bert-base-japanese-v2 / tokenizer_config.json

First commit of the bert-base-japanese-v2 model and tokenizer.

c89b4e4 about 3 years ago

No virus

174 Bytes

	{
	"do_lower_case": false,
	"word_tokenizer_type": "mecab",
	"subword_tokenizer_type": "wordpiece",
	"mecab_kwargs": {
	"mecab_dic": "unidic_lite"
	}
	}