{
    "text_encoder": {
        "model_type": "bert",
        "dim": 384,
        "context_dim": 768,
        "vocab_size": 250037,
        "padding_idx": 1,
        "num_layers": 12,
        "num_heads": 12,
        "embedding_dim": 256,
        "multimodal_layers_ids": [8, 9, 10, 11],
        "head_one_neuron": false,
        "pooling": "mean",
        "max_position_embeddings": 50,
        "dropout_prob": 0.1
    },
    "image_encoder": {
        "dim": 768,
        "patch_size": 16,
        "image_size": 224,
        "num_layers": 12,
        "num_heads": 12,
        "embedding_dim": 256,
        "pooling": "cls"
    }
}