deberta-v2-base-japanese-char-wwm / tokenizer_config.json
nobu-g's picture
first commit
8298794
raw
history blame
520 Bytes
{
"cls_token": "[CLS]",
"do_lower_case": false,
"do_subword_tokenize": true,
"do_word_tokenize": true,
"jumanpp_kwargs": null,
"mask_token": "[MASK]",
"mecab_kwargs": null,
"model_max_length": 1000000000000000019884624838656,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": null,
"subword_tokenizer_type": "character",
"sudachi_kwargs": null,
"tokenizer_class": "BertJapaneseTokenizer",
"unk_token": "[UNK]",
"word_tokenizer_type": "basic"
}