ptaszynski commited on
Commit
4a6364a
1 Parent(s): 4472951

Upload tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +1 -0
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "do_lower_case": false, "do_word_tokenize": true, "do_subword_tokenize": true, "word_tokenizer_type": "mecab", "subword_tokenizer_type": "wordpiece", "never_split": null, "mecab_kwargs": {"mecab_dic": "ipadic"}, "tokenize_chinese_chars": false}