Adding a 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":"[PAD]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":1,"special":true,"content":"[UNK]","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":{"type":"BertNormalizer","clean_text":true,"handle_chinese_chars":true,"strip_accents":null,"lowercase":true},"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":[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":{"[PAD]":0,"[UNK]":1,"[CLS]":2,"[SEP]":3,"[MASK]":4,"0":5,"1":6,"2":7,"3":8,"4":9,"5":10,"6":11,"7":12,"8":13,"9":14,"a":15,"b":16,"c":17,"d":18,"e":19,"f":20,"g":21,"h":22,"i":23,"j":24,"k":25,"l":26,"m":27,"n":28,"o":29,"p":30,"q":31,"r":32,"s":33,"t":34,"u":35,"v":36,"w":37,"x":38,"y":39,"z":40}}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}