{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "([bos])", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "([eos])", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "([unk])", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "([pad])", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 4, "content": "([mask])", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 247, "content": "(LNG)", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 248, "content": "(UNK)", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 249, "content": "(SPN)", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false } ], "normalizer": null, "pre_tokenizer": { "type": "Metaspace", "replacement": "▁", "add_prefix_space": true, "prepend_scheme": "always" }, "post_processor": { "type": "TemplateProcessing", "single": [ { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "([eos])", "type_id": 0 } } ], "pair": [ { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "([eos])", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 1 } }, { "SpecialToken": { "id": "([eos])", "type_id": 1 } } ], "special_tokens": { "([bos])": { "id": "([bos])", "ids": [ 0 ], "tokens": [ "([bos])" ] }, "([eos])": { "id": "([eos])", "ids": [ 1 ], "tokens": [ "([eos])" ] } } }, "decoder": { "type": "Metaspace", "replacement": "▁", "add_prefix_space": true, "prepend_scheme": "always" }, "model": { "type": "Unigram", "unk_id": 2, "vocab": [ [ "([bos])", 0.0 ], [ "([eos])", 0.0 ], [ "([unk])", 0.0 ], [ "([pad])", 0.0 ], [ "([mask])", 0.0 ], [ "▁", -1.9847706990161544 ], [ "a", -3.1314497930271177 ], [ "t", -3.1881965015958187 ], [ "i", -3.4243963619008255 ], [ "d", -3.5014511936716186 ], [ "o", -3.5274805409389582 ], [ "m", -3.558661298685198 ], [ "u", -3.625320681110813 ], [ "s", -3.712394209496356 ], [ "v", -3.72415747794809 ], [ ",", -3.805334281306008 ], [ "k", -3.823407487612606 ], [ "á", -4.06402185490056 ], [ "e", -4.118975276125365 ], [ "r", -4.1561955333170815 ], [ "l", -4.207310751159483 ], [ "n", -4.260244529295308 ], [ "y", -4.279903492234059 ], [ "í", -4.4102129224806585 ], [ "ě", -4.502923994115825 ], [ "p", -4.532547889978606 ], [ "▁v", -4.559246971264237 ], [ "ní", -4.566408642453595 ], [ ".", -4.579478426041845 ], [ "ch", -4.7060160462408955 ], [ "b", -4.7267873231612505 ], [ "z", -4.741376547385773 ], [ "▁s", -4.7959555301926695 ], [ "▁po", -4.890977951755792 ], [ "▁z", -4.9117950878941965 ], [ "j", -4.983830676165416 ], [ "é", -4.997351240560704 ], [ "li", -5.030678383363137 ], [ "c", -5.0396387435626995 ], [ "ž", -5.049142114448735 ], [ "to", -5.057673228667184 ], [ "h", -5.079586658466628 ], [ "▁je", -5.113720460724675 ], [ "me", -5.1181371558896736 ], [ "▁na", -5.127083114594628 ], [ "▁pro", -5.147757595304579 ], [ "č", -5.179515263964058 ], [ "ů", -5.200945320530458 ], [ "ho", -5.221618751844693 ], [ "le", -5.2250844030131365 ], [ "ně", -5.27972704953069 ], [ "ce", -5.281994589031864 ], [ "▁ne", -5.308616451754174 ], [ "ý", -5.31697552150202 ], [ "▁se", -5.337009578506832 ], [ "la", -5.338199582903597 ], [ "ni", -5.339196490125113 ], [ "▁to", -5.349248427402005 ], [ "te", -5.381248563144281 ], [ "ra", -5.498126975121622 ], [ "š", -5.515959757283252 ], [ "pr", -5.6046024850544 ], [ "▁za", -5.620837358908096 ], [ "▁do", -5.620997292088125 ], [ "ro", -5.62869520219124 ], [ "g", -5.636274983240279 ], [ "en", -5.672796438052734 ], [ "ná", -5.6936132171970435 ], [ "ou", -5.705221838268827 ], [ "po", -5.731479162812082 ], [ "ci", -5.737597320989661 ], [ "▁k", -5.739511554705135 ], [ "ře", -5.750324760230148 ], [ "em", -5.7763291411793904 ], [ "▁že", -5.826140091837006 ], [ "mi", -5.832772778061484 ], [ "na", -5.836487492053504 ], [ "lo", -5.843302017381193 ], [ "f", -5.863906577570942 ], [ "vá", -5.896441383118669 ], [ "ne", -5.970429860963618 ], [ "né", -6.012839546213854 ], [ "ř", -6.0240161726213195 ], [ "jí", -6.0667261910328385 ], [ "ji", -6.0952373324629345 ], [ "ří", -6.233171041707054 ], [ ")", -6.275676190119125 ], [ "ze", -6.28944574316632 ], [ "ovat", -6.332103824255016 ], [ "ých", -6.338664587271952 ], [ "▁tak", -6.3416936938172075 ], [ "▁jak", -6.355716899830018 ], [ "še", -6.358544883928106 ], [ "kon", -6.362030472567895 ], [ "ské", -6.372589277660225 ], [ "cí", -6.396436911266985 ], [ "▁Evrop", -6.396990124349596 ], [ "ost", -6.415178844816895 ], [ "▁ob", -6.4345557525303665 ], [ "▁při", -6.453429679947529 ], [ "K", -6.557669972049428 ], [ "▁byl", -6.5913081200567305 ], [ "ú", -6.608159467526681 ], [ "▁by", -6.666809422458517 ], [ "▁děkuj", -6.724698564420603 ], [ "▁aby", -6.7258358147743795 ], [ "▁pří", -6.764730143329496 ], [ "ové", -6.787307118513603 ], [ "str", -6.844449647445437 ], [ "▁roz", -6.859666898290389 ], [ "▁které", -6.884647178230626 ], [ "▁bude", -6.909815247130545 ], [ "P", -6.91499677672085 ], [ "▁práv", -6.925378846074215 ], [ "ální", -7.001369471478936 ], [ "2", -7.002935587142833 ], [ "UN", -7.008632740292555 ], [ "oval", -7.0155367155397705 ], [ "▁stát", -7.030364051450455 ], [ "S", -7.056765638137547 ], [ "0", -7.090000239807136 ], [ "▁paní", -7.138568988225609 ], [ "bycho", -7.1887860518667495 ], [ "1", -7.204853513146585 ], [ "ň", -7.207931701488759 ], [ "potřeb", -7.285106413483476 ], [ "x", -7.315223767308989 ], [ "E", -7.375340704041776 ], [ "?", -7.386826804856964 ], [ "LNG", -7.3929905598606975 ], [ "R", -7.401684079434748 ], [ "▁další", -7.420579256632934 ], [ "▁koleg", -7.428233796020805 ], [ "▁návrh", -7.448936921677545 ], [ "-", -7.472487244726157 ], [ "ď", -7.533773150491692 ], [ "▁který", -7.537522052818428 ], [ "▁budou", -7.575344678712463 ], [ "▁občan", -7.594603707059271 ], [ "A", -7.615608685547574 ], [ "M", -7.653390606972009 ], [ "B", -7.6553176992492755 ], [ "▁společn", -7.670544502769873 ], [ "U", -7.67580272611945 ], [ "▁hlasování", -7.707787867541219 ], [ "3", -7.88204425480434 ], [ "▁komisař", -7.930804195673383 ], [ "▁myslím", -7.947026544282705 ], [ "▁parlament", -8.01146461330666 ], [ "▁skutečn", -8.050309277818695 ], [ "N", -8.097239230405401 ], [ "5", -8.105742503400506 ], [ "T", -8.121502869949357 ], [ "C", -8.176809220997738 ], [ "L", -8.187699548052356 ], [ "▁důležité", -8.214330862977269 ], [ "▁samozřejm", -8.238805618383932 ], [ "I", -8.29023538966668 ], [ "V", -8.303056077697512 ], [ "4", -8.304901096612927 ], [ "ť", -8.317912432172614 ], [ "D", -8.335528489527377 ], [ "O", -8.350878966312928 ], [ "F", -8.414064871470213 ], [ "Č", -8.44899681851851 ], [ "H", -8.500046908605349 ], [ "G", -8.523514969953006 ], [ "6", -8.57862541478596 ], [ "7", -8.59906766269739 ], [ "J", -8.64470295468657 ], [ "9", -8.679007107657972 ], [ "ó", -8.721975323121864 ], [ "8", -8.76492085037819 ], [ "w", -8.814906263661838 ], [ "(", -8.961548871720103 ], [ "Z", -9.1304809676736 ], [ "*", -9.405361687806153 ], [ "W", -9.730428224989948 ], [ "Ř", -10.146836119011482 ], [ "%", -10.215135657592311 ], [ "!", -10.607176887842284 ], [ "X", -10.677269027212253 ], [ "Ú", -10.88161257963682 ], [ "Y", -11.097694614772804 ], [ "ö", -11.595201719460682 ], [ "ü", -12.021529093476044 ], [ "ń", -12.15686214196699 ], [ ":", -12.2478269369759 ], [ "ä", -12.31341833482536 ], [ "–", -12.38361537916034 ], [ "Q", -12.499113954658911 ], [ "ă", -12.72733247526874 ], [ ";", -12.894343139183434 ], [ "'", -13.023509805850113 ], [ "è", -13.094938377278702 ], [ "ñ", -13.094938377278703 ], [ "ł", -13.171861454201824 ], [ "ś", -13.346103878444616 ], [ "’", -13.446103878445394 ], [ "ç", -13.55721498955898 ], [ "+", -13.682214989568084 ], [ "î", -13.682214989568084 ], [ "ę", -13.825072132425229 ], [ "ş", -13.825072132465184 ], [ "/", -13.825072132465186 ], [ "Ť", -13.991738799131848 ], [ "ė", -14.191738799131851 ], [ "ê", -14.775072132425228 ], [ "â", -14.775072132465183 ], [ "Ě", -14.775072132465183 ], [ "ț", -14.775072132465183 ], [ "ż", -14.775072132465183 ], [ "Ș", -15.275072132425244 ], [ "´", -15.27507213246516 ], [ "§", -15.275072132465189 ], [ "”", -15.275072132465189 ], [ "ë", -15.275072132465189 ], [ "​", -15.275072132465189 ], [ "ī", -15.275072132465189 ], [ "ß", -16.273572132465187 ], [ "Ş", -16.273672132465187 ], [ "Ó", -16.273772132465187 ], [ "Ł", -16.273872132465186 ], [ "ã", -16.273972132465186 ], [ "Í", -16.274072132465186 ], [ "Š", -16.274172132465186 ], [ "ć", -16.274272132465185 ], [ "ź", -16.27437213246519 ], [ "ţ", -16.27447213246519 ], [ "“", -16.274572132465188 ], [ "q", -16.274672132465188 ], [ "ï", -16.274772132465188 ], [ "Á", -16.274872132465187 ], [ "ș", -16.274972132465187 ], [ "Ö", -16.275072132425237 ], [ "ā", -16.275072132425237 ], [ "É", -16.275072132465176 ], [ "Ž", -16.275072132465187 ], [ "—", -16.275072132465187 ], [ "¨", -16.275072132465187 ], [ "°", -16.275072132465187 ], [ "ū", -16.275072132465187 ], [ "Ď", -16.275072132465187 ], [ "»", -16.275072132465187 ], [ "…", -16.275072132465187 ], [ "«", -16.275072132465187 ], [ "‑", -16.275072132465187 ] ], "byte_fallback": false } }