{
  "attention_probs_dropout_prob": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 2048,
  "num_attention_heads": 8,
  "num_hidden_layers": 12,
  "type_vocab_size": 2,
  "vocab_size": 49408,
  "num_decoder_layers": 3,
  "max_target_embeddings": 77
}