configs/architecture_config.json

{
  "architecture": "NeoAraBERTTypePredictor",
  "task": "mention-level 21-class Arabic entity typing",
  "base_model": "U4RASD/NeoAraBERT",
  "input_markers": [
    "[ENT]",
    "[/ENT]"
  ],
  "representation": "last hidden state at token position 0 (CLS)",
  "dropout": 0.1,
  "classifier": [
    768,
    21
  ],
  "loss": "ordinary unweighted multiclass cross-entropy",
  "num_labels": 21,
  "labels": [
    "GPE",
    "ORG",
    "DATE",
    "PERS",
    "NORP",
    "ORDINAL",
    "OCC",
    "EVENT",
    "CARDINAL",
    "LOC",
    "WEBSITE",
    "FAC",
    "LAW",
    "TIME",
    "MONEY",
    "CURR",
    "LANGUAGE",
    "PERCENT",
    "PRODUCT",
    "QUANTITY",
    "UNIT"
  ],
  "tokenizer_size": 65002,
  "hidden_size": 768,
  "max_length": 512,
  "context_candidates": [
    null,
    500,
    300,
    150,
    80,
    30,
    0
  ]
}