1 line
428 KiB
JSON
1 line
428 KiB
JSON
|
{"version":"1.0","truncation":{"max_length":384,"strategy":"LongestFirst","stride":0},"padding":{"strategy":"BatchLongest","direction":"Right","pad_to_multiple_of":null,"pad_id":0,"pad_type_id":0,"pad_token":"[PAD]"},"added_tokens":[{"id":0,"special":true,"content":"[PAD]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":100,"special":true,"content":"[UNK]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":101,"special":true,"content":"[CLS]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":102,"special":true,"content":"[SEP]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":103,"special":true,"content":"[MASK]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false}],"normalizer":{"type":"BertNormalizer","clean_text":true,"handle_chinese_chars":true,"strip_accents":null,"lowercase":false},"pre_tokenizer":{"type":"BertPreTokenizer"},"post_processor":{"type":"TemplateProcessing","single":[{"SpecialToken":{"id":"[CLS]","type_id":0}},{"Sequence":{"id":"A","type_id":0}},{"SpecialToken":{"id":"[SEP]","type_id":0}}],"pair":[{"SpecialToken":{"id":"[CLS]","type_id":0}},{"Sequence":{"id":"A","type_id":0}},{"SpecialToken":{"id":"[SEP]","type_id":0}},{"Sequence":{"id":"B","type_id":1}},{"SpecialToken":{"id":"[SEP]","type_id":1}}],"special_tokens":{"[CLS]":{"id":"[CLS]","ids":[101],"tokens":["[CLS]"]},"[SEP]":{"id":"[SEP]","ids":[102],"tokens":["[SEP]"]}}},"decoder":{"type":"WordPiece","prefix":"##","cleanup":true},"model":{"type":"WordPiece","unk_token":"[UNK]","continuing_subword_prefix":"##","max_input_chars_per_word":100,"vocab":{"[PAD]":0,"[unused1]":1,"[unused2]":2,"[unused3]":3,"[unused4]":4,"[unused5]":5,"[unused6]":6,"[unused7]":7,"[unused8]":8,"[unused9]":9,"[unused10]":10,"[unused11]":11,"[unused12]":12,"[unused13]":13,"[unused14]":14,"[unused15]":15,"[unused16]":16,"[unused17]":17,"[unused18]":18,"[unused19]":19,"[unused20]":20,"[unused21]":21,"[unused22]":22,"[unused23]":23,"[unused24]":24,"[unused25]":25,"[unused26]":26,"[unused27]":27,"[unused28]":28,"[unused29]":29,"[unused30]":30,"[unused31]":31,"[unused32]":32,"[unused33]":33,"[unused34]":34,"[unused35]":35,"[unused36]":36,"[unused37]":37,"[unused38]":38,"[unused39]":39,"[unused40]":40,"[unused41]":41,"[unused42]":42,"[unused43]":43,"[unused44]":44,"[unused45]":45,"[unused46]":46,"[unused47]":47,"[unused48]":48,"[unused49]":49,"[unused50]":50,"[unused51]":51,"[unused52]":52,"[unused53]":53,"[unused54]":54,"[unused55]":55,"[unused56]":56,"[unused57]":57,"[unused58]":58,"[unused59]":59,"[unused60]":60,"[unused61]":61,"[unused62]":62,"[unused63]":63,"[unused64]":64,"[unused65]":65,"[unused66]":66,"[unused67]":67,"[unused68]":68,"[unused69]":69,"[unused70]":70,"[unused71]":71,"[unused72]":72,"[unused73]":73,"[unused74]":74,"[unused75]":75,"[unused76]":76,"[unused77]":77,"[unused78]":78,"[unused79]":79,"[unused80]":80,"[unused81]":81,"[unused82]":82,"[unused83]":83,"[unused84]":84,"[unused85]":85,"[unused86]":86,"[unused87]":87,"[unused88]":88,"[unused89]":89,"[unused90]":90,"[unused91]":91,"[unused92]":92,"[unused93]":93,"[unused94]":94,"[unused95]":95,"[unused96]":96,"[unused97]":97,"[unused98]":98,"[unused99]":99,"[UNK]":100,"[CLS]":101,"[SEP]":102,"[MASK]":103,"<S>":104,"<T>":105,"!":106,"\"":107,"#":108,"$":109,"%":110,"&":111,"'":112,"(":113,")":114,"*":115,"+":116,",":117,"-":118,".":119,"/":120,"d":121,"e":122,"a":123,"##ra":124,"de":125,"p":126,"c":127,"##os":128,"##nt":129,"##re":130,":":131,";":132,"<":133,"=":134,">":135,"?":136,"@":137,"##as":138,"s":139,"##er":140,"##or":141,"##ad":142,"##es":143,"co":144,"##is":145,"o":146,"##in":147,"##ma":148,"n":149,"##ão":150,"##ia":151,"##qu":152,"f":153,"##ta":154,"##me":155,"##ic":156,"##ro":157,"##nd":158,"##ar":159,"t":160,"##id":161,"##al":162,"qu":163,"[":164,"\\":165,"]":166,"^":167,"_":168,"u":169,"com":170,"do":171,"##ri":172,"em":173,"m":174,"##nte":175,"se":176,"A":177,"##el":178,"que":179,"da":180,"##on":181,"##ção":182,"##to":183,"re":184,"##te":185,"##ara":186,"C":187,"es":188,"v"
|