dummy-tokenizer-wordlevel / tokenizer.json
SaulLu's picture
add tokenizer
383e287
{"version":"1.0","truncation":null,"padding":{"strategy":{"Fixed":10},"direction":"Right","pad_to_multiple_of":null,"pad_id":3,"pad_type_id":0,"pad_token":"[PAD]"},"added_tokens":[{"id":0,"special":true,"content":"[UNK]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":1,"special":true,"content":"[CLS]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":2,"special":true,"content":"[SEP]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":3,"special":true,"content":"[PAD]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":4,"special":true,"content":"[MASK]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false}],"normalizer":{"type":"Sequence","normalizers":[{"type":"NFD"},{"type":"Lowercase"},{"type":"StripAccents"}]},"pre_tokenizer":{"type":"Sequence","pretokenizers":[{"type":"Whitespace"},{"type":"Digits","individual_digits":true}]},"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":[1],"tokens":["[CLS]"]},"[SEP]":{"id":"[SEP]","ids":[2],"tokens":["[SEP]"]}}},"decoder":null,"model":{"type":"WordLevel","vocab":{"[UNK]":0,"[CLS]":1,"[SEP]":2,"[PAD]":3,"[MASK]":4,".":5,"this":6,"sentence":7,"is":8,"one":9,"the":10,"2":11,"#)":12,"3":13,"numbers":14,"symbols":15,"first":16,"contains":17,"1":18,"not":19,"but":20,"second":21,"(":22,"and":23,"over":24},"unk_token":"[UNK]"}}