tokenizer_config.json

{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "do_lower_case": true, "do_word_tokenize": true, "do_subword_tokenize": true, "word_tokenizer_type": "mecab", "subword_tokenizer_type": "wordpiece", "never_split": null, "mecab_kwargs": null, "is_fast": true, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "sonoisa/clip-base-japanese", "tokenizer_class": "BertJapaneseTokenizer"}