{ "architectures": [ "BertModel" ], "attention_probs_dropout_prob": 0.1, "directionality": "bidi", "drop_worst_after": 0, "drop_worst_ratio": 0, "finetuning_task": "image_captioning", "freeze_embedding": true, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "img_feature_dim": 2054, "img_feature_type": "frcnn", "initializer_range": 0.02, "intermediate_size": 3072, "label_smoothing": 0, "layer_norm_eps": 1e-12, "loss_type": "sfmx", "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 12, "num_hidden_layers": 12, "num_labels": 2, "output_attentions": false, "output_hidden_states": false, "pooler_fc_size": 768, "pooler_num_attention_heads": 12, "pooler_num_fc_layers": 3, "pooler_size_per_head": 128, "pooler_type": "first_token_transform", "tie_weights": true, "torchscript": false, "type_vocab_size": 2, "vocab_size": 50000 }