tokenizer_config.json

    "tokenizer_class": "BertTokenizer",
    "special_tokens": {
        "0": {
            "content": "[PAD]",
            "lstrip": False,
            "normalized": False,
            "rstrip": False,
            "single_word": False,
            "special": True
        },
        "1": {
            "content": "[UNK]",
            "lstrip": False,
            "normalized": False,
            "rstrip": False,
            "single_word": False,
            "special": True
        },
        "2": {
            "content": "[CLS]",
            "lstrip": False,
            "normalized": False,
            "rstrip": False,
            "single_word": False,
            "special": True
        },
        "3": {
            "content": "[SEP]",
            "lstrip": False,
            "normalized": False,
            "rstrip": False,
            "single_word": False,
            "special": True
        },
        "4": {
            "content": "[MASK]",
            "lstrip": False,
            "normalized": False,
            "rstrip": False,
            "single_word": False,
            "special": True
        }
    },
    "clean_up_tokenization_spaces": True,
    "cls_token": "[CLS]",
    "do_basic_tokenize": True,
    "do_lower_case": False,
    "mask_token": "[MASK]",
    "max_len": 512,
    "model_max_length": 512,
    "pad_token": "[PAD]",
    "sep_token": "[SEP]",
    "tokenize_chinese_chars": True,
    "unk_token": "[UNK]"
}