tokenizer_config.json

{
    "pretrained_model_name_or_path": "CamembertTokenizer",
    "bos_token": "<s>",
    "eos_token": "</s>",
    "unk_token": "<unk>",
    "sep_token": "</s>",
    "cls_token": "<s>",
    "pad_token": "<pad>",
    "mask_token": "<mask>",
    "additional_special_tokens": [
        "<s>NOTUSED",
        "</s>NOTUSED",
        "<th_roberta_space_token>"
    ]
}