{
  "architectures": [
    "BertForMaskedLM"
  ],
  "model_type": "bert",
  "attention_probs_dropout_prob": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 2048,
  "max_position_embeddings": 512,
  "num_attention_heads": 8,
  "num_hidden_layers": 8,
  "type_vocab_size": 2,
  "vocab_size": 32768
}