bert-large-japanese-char / tokenizer_config.json

First commit of the bert-large-japanese-char model and tokenizer.

b0da028 about 3 years ago

No virus

174 Bytes

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