { |
| "content": "hin_Deva", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271090": { |
| "content": "hne_Deva", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271091": { |
| "content": "hrv_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271092": { |
| "content": "hun_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271093": { |
| "content": "hye_Armn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271094": { |
| "content": "ibo_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271095": { |
| "content": "ilo_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271096": { |
| "content": "ind_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271097": { |
| "content": "isl_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271098": { |
| "content": "ita_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271099": { |
| "content": "jav_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271100": { |
| "content": "jpn_Jpan", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271101": { |
| "content": "kab_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271102": { |
| "content": "kac_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271103": { |
| "content": "kam_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271104": { |
| "content": "kan_Knda", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271105": { |
| "content": "kas_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271106": { |
| "content": "kas_Deva", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271107": { |
| "content": "kat_Geor", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271108": { |
| "content": "kaz_Cyrl", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271109": { |
| "content": "kbd_Cyrl", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271110": { |
| "content": "kbp_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271111": { |
| "content": "kea_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271112": { |
| "content": "khk_Cyrl", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271113": { |
| "content": "khm_Khmr", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271114": { |
| "content": "kik_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271115": { |
| "content": "kin_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271116": { |
| "content": "kir_Cyrl", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271117": { |
| "content": "kmb_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271118": { |
| "content": "kmr_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271119": { |
| "content": "knc_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271120": { |
| "content": "knc_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271121": { |
| "content": "kon_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271122": { |
| "content": "kor_Hang", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271123": { |
| "content": "lao_Laoo", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271124": { |
| "content": "lij_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271125": { |
| "content": "lim_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271126": { |
| "content": "lin_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271127": { |
| "content": "lit_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271128": { |
| "content": "lmo_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271129": { |
| "content": "ltg_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271130": { |
| "content": "ltz_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271131": { |
| "content": "lua_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271132": { |
| "content": "lug_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271133": { |
| "content": "luo_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271134": { |
| "content": "lus_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271135": { |
| "content": "lvs_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271136": { |
| "content": "mag_Deva", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271137": { |
| "content": "mai_Deva", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271138": { |
| "content": "mal_Mlym", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271139": { |
| "content": "mar_Deva", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271140": { |
| "content": "min_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271141": { |
| "content": "mkd_Cyrl", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271142": { |
| "content": "mlt_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271143": { |
| "content": "mni_Beng", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271144": { |
| "content": "mos_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271145": { |
| "content": "mri_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271146": { |
| "content": "mya_Mymr", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271147": { |
| "content": "nld_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271148": { |
| "content": "nno_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271149": { |
| "content": "nob_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271150": { |
| "content": "npi_Deva", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271151": { |
| "content": "nso_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271152": { |
| "content": "nus_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271153": { |
| "content": "nya_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271154": { |
| "content": "oci_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271155": { |
| "content": "ory_Orya", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271156": { |
| "content": "pag_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271157": { |
| "content": "pan_Guru", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271158": { |
| "content": "pap_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271159": { |
| "content": "pbt_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271160": { |
| "content": "pes_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271161": { |
| "content": "plt_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271162": { |
| "content": "pol_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271163": { |
| "content": "por_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271164": { |
| "content": "prs_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271165": { |
| "content": "quy_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271166": { |
| "content": "ron_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271167": { |
| "content": "run_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271168": { |
| "content": "rus_Cyrl", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271169": { |
| "content": "sag_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271170": { |
| "content": "san_Deva", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271171": { |
| "content": "sat_Beng", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271172": { |
| "content": "scn_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271173": { |
| "content": "shn_Mymr", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271174": { |
| "content": "sin_Sinh", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271175": { |
| "content": "slk_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271176": { |
| "content": "slv_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271177": { |
| "content": "smo_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271178": { |
| "content": "sna_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271179": { |
| "content": "snd_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271180": { |
| "content": "som_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271181": { |
| "content": "sot_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271182": { |
| "content": "spa_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271183": { |
| "content": "srd_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271184": { |
| "content": "srp_Cyrl", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271185": { |
| "content": "ssw_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271186": { |
| "content": "sun_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271187": { |
| "content": "swe_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271188": { |
| "content": "swh_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271189": { |
| "content": "szl_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271190": { |
| "content": "tam_Taml", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271191": { |
| "content": "taq_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271192": { |
| "content": "taq_Tfng", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271193": { |
| "content": "tat_Cyrl", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271194": { |
| "content": "tel_Telu", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271195": { |
| "content": "tgk_Cyrl", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271196": { |
| "content": "tgl_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271197": { |
| "content": "tha_Thai", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271198": { |
| "content": "tir_Ethi", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271199": { |
| "content": "tpi_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271200": { |
| "content": "tsn_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271201": { |
| "content": "tso_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271202": { |
| "content": "tuk_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271203": { |
| "content": "tum_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271204": { |
| "content": "tur_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271205": { |
| "content": "twi_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271206": { |
| "content": "tzm_Tfng", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271207": { |
| "content": "uig_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271208": { |
| "content": "ukr_Cyrl", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271209": { |
| "content": "umb_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271210": { |
| "content": "urd_Arab", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271211": { |
| "content": "uzn_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271212": { |
| "content": "vec_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271213": { |
| "content": "vie_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271214": { |
| "content": "war_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271215": { |
| "content": "wol_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271216": { |
| "content": "xho_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271217": { |
| "content": "ydd_Hebr", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271218": { |
| "content": "yor_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271219": { |
| "content": "yue_Hant", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271220": { |
| "content": "zho_Hans", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271221": { |
| "content": "zho_Hant", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271222": { |
| "content": "zsm_Latn", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "271223": { |
| "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", |
| "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", |
| "kbd_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>", |
| "extra_special_tokens": {}, |
| "legacy_behaviour": false, |
| "mask_token": "<mask>", |
| "max_length": 1024, |
| "model_max_length": 1024, |
| "pad_to_multiple_of": null, |
| "pad_token": "<pad>", |
| "pad_token_type_id": 0, |
| "padding_side": "right", |
| "sep_token": "</s>", |
| "sp_model_kwargs": {}, |
| "src_lang": "eng_Latn", |
| "stride": 0, |
| "tgt_lang": "kbd_Cyrl", |
| "tokenizer_class": "NllbTokenizer", |
| "truncation_side": "right", |
| "truncation_strategy": "longest_first", |
| "unk_token": "<unk>" |
| } |
|
|