{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 4, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": { "type": "Sequence", "normalizers": [ { "type": "Replace", "pattern": { "String": "``" }, "content": "\"" }, { "type": "Replace", "pattern": { "String": "''" }, "content": "\"" }, { "type": "Lowercase" } ] }, "pre_tokenizer": { "type": "Metaspace", "replacement": "▁", "add_prefix_space": true }, "post_processor": { "type": "TemplateProcessing", "single": [ { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "", "type_id": 0 } } ], "pair": [ { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 1 } }, { "SpecialToken": { "id": "", "type_id": 1 } } ], "special_tokens": { "": { "id": "", "ids": [ 1 ], "tokens": [ "" ] }, "": { "id": "", "ids": [ 0 ], "tokens": [ "" ] } } }, "decoder": { "type": "Metaspace", "replacement": "▁", "add_prefix_space": true }, "model": { "type": "Unigram", "unk_id": 2, "vocab": [ [ "", 0.0 ], [ "", 0.0 ], [ "", 0.0 ], [ "", 0.0 ], [ "", 0.0 ], [ "▁", -2.75869814074289 ], [ "e", -3.312616264157093 ], [ "s", -3.3719250475744023 ], [ "en", -3.4381247480535055 ], [ "t", -3.4483632100593855 ], [ "n", -3.547764495418159 ], [ ".", -3.5814135507251574 ], [ "r", -3.985586727685172 ], [ "er", -4.105435074111609 ], [ "m", -4.147527265282559 ], [ "i", -4.3082347989832055 ], [ "a", -4.3383306500535515 ], [ "l", -4.38396185963647 ], [ "f", -4.457483526274293 ], [ "o", -4.458795876478087 ], [ "▁die", -4.4787959590968995 ], [ "d", -4.493714500336141 ], [ "▁der", -4.501206395980885 ], [ "h", -4.52087054257445 ], [ "g", -4.555359630477829 ], [ "k", -4.728413108345041 ], [ "b", -4.728493687673806 ], [ ",", -4.820429382378366 ], [ "▁in", -4.874868547517902 ], [ "te", -4.8754477832389895 ], [ "u", -4.877424070683746 ], [ "ch", -4.988026220956888 ], [ "ä", -4.998125557134038 ], [ "▁er", -5.020901588613167 ], [ "▁und", -5.020987097232181 ], [ "st", -5.0366433890513935 ], [ "ge", -5.072876596622347 ], [ "an", -5.100975368722509 ], [ "in", -5.102158730903094 ], [ "▁be", -5.108610311744911 ], [ "ung", -5.1190311944470075 ], [ "▁f", -5.128309174690552 ], [ "▁ge", -5.1693233905184695 ], [ "z", -5.188069767394529 ], [ "al", -5.209618747931673 ], [ "▁ein", -5.27127238240482 ], [ "de", -5.290898364318425 ], [ "ra", -5.310737078354421 ], [ "sch", -5.330307854624641 ], [ "▁k", -5.3439892292629665 ], [ "ü", -5.349766851766532 ], [ "p", -5.358254544579557 ], [ "▁b", -5.374240716221312 ], [ "w", -5.374880378418631 ], [ "▁ver", -5.396650532371973 ], [ "▁das", -5.4088127181600445 ], [ "▁ist", -5.456919152804689 ], [ "▁w", -5.485700876577935 ], [ "ig", -5.514026257241172 ], [ "lich", -5.518694259277911 ], [ "ar", -5.566747964819074 ], [ "▁p", -5.59180084924148 ], [ "or", -5.6276096697376055 ], [ "▁zu", -5.631915414929317 ], [ "▁an", -5.651446139739569 ], [ "v", -5.655471557856529 ], [ "au", -5.680286737329078 ], [ "ri", -5.682891895835626 ], [ "▁g", -5.696772444556638 ], [ "t.", -5.720050742665396 ], [ "-", -5.731128772318598 ], [ "▁auf", -5.7391396137393755 ], [ "ten", -5.748796887378994 ], [ "▁den", -5.767460627814067 ], [ "▁von", -5.7686699854994306 ], [ "gen", -5.770827998696065 ], [ "ter", -5.800157779559516 ], [ "▁sie", -5.803880645133027 ], [ "▁im", -5.817053967080254 ], [ "es", -5.820632369133392 ], [ "▁st", -5.827494754236234 ], [ "▁mit", -5.835538013517159 ], [ "it", -5.85709415599162 ], [ "▁wurde", -5.863190745594553 ], [ "y", -5.869776654571931 ], [ "ie", -5.87648437488655 ], [ "el", -5.8772670095245285 ], [ "▁eine", -5.880839248870803 ], [ "▁da", -5.8811216497434256 ], [ "▁aus", -5.898171630004322 ], [ "▁des", -5.915988264641809 ], [ "ö", -5.943319109015437 ], [ "on", -5.964821949828586 ], [ "li", -5.965697962947251 ], [ "▁sich", -5.983988699861534 ], [ "ck", -5.987007414057961 ], [ "▁war", -6.000573800306791 ], [ "hr", -6.004652206220825 ], [ "and", -6.005911091333797 ], [ "der", -6.018052059112792 ], [ "▁sch", -6.025410868369095 ], [ "▁als", -6.053585166436022 ], [ "us", -6.053597772180238 ], [ "am", -6.061784753367641 ], [ "ol", -6.070955151121469 ], [ "la", -6.080065708956543 ], [ "c", -6.086265614984958 ], [ "le", -6.1076147077692635 ], [ "den", -6.114766195397976 ], [ "▁auch", -6.13731418947477 ], [ "is", -6.141541370512261 ], [ "il", -6.158091580072076 ], [ "▁so", -6.158530638257609 ], [ "ro", -6.15865315958899 ], [ "▁für", -6.165951066569487 ], [ "▁es", -6.1694911089023545 ], [ "ben", -6.186844455940097 ], [ "ze", -6.190549524761561 ], [ "he", -6.2117989916965435 ], [ "ein", -6.216423579134291 ], [ "▁diese", -6.223669382913062 ], [ "ut", -6.235742695350446 ], [ "▁dem", -6.265119060284393 ], [ "▁nicht", -6.267290907384584 ], [ "▁nach", -6.274872680837348 ], [ "ur", -6.283759922503204 ], [ "at", -6.285377567240927 ], [ "▁se", -6.29495417335896 ], [ "▁vor", -6.307141876945975 ], [ "icht", -6.316192736375152 ], [ "▁bei", -6.318530243906897 ], [ "be", -6.319935480438783 ], [ "ste", -6.322867964484766 ], [ "di", -6.349601859601732 ], [ "ach", -6.352561667885455 ], [ "um", -6.35874918951737 ], [ "rei", -6.3804295161870215 ], [ "her", -6.392298871024934 ], [ "und", -6.393730838032889 ], [ "ll", -6.403448420498377 ], [ "▁re", -6.407967993323538 ], [ "ber", -6.4118177789026305 ], [ "▁sind", -6.431958277710065 ], [ "▁über", -6.451899490364783 ], [ "zi", -6.453047985028677 ], [ "ischen", -6.456424600422075 ], [ "ell", -6.456572654145521 ], [ "▁le", -6.468428156424034 ], [ "▁unter", -6.475003886305272 ], [ "ion", -6.481981767543816 ], [ "▁wir", -6.504626258504164 ], [ "▁ma", -6.505562218270631 ], [ "un", -6.537869386512531 ], [ "▁ab", -6.53894594077949 ], [ "▁seine", -6.53959793265474 ], [ "ische", -6.5414490480314065 ], [ "▁ha", -6.5414792852485935 ], [ "iert", -6.544741108919061 ], [ "tz", -6.567036042841911 ], [ "ß", -6.583993527198341 ], [ "ff", -6.594808892704224 ], [ "ho", -6.609771652969307 ], [ "ungen", -6.622011689293361 ], [ "▁wird", -6.624052586000612 ], [ "ort", -6.64188931074667 ], [ "ik", -6.6449616366863395 ], [ "\"", -6.649035786016627 ], [ "▁ich", -6.667445555964779 ], [ "hl", -6.675546551876016 ], [ "j", -6.678062410734741 ], [ "ist", -6.678334519818016 ], [ "wi", -6.683201932746302 ], [ "▁me", -6.707477675514756 ], [ "et", -6.7082257040432385 ], [ "▁ent", -6.708777597631121 ], [ "▁hat", -6.719245702825722 ], [ "ver", -6.72050168797791 ], [ "teil", -6.722221259612915 ], [ "igen", -6.750758692698236 ], [ "▁sein", -6.754158997802707 ], [ "uch", -6.761191366690705 ], [ "wa", -6.767589385032776 ], [ "ru", -6.7707355793973445 ], [ "lo", -6.781946795476449 ], [ "▁un", -6.793240157693967 ], [ "▁\"", -6.793952600948693 ], [ "spiel", -6.797090101463743 ], [ "▁zwei", -6.820649612058805 ], [ "kt", -6.824778692788945 ], [ "ger", -6.826413290597994 ], [ "hn", -6.829649698355993 ], [ "ür", -6.831854793290278 ], [ "▁um", -6.83341429147152 ], [ "ation", -6.838320671594765 ], [ "ing", -6.859880950467392 ], [ "x", -6.867989807676651 ], [ "reich", -6.882826310932511 ], [ "▁durch", -6.906881475050824 ], [ "▁ihre", -6.915547046241542 ], [ "lä", -6.919560669981115 ], [ "ord", -6.924469538872247 ], [ "ul", -6.9328674329671784 ], [ "zu", -6.987463065132173 ], [ "▁kon", -6.9895622039188385 ], [ "▁ka", -6.9961911950125355 ], [ "schaft", -6.999766869887019 ], [ "mal", -7.0344460413602174 ], [ "arbeit", -7.034993259437014 ], [ "▁werden", -7.039547600078 ], [ "▁mi", -7.050385916918238 ], [ "mp", -7.050641651972958 ], [ "elt", -7.054873992102243 ], [ "sten", -7.060614698146619 ], [ "▁alle", -7.103913175256194 ], [ "▁jahr", -7.112000128895074 ], [ "▁man", -7.127383616207302 ], [ "ör", -7.1412986640648 ], [ "▁zum", -7.14242469612301 ], [ "▁dieser", -7.165352785519538 ], [ "tzt", -7.171631771269578 ], [ "▁sa", -7.202048321039051 ], [ "bau", -7.20644117856231 ], [ "halt", -7.216762802931504 ], [ "▁mehr", -7.22039706170982 ], [ "▁mo", -7.226091520168657 ], [ "▁je", -7.227233521431723 ], [ "▁noch", -7.236773242116545 ], [ "komm", -7.247720965761744 ], [ "wei", -7.2828589669479875 ], [ "lei", -7.305385785004669 ], [ "▁wie", -7.327891201857508 ], [ "keit", -7.335373568623929 ], [ "▁nur", -7.348978214165395 ], [ "▁viel", -7.352513338463417 ], [ "vi", -7.368230379975277 ], [ "tre", -7.374482326525023 ], [ "▁neu", -7.375154113455144 ], [ "akt", -7.379326849574493 ], [ "heit", -7.390110112007271 ], [ "„", -7.40176410423696 ], [ "“", -7.40883866542336 ], [ "recht", -7.409385457473615 ], [ "▁hier", -7.428545346494632 ], [ "▁haben", -7.440458770925609 ], [ "?", -7.4523704427474655 ], [ "▁do", -7.455892524902303 ], [ "leg", -7.456050734990962 ], [ "bild", -7.45766768969791 ], [ "▁hin", -7.471094508844784 ], [ "lang", -7.504466892165924 ], [ "▁kann", -7.536434222203006 ], [ "▁andere", -7.543091364154497 ], [ "mme", -7.5612321696173215 ], [ "fahr", -7.571192391627544 ], [ "q", -7.587118602885619 ], [ "gleich", -7.597417875437799 ], [ "▁drei", -7.599016169524393 ], [ "▁jedoch", -7.6002320596282225 ], [ "burg", -7.602107044866537 ], [ "▁oder", -7.604658598051678 ], [ "▁heute", -7.606711186892904 ], [ "▁keine", -7.6131058818296 ], [ "▁groß", -7.61440321043448 ], [ "sitz", -7.644053928528626 ], [ "ließ", -7.65677102477242 ], [ "▁später", -7.681462829134073 ], [ "▁co", -7.688024955724712 ], [ "weise", -7.694226505370855 ], [ "ierung", -7.705463265715375 ], [ "form", -7.724321308170094 ], [ "▁muss", -7.748649003246093 ], [ "▁gibt", -7.7502204236923244 ], [ "werk", -7.753334848484616 ], [ "folge", -7.762185849321737 ], [ "▁weitere", -7.764369532721215 ], [ "mittel", -7.780095405398454 ], [ "weg", -7.791796549586241 ], [ "punkt", -7.845096448765087 ], [ "▁liegt", -7.871328708467415 ], [ "▁können", -7.892505531307874 ], [ "stelle", -7.905102190407893 ], [ "staat", -7.923151986545443 ], [ "▁erfolg", -7.930287001745647 ], [ "bahn", -7.942413993335366 ], [ "nehmen", -7.953030717890771 ], [ "gebiet", -7.954203121546094 ], [ "▁dabei", -7.955131162440692 ], [ "grün", -7.977574976420131 ], [ "▁süd", -7.986156104193258 ], [ "wirtschaft", -8.007825074707023 ], [ "!", -8.01228655161355 ], [ "fass", -8.014442284722913 ], [ "▁zusammen", -8.017787194974085 ], [ "▁müssen", -8.019995697129897 ], [ "▁bekannt", -8.026468634167097 ], [ "kirche", -8.03219648494238 ], [ "gesetz", -8.065492615461816 ], [ "▁sollte", -8.069228675299462 ], [ "nahme", -8.08402740554071 ], [ "möglich", -8.103342473383943 ], [ "▁gehört", -8.103960144411996 ], [ "▁vom", -8.11029946558302 ], [ "trieb", -8.132262754066497 ], [ "▁deutsche", -8.192299759856168 ], [ "schloss", -8.195050727940053 ], [ "▁europäische", -8.197116052214193 ], [ "meister", -8.20172742580222 ], [ "▁befindet", -8.249029222994382 ], [ "▁selbst", -8.259068090189473 ], [ "▁zwischen", -8.273903230387441 ], [ "ologi", -8.27427649405356 ], [ "▁möchte", -8.286080099671937 ], [ "▁europa", -8.305009397364849 ], [ "▁während", -8.311893165250204 ], [ "▁außerdem", -8.31683927148722 ], [ "gestellt", -8.341358703560255 ], [ "gruppe", -8.41887542840609 ], [ "▁kommission", -8.435971328600344 ], [ "ständig", -8.454271334745378 ], [ "▁allerdings", -8.481979445575766 ], [ "wissenschaft", -8.494042654613365 ], [ "▁zahlreiche", -8.505652670619737 ], [ "▁zunächst", -8.569961824648042 ], [ "▁parlament", -8.575405135909682 ], [ "▁ebenfalls", -8.600438945496862 ], [ "präsident", -8.604066919002488 ], [ "▁studierte", -8.665383737644929 ], [ "gebäude", -8.67137606251437 ], [ "▁weltkrieg", -8.697149280895086 ], [ "produkt", -8.737487425468892 ], [ "▁universität", -8.75461705933243 ], [ "▁deutschland", -8.781872005967628 ], [ "▁verheiratet", -8.893236961619962 ], [ "▁ursprünglich", -9.07675048545418 ], [ ":", -9.17176916010953 ], [ "’", -9.403621455832074 ], [ "–", -9.720010046222232 ], [ "(", -9.967011307247525 ], [ ")", -9.967011307247526 ], [ "'", -9.967011307247526 ], [ ";", -10.03099047461219 ], [ "á", -11.14485899373271 ], [ "í", -11.374838851749285 ], [ "‘", -11.412477612533788 ], [ "ó", -11.605264112823864 ], [ "»", -11.659884984961778 ], [ "ō", -11.674019437064464 ], [ "«", -11.674019437064464 ], [ "‚", -11.755545670894074 ], [ "š", -12.081262834240782 ], [ "&", -12.182471666882812 ], [ "é", -12.584975346684514 ], [ "č", -12.602832489541656 ], [ "ł", -12.639532826241991 ], [ "ř", -12.758480859736956 ], [ "”", -12.846446080865917 ], [ "â", -12.942901662531366 ], [ "ø", -13.021885504673104 ], [ "ž", -13.021885504673104 ], [ "ý", -13.137949506031225 ], [ "ı", -13.137949506031225 ], [ "ş", -13.169199506031225 ], [ "ô", -13.201457570547351 ], [ "ã", -13.234790903880686 ], [ "ñ", -13.269273662501377 ], [ "ū", -13.30498794821566 ], [ "´", -13.342024985252698 ], [ "ʿ", -13.3420249852527 ], [ "ā", -13.3420249852527 ], [ "ú", -13.380486523714236 ], [ "ë", -13.420486523714237 ], [ "ě", -13.64870504432406 ], [ "ə", -13.648705044324062 ], [ "ī", -13.94488237490544 ], [ "…", -14.016310946334023 ], [ "đ", -14.016310946334023 ], [ "—", -14.093234023257136 ], [ "æ", -14.09323402325714 ], [ "=", -14.093234023257144 ], [ "ń", -14.17656735659058 ], [ "å", -14.17656735659058 ], [ "ă", -14.367476447500716 ], [ "î", -14.4785875586143 ], [ "ð", -14.4785875586143 ], [ "ą", -14.603587558623405 ], [ "ň", -14.603587558623408 ], [ "_", -14.746444701520504 ], [ "ė", -14.746444701520508 ], [ "/", -14.913111368187174 ], [ "ï", -14.913111368187174 ], [ "−", -14.913111368187174 ], [ "ḫ", -15.113111368147216 ], [ "ő", -15.113111368147216 ], [ "ò", -15.113111368187171 ], [ "″", -15.113111368187177 ], [ "`", -15.363111368147216 ], [ "‟", -15.363111368187166 ], [ "ę", -15.363111368187177 ], [ "ů", -15.363111368187177 ], [ "′", -15.363111368187177 ], [ "¡", -15.69644470148055 ], [ "‹", -15.69644470148055 ], [ "а", -15.696444701480564 ], [ "‑", -15.696444701520496 ], [ "›", -15.696444701520504 ], [ "]", -15.696444701520509 ], [ "и", -15.696444701520509 ], [ "ġ", -15.696444701520509 ], [ "ì", -15.696444701520509 ], [ "о", -15.696444701520509 ], [ "ả", -16.19644470148055 ], [ "ť", -16.19644470148055 ], [ "õ", -16.19644470148055 ], [ "ṣ", -16.196444701480555 ], [ "ш", -16.196444701480566 ], [ "~", -16.19644470152049 ], [ "ạ", -16.196444701520498 ], [ "%", -16.19644470152051 ], [ "û", -16.19644470152051 ], [ "ế", -16.19644470152051 ], [ "ș", -17.194144701520507 ], [ "→", -17.19424470152051 ], [ "е", -17.19434470152051 ], [ "ç", -17.19444470152051 ], [ "ź", -17.19454470152051 ], [ "ț", -17.19464470152051 ], [ "р", -17.19474470152051 ], [ "ď", -17.19484470152051 ], [ "в", -17.19494470152051 ], [ "ğ", -17.19504470152051 ], [ "ż", -17.19514470152051 ], [ "ś", -17.195244701520508 ], [ "с", -17.195344701520508 ], [ "ф", -17.195444701520508 ], [ "[", -17.195544701520507 ], [ "à", -17.195644701520507 ], [ "œ", -17.19574470152051 ], [ "̇", -17.19584470152051 ], [ "ć", -17.19594470152051 ], [ "ê", -17.19604470152051 ], [ "ơ", -17.19614470152051 ], [ "µ", -17.19624470152051 ], [ "ʻ", -17.19634470152051 ], [ "̥", -17.19644470148056 ], [ "ħ", -17.19644470148056 ], [ "к", -17.19644470148057 ], [ "*", -17.19644470148057 ], [ "+", -17.19644470148057 ], [ "ſ", -17.196444701520498 ], [ "ŏ", -17.196444701520498 ], [ "ē", -17.196444701520498 ], [ "§", -17.196444701520498 ], [ "м", -17.19644470152051 ], [ "ה", -17.19644470152051 ], [ "孙", -17.19644470152051 ], [ "临", -17.19644470152051 ], [ "ṟ", -17.19644470152051 ], [ "比", -17.19644470152051 ], [ "辶", -17.19644470152051 ], [ "关", -17.19644470152051 ], [ "尣", -17.19644470152051 ], [ "ʾ", -17.19644470152051 ], [ "ṭ", -17.19644470152051 ], [ "þ", -17.19644470152051 ], [ "ắ", -17.19644470152051 ], [ "ņ", -17.19644470152051 ], [ "ụ", -17.19644470152051 ], [ "ễ", -17.19644470152051 ], [ "ù", -17.19644470152051 ], [ "ч", -17.19644470152051 ], [ "ན", -17.19644470152051 ], [ "カ", -17.19644470152051 ], [ "°", -17.19644470152051 ], [ "合", -17.19644470152051 ], [ "è", -17.19644470152051 ], [ "×", -17.19644470152051 ], [ "̆", -17.19644470152051 ], [ "道", -17.19644470152051 ], [ "城", -17.19644470152051 ], [ "臣", -17.19644470152051 ], [ "無", -17.19644470152051 ], [ "ע", -17.19644470152051 ], [ "镇", -17.19644470152051 ], [ "ַ", -17.19644470152051 ], [ "$", -17.19644470152051 ], [ "ộ", -17.19644470152051 ], [ "ǐ", -17.19644470152051 ], [ "东", -17.19644470152051 ], [ "ѹ", -17.19644470152051 ], [ "支", -17.19644470152051 ], [ "泽", -17.19644470152051 ], [ "黃", -17.19644470152051 ], [ "⟩", -17.19644470152051 ], [ "་", -17.19644470152051 ], [ "י", -17.19644470152051 ], [ "毛", -17.19644470152051 ], [ "⟨", -17.19644470152051 ], [ "≡", -17.19644470152051 ], [ "ằ", -17.19644470152051 ], [ "ש", -17.19644470152051 ] ] } }