{
    "embed_dim": 512,
    "image_resolution": 224,
    "vision_layers": [
        3,
        4,
        23,
        3
    ],
    "vision_width": 64,
    "vision_patch_size": null,
    "context_length": 77,
    "vocab_size": 49408,
    "transformer_width": 512,
    "transformer_heads": 8,
    "transformer_layers": 12
}