Upload tokenizer
e44846b
verified
|
{ |
|
"<mask>": 271020, |
|
"ace_Arab": 271021, |
|
"ace_Latn": 271022, |
|
"acm_Arab": 271023, |
|
"acq_Arab": 271024, |
|
"aeb_Arab": 271025, |
|
"afr_Latn": 271026, |
|
"ajp_Arab": 271027, |
|
"aka_Latn": 271028, |
|
"als_Latn": 271029, |
|
"amh_Ethi": 271030, |
|
"apc_Arab": 271031, |
|
"arb_Arab": 271032, |
|
"ars_Arab": 271033, |
|
"ary_Arab": 271034, |
|
"arz_Arab": 271035, |
|
"asm_Beng": 271036, |
|
"ast_Latn": 271037, |
|
"awa_Deva": 271038, |
|
"ayr_Latn": 271039, |
|
"azb_Arab": 271040, |
|
"azj_Latn": 271041, |
|
"bak_Cyrl": 271042, |
|
"bam_Latn": 271043, |
|
"ban_Latn": 271044, |
|
"bel_Cyrl": 271045, |
|
"bem_Latn": 271046, |
|
"ben_Beng": 271047, |
|
"bho_Deva": 271048, |
|
"bjn_Arab": 271049, |
|
"bjn_Latn": 271050, |
|
"bod_Tibt": 271051, |
|
"bos_Latn": 271052, |
|
"bug_Latn": 271053, |
|
"bul_Cyrl": 271054, |
|
"cat_Latn": 271055, |
|
"ceb_Latn": 271056, |
|
"ces_Latn": 271057, |
|
"cjk_Latn": 271058, |
|
"ckb_Arab": 271059, |
|
"crh_Latn": 271060, |
|
"cym_Latn": 271061, |
|
"dan_Latn": 271062, |
|
"deu_Latn": 271063, |
|
"dik_Latn": 271064, |
|
"dyu_Latn": 271065, |
|
"dzo_Tibt": 271066, |
|
"ell_Grek": 271067, |
|
"eng_Latn": 271068, |
|
"epo_Latn": 271069, |
|
"est_Latn": 271070, |
|
"eus_Latn": 271071, |
|
"ewe_Latn": 271072, |
|
"fao_Latn": 271073, |
|
"fij_Latn": 271074, |
|
"fin_Latn": 271075, |
|
"fon_Latn": 271076, |
|
"fra_Latn": 271077, |
|
"fur_Latn": 271078, |
|
"fuv_Latn": 271079, |
|
"gaz_Latn": 271080, |
|
"gla_Latn": 271081, |
|
"gle_Latn": 271082, |
|
"glg_Latn": 271083, |
|
"grn_Latn": 271084, |
|
"guj_Gujr": 271085, |
|
"hat_Latn": 271086, |
|
"hau_Latn": 271087, |
|
"heb_Hebr": 271088, |
|
"hin_Deva": 271089, |
|
"hne_Deva": 271090, |
|
"hrv_Latn": 271091, |
|
"hun_Latn": 271092, |
|
"hye_Armn": 271093, |
|
"ibo_Latn": 271094, |
|
"ilo_Latn": 271095, |
|
"ind_Latn": 271096, |
|
"isl_Latn": 271097, |
|
"ita_Latn": 271098, |
|
"jav_Latn": 271099, |
|
"jpn_Jpan": 271100, |
|
"kab_Latn": 271101, |
|
"kac_Latn": 271102, |
|
"kam_Latn": 271103, |
|
"kan_Knda": 271104, |
|
"kas_Arab": 271105, |
|
"kas_Deva": 271106, |
|
"kat_Geor": 271107, |
|
"kaz_Cyrl": 271108, |
|
"kbd_Cyrl": 271109, |
|
"kbp_Latn": 271110, |
|
"kea_Latn": 271111, |
|
"khk_Cyrl": 271112, |
|
"khm_Khmr": 271113, |
|
"kik_Latn": 271114, |
|
"kin_Latn": 271115, |
|
"kir_Cyrl": 271116, |
|
"kmb_Latn": 271117, |
|
"kmr_Latn": 271118, |
|
"knc_Arab": 271119, |
|
"knc_Latn": 271120, |
|
"kon_Latn": 271121, |
|
"kor_Hang": 271122, |
|
"lao_Laoo": 271123, |
|
"lij_Latn": 271124, |
|
"lim_Latn": 271125, |
|
"lin_Latn": 271126, |
|
"lit_Latn": 271127, |
|
"lmo_Latn": 271128, |
|
"ltg_Latn": 271129, |
|
"ltz_Latn": 271130, |
|
"lua_Latn": 271131, |
|
"lug_Latn": 271132, |
|
"luo_Latn": 271133, |
|
"lus_Latn": 271134, |
|
"lvs_Latn": 271135, |
|
"mag_Deva": 271136, |
|
"mai_Deva": 271137, |
|
"mal_Mlym": 271138, |
|
"mar_Deva": 271139, |
|
"min_Latn": 271140, |
|
"mkd_Cyrl": 271141, |
|
"mlt_Latn": 271142, |
|
"mni_Beng": 271143, |
|
"mos_Latn": 271144, |
|
"mri_Latn": 271145, |
|
"mya_Mymr": 271146, |
|
"nld_Latn": 271147, |
|
"nno_Latn": 271148, |
|
"nob_Latn": 271149, |
|
"npi_Deva": 271150, |
|
"nso_Latn": 271151, |
|
"nus_Latn": 271152, |
|
"nya_Latn": 271153, |
|
"oci_Latn": 271154, |
|
"ory_Orya": 271155, |
|
"pag_Latn": 271156, |
|
"pan_Guru": 271157, |
|
"pap_Latn": 271158, |
|
"pbt_Arab": 271159, |
|
"pes_Arab": 271160, |
|
"plt_Latn": 271161, |
|
"pol_Latn": 271162, |
|
"por_Latn": 271163, |
|
"prs_Arab": 271164, |
|
"quy_Latn": 271165, |
|
"ron_Latn": 271166, |
|
"run_Latn": 271167, |
|
"rus_Cyrl": 271168, |
|
"sag_Latn": 271169, |
|
"san_Deva": 271170, |
|
"sat_Beng": 271171, |
|
"scn_Latn": 271172, |
|
"shn_Mymr": 271173, |
|
"sin_Sinh": 271174, |
|
"slk_Latn": 271175, |
|
"slv_Latn": 271176, |
|
"smo_Latn": 271177, |
|
"sna_Latn": 271178, |
|
"snd_Arab": 271179, |
|
"som_Latn": 271180, |
|
"sot_Latn": 271181, |
|
"spa_Latn": 271182, |
|
"srd_Latn": 271183, |
|
"srp_Cyrl": 271184, |
|
"ssw_Latn": 271185, |
|
"sun_Latn": 271186, |
|
"swe_Latn": 271187, |
|
"swh_Latn": 271188, |
|
"szl_Latn": 271189, |
|
"tam_Taml": 271190, |
|
"taq_Latn": 271191, |
|
"taq_Tfng": 271192, |
|
"tat_Cyrl": 271193, |
|
"tel_Telu": 271194, |
|
"tgk_Cyrl": 271195, |
|
"tgl_Latn": 271196, |
|
"tha_Thai": 271197, |
|
"tir_Ethi": 271198, |
|
"tpi_Latn": 271199, |
|
"tsn_Latn": 271200, |
|
"tso_Latn": 271201, |
|
"tuk_Latn": 271202, |
|
"tum_Latn": 271203, |
|
"tur_Latn": 271204, |
|
"twi_Latn": 271205, |
|
"tzm_Tfng": 271206, |
|
"uig_Arab": 271207, |
|
"ukr_Cyrl": 271208, |
|
"umb_Latn": 271209, |
|
"urd_Arab": 271210, |
|
"uzn_Latn": 271211, |
|
"vec_Latn": 271212, |
|
"vie_Latn": 271213, |
|
"war_Latn": 271214, |
|
"wol_Latn": 271215, |
|
"xho_Latn": 271216, |
|
"ydd_Hebr": 271217, |
|
"yor_Latn": 271218, |
|
"yue_Hant": 271219, |
|
"zho_Hans": 271220, |
|
"zho_Hant": 271221, |
|
"zsm_Latn": 271222, |
|
"zul_Latn": 271223 |
|
} |
|
|