add tokenizer

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer.json

@@ -0,0 +1 @@
+{"version":"1.0","truncation":null,"padding":null,"added_tokens":[{"id":0,"special":true,"content":"[UNK]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":1,"special":true,"content":"[PAD]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":2,"special":true,"content":"[CLS]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":3,"special":true,"content":"[SEP]","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":null,"pre_tokenizer":{"type":"WhitespaceSplit"},"post_processor":{"type":"TemplateProcessing","single":[{"SpecialToken":{"id":"[CLS]","type_id":0}},{"Sequence":{"id":"A","type_id":0}},{"SpecialToken":{"id":"[SEP]","type_id":0}}],"pair":[{"Sequence":{"id":"A","type_id":0}},{"Sequence":{"id":"B","type_id":1}}],"special_tokens":{"[CLS]":{"id":"[CLS]","ids":[2],"tokens":["[CLS]"]},"[SEP]":{"id":"[SEP]","ids":[3],"tokens":["[SEP]"]}}},"decoder":{"type":"WordPiece","prefix":"##","cleanup":true},"model":{"type":"WordPiece","unk_token":"[UNK]","continuing_subword_prefix":"##","max_input_chars_per_word":100,"vocab":{"[UNK]":0,"[PAD]":1,"[CLS]":2,"[SEP]":3,"[MASK]":4,"#":5,"%":6,"(":7,")":8,"*":9,"+":10,"-":11,".":12,"/":13,"0":14,"1":15,"2":16,"3":17,"4":18,"5":19,"6":20,"7":21,"8":22,"9":23,":":24,"=":25,"@":26,"A":27,"B":28,"C":29,"F":30,"G":31,"H":32,"I":33,"K":34,"L":35,"M":36,"N":37,"O":38,"P":39,"R":40,"S":41,"T":42,"V":43,"W":44,"Z":45,"[":46,"\\":47,"]":48,"a":49,"b":50,"c":51,"d":52,"e":53,"g":54,"i":55,"l":56,"n":57,"o":58,"r":59,"s":60,"t":61,"u":62,"|":63}}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "pad_token": "[PAD]", "cls_token": "[CLS]", "sep_token": "[SEP]", "mask_token": "[MASK]", "tokenizer_class": "PreTrainedTokenizerFast"}