bert-base-japanese-v2 / tokenizer_config.json
1 {
2 "do_lower_case": false,
3 "word_tokenizer_type": "mecab",
4 "subword_tokenizer_type": "wordpiece",
5 "mecab_kwargs": {
6 "mecab_dic": "unidic_lite"
7 }
8 }
9