config.json

{"text_encoder": {"model_type": "bert", "dim": 512, "context_dim": 1024, "vocab_size": 30522, "padding_idx": 0, "num_layers": 12, "num_heads": 8, "embedding_dim": 768, "multimodal_layers_ids": [6, 7, 8, 9, 10, 11], "head_one_neuron": false, "pooling": "cls", "max_position_embeddings": 64, "dropout_prob": 0.1}, "image_encoder": {"dim": 1024, "patch_size": 14, "image_size": 224, "num_layers": 24, "num_heads": 16, "embedding_dim": 768, "pooling": "cls", "num_reg_tokens": 4}}