tokenizer_config.json

{
    "do_lower_case": false,
    "remove_space": true,
    "keep_accents": false,
    "bos_token": "[CLS]",
    "eos_token": "[SEP]",
    "unk_token": "<unk>",
    "sep_token": "[SEP]",
    "pad_token": "<pad>",
    "cls_token": "[CLS]",
    "mask_token": {
        "content": "[MASK]",
        "single_word": false,
        "lstrip": true,
        "rstrip": false,
        "normalized": true,
        "__type": "AddedToken"
    },
    "model_max_length": 512,
    "special_tokens_map_file": null
}