open_clip_config.json

{
    "model_cfg": {
      "embed_dim": 512,
      "vision_cfg": {
        "image_size": 224,
        "layers": 12,
        "width": 768,
        "patch_size": 16
      },
      "text_cfg": {
        "context_length": 77,
        "vocab_size": 49408,
        "width": 512,
        "heads": 8,
        "layers": 12
      }
    },
    "preprocess_cfg": {
      "mean": [
        0.48145466,
        0.4578275,
        0.40821073
      ],
      "std": [
        0.26862954,
        0.26130258,
        0.27577711
      ]
    }
  }