| {"tokenizer_file": "custom_tokenizer.json", "model_type": "bpe", "normalizer": {"type": "Sequence", "normalizers": [{"type": "NFD"}, {"type": "Lowercase"}, {"type": "StripAccents"}]}, "pre_tokenizer": {"type": "Sequence", "pre_tokenizers": [{"type": "Whitespace"}, {"type": "Punctuation"}, {"type": "Digits", "individual_digits": "false"}]}, "do_lower_case": "true"} |