{
  "_name_or_path": "deepset/gelectra-large",
  "architectures": [
    "ElectraForTokenClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "embedding_size": 1024,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 1024,
  "id2label": {
    "0": "B-LOC",
    "1": "B-ORG",
    "2": "B-OTH",
    "3": "B-PER",
    "4": "I-LOC",
    "5": "I-ORG",
    "6": "I-OTH",
    "7": "I-PER",
    "8": "O"
  },
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "label2id": {
    "B-LOC": "0",
    "B-ORG": "1",
    "B-OTH": "2",
    "B-PER": "3",
    "I-LOC": "4",
    "I-ORG": "5",
    "I-OTH": "6",
    "I-PER": "7",
    "O": "8"
  },
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "electra",
  "num_attention_heads": 16,
  "num_hidden_layers": 24,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "summary_activation": "gelu",
  "summary_last_dropout": 0.1,
  "summary_type": "first",
  "summary_use_proj": true,
  "transformers_version": "4.22.2",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 31102
}