label_config.json

{
  "task": "token_classification_ner",
  "scheme": "BIO",
  "labels": [
    "O",
    "B-Disease",
    "I-Disease",
    "B-GeneOrGeneProduct",
    "I-GeneOrGeneProduct",
    "B-Variant",
    "I-Variant"
  ],
  "label2id": {
    "O": 0,
    "B-Disease": 1,
    "I-Disease": 2,
    "B-GeneOrGeneProduct": 3,
    "I-GeneOrGeneProduct": 4,
    "B-Variant": 5,
    "I-Variant": 6
  },
  "id2label": {
    "0": "O",
    "1": "B-Disease",
    "2": "I-Disease",
    "3": "B-GeneOrGeneProduct",
    "4": "I-GeneOrGeneProduct",
    "5": "B-Variant",
    "6": "I-Variant"
  },
  "types": [
    "Disease",
    "GeneOrGeneProduct",
    "Variant"
  ],
  "ignore_index": -100,
  "label_policy": "gold (BioRED); Chemical/Species/CellLine folded to O",
  "alignment": "char spans -> subword tokens via tokenizer offset_mapping",
  "source": "BioRED",
  "type_map": {
    "Gene": "GeneOrGeneProduct",
    "Disease": "Disease",
    "Variant": "Variant"
  }
}