Create tokenizer_config.json
This commit is contained in:
10
bert/bert-large-japanese-v2/tokenizer_config.json
Normal file
10
bert/bert-large-japanese-v2/tokenizer_config.json
Normal 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"
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user