tokenizer_config.json

{
    "add_prefix_space": false,
    "bos_token": "<s>",
    "clean_up_tokenization_spaces": true,
    "cls_token": "<s>",
    "eos_token": "</s>",
    "errors": "replace",
    "mask_token": "<mask>",
    "model_max_length": 512,
    "pad_token": "<pad>",
    "sep_token": "</s>",
    "tokenizer_class": "RobertaTokenizer",
    "trim_offsets": true,
    "unk_token": "<unk>",
    "name_or_path": "roberta-base"
}