Create tokenizer_config.json

This commit is contained in:
Stardust·减
2023-10-11 18:36:55 +08:00
committed by GitHub
parent 95dc34f1a2
commit 7273c086d2

View File

@@ -0,0 +1,10 @@
{
"tokenizer_class": "BertJapaneseTokenizer",
"model_max_length": 512,
"do_lower_case": false,
"word_tokenizer_type": "mecab",
"subword_tokenizer_type": "wordpiece",
"mecab_kwargs": {
"mecab_dic": "unidic_lite"
}
}