{ "pat_str": "'s|'t|'re|'ve|'m|'ll|'d| ?[\\p{L}]+| ?[\\p{N}]+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)|\\s+", "tokenizer_class": "OBITokenizer", "auto_map": { "AutoTokenizer": [ "tokenizeConfig.OBITokenizer", null ] }, "vocab_size": 600 }