{ "added_tokens_decoder": { "0": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "1": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "2": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "3": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "4": { "content": "[START_REF]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "5": { "content": "[END_REF]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "6": { "content": "[IMAGE]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "7": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "8": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "9": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "10": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "11": { "content": "[START_SUP]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "12": { "content": "[END_SUP]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "13": { "content": "[START_SUB]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "14": { "content": "[END_SUB]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "15": { "content": "[START_DNA]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "16": { "content": "[END_DNA]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "17": { "content": "[START_AMINO]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "18": { "content": "[END_AMINO]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "19": { "content": "[START_SMILES]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "20": { "content": "[END_SMILES]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "21": { "content": "[START_I_SMILES]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "22": { "content": "[END_I_SMILES]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50000": { "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "50001": { "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "50002": { "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "50003": { "content": "①", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50004": { "content": "②", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50005": { "content": "③", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50006": { "content": "④", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50007": { "content": "⑤", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50008": { "content": "⑥", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50009": { "content": "⑦", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50010": { "content": "⑧", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50011": { "content": "⑨", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50012": { "content": "⑩", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50013": { "content": "⑪", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50014": { "content": "⑫", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50015": { "content": "⑬", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50016": { "content": "⑭", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50017": { "content": "⑮", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50018": { "content": "⑯", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50019": { "content": "⑰", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50020": { "content": "⑱", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50021": { "content": "⑲", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50022": { "content": "⑳", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50023": { "content": "[newline]", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "50024": { "content": "[image]", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false } }, "additional_special_tokens": [ "①", "②", "③", "④", "⑤", "⑥", "⑦", "⑧", "⑨", "⑩", "⑪", "⑫", "⑬", "⑭", "⑮", "⑯", "⑰", "⑱", "⑲", "⑳" ], "bos_token": "", "clean_up_tokenization_spaces": false, "eos_token": "", "max_length": 4096, "model_max_length": 4096, "pad_to_multiple_of": null, "pad_token": "", "pad_token_type_id": 0, "padding_side": "right", "processor_class": "DonutProcessor", "stride": 0, "tokenizer_class": "NougatTokenizer", "truncation_side": "right", "truncation_strategy": "longest_first", "unk_token": "", "vocab_file": null }