{
    "model_cfg": {
        "embed_dim": 1024,
        "vision_cfg": {
            "image_size": 224,
            "layers": 40,
            "width": 1408,
            "head_width": 88,
            "mlp_ratio": 4.3637,
            "patch_size": 14
        },
        "text_cfg": {
            "context_length": 77,
            "vocab_size": 49408,
            "width": 1024,
            "heads": 16,
            "layers": 24
        }
    },
    "preprocess_cfg": {
        "mean": [
            0.48145466,
            0.4578275,
            0.40821073
        ],
        "std": [
            0.26862954,
            0.26130258,
            0.27577711
        ]
    }
}