{
  "architectures": [
    "DistilBertForMaskedLM"
  ],
  "activation": "gelu",
  "attention_dropout": 0.1,
  "dim": 768,
  "dropout": 0.1,
  "finetuning_task": null,
  "hidden_dim": 3072,
  "initializer_range": 0.02,
  "is_decoder": false,
  "max_position_embeddings": 512,
  "n_heads": 12,
  "n_layers": 3,
  "num_labels": 2,
  "output_attentions": false,
  "output_hidden_states": false,
  "output_past": true,
  "pruned_heads": {},
  "qa_dropout": 0.1,
  "seq_classif_dropout": 0.2,
  "sinusoidal_pos_embds": false,
  "tie_weights_": true,
  "torchscript": false,
  "use_bfloat16": false,
  "vocab_size": 8002
}