tokenizer_config.json

{
    "src_lang": null,
    "tgt_lang": null,
    "bos_token": "<s>",
    "eos_token": "</s>",
    "sep_token": "</s>",
    "unk_token": "<unk>",
    "pad_token": "<pad>",
    "model_max_length": 256,
    "name_or_path": "naist-nlp/mitre_466m",
    "tokenizer_class": "MitreTokenizer",
    "auto_map": {
        "AutoTokenizer": ["tokenization_mitre.MitreTokenizer"]
    }
}