{
    "added_tokens_decoder": {
        "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_lower_case": true,
    "mask_token": "[MASK]",
    "model_max_length": 1000000,
    "pad_token": "[PAD]",
    "sep_token": "[SEP]",
    "strip_accents": null,
    "tokenize_chinese_chars": true,
    "tokenizer_class": "BertTokenizer",
    "unk_token": "[UNK]"
}