{
  "attention_probs_dropout_prob": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "max_position_embeddings": 512,
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "type_vocab_size": 2,
  "vocab_size": 30522,
  "v_feature_size": 2048,
  "v_target_size": 1601,
  "v_hidden_size": 1024,
  "v_num_hidden_layers": 6,
  "v_num_attention_heads": 8,
  "v_intermediate_size": 1024,
  "bi_hidden_size": 1024,
  "bi_num_attention_heads": 8,
  "bi_intermediate_size": 1024,
  "bi_attention_type": 1,
  "v_attention_probs_dropout_prob": 0.1,
  "v_hidden_act": "gelu",
  "v_hidden_dropout_prob": 0.1,
  "v_initializer_range": 0.02,
  "pooling_method": "mul",
  "v_biattention_id": [0, 1, 2, 3, 4, 5],
  "t_biattention_id": [6, 7, 8, 9, 10, 11],
  "gnn_act": "gelu",
  "num_v_gnn_layers": 2,
  "num_q_gnn_layers": 2,
  "num_h_gnn_layers": 2,
  "num_gnn_attention_heads": 4,
  "gnn_dropout_prob": 0.1,
  "v_gnn_edge_dim": 12,
  "q_gnn_edge_dim": 48,
  "v_gnn_ids": [0, 1, 2, 3, 4, 5],
  "t_gnn_ids": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
}