tokenizer_config.json

{
  "clean_up_tokenization_spaces": true,
  "cls_token": "[CLS]",
  "do_basic_tokenize": true,
  "do_lower_case": true,
  "id2label": {
    "0": "O",
    "1": "B-Title",
    "10": "B-Algorithm",
    "11": "B-Figure",
    "12": "B-Table",
    "13": "B-Caption",
    "14": "B-Header",
    "15": "B-Footer",
    "16": "B-Footnote",
    "17": "I-Title",
    "18": "I-Author",
    "19": "I-Abstract",
    "2": "B-Author",
    "20": "I-Keywords",
    "21": "I-Section",
    "22": "I-Paragraph",
    "23": "I-List",
    "24": "I-Bibliography",
    "25": "I-Equation",
    "26": "I-Algorithm",
    "27": "I-Figure",
    "28": "I-Table",
    "29": "I-Caption",
    "3": "B-Abstract",
    "30": "I-Header",
    "31": "I-Footer",
    "32": "I-Footnote",
    "4": "B-Keywords",
    "5": "B-Section",
    "6": "B-Paragraph",
    "7": "B-List",
    "8": "B-Bibliography",
    "9": "B-Equation"
  },
  "label2id": {
    "B-Abstract": 3,
    "B-Algorithm": 10,
    "B-Author": 2,
    "B-Bibliography": 8,
    "B-Caption": 13,
    "B-Equation": 9,
    "B-Figure": 11,
    "B-Footer": 15,
    "B-Footnote": 16,
    "B-Header": 14,
    "B-Keywords": 4,
    "B-List": 7,
    "B-Paragraph": 6,
    "B-Section": 5,
    "B-Table": 12,
    "B-Title": 1,
    "I-Abstract": 19,
    "I-Algorithm": 26,
    "I-Author": 18,
    "I-Bibliography": 24,
    "I-Caption": 29,
    "I-Equation": 25,
    "I-Figure": 27,
    "I-Footer": 31,
    "I-Footnote": 32,
    "I-Header": 30,
    "I-Keywords": 20,
    "I-List": 23,
    "I-Paragraph": 22,
    "I-Section": 21,
    "I-Table": 28,
    "I-Title": 17,
    "O": 0
  },
  "mask_token": "[MASK]",
  "model_max_length": 1000000000000000019884624838656,
  "never_split": null,
  "num_labels": 33,
  "pad_token": "[PAD]",
  "sep_token": "[SEP]",
  "strip_accents": null,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "BertTokenizer",
  "unk_token": "[UNK]"
}