{
  "model_cfg": {
    "embed_dim": 640,
    "vision_cfg": {
      "timm_model_name": "convnext_base",
      "timm_model_pretrained": false,
      "timm_pool": "",
      "timm_proj": "linear",
      "timm_drop": 0.0,
      "timm_drop_path": 0.1,
      "image_size": 256
    },
    "text_cfg": {
      "context_length": 77,
      "vocab_size": 49408,
      "width": 640,
      "heads": 10,
      "layers": 12
    }
  },
  "preprocess_cfg": {
    "mean": [
      0.48145466,
      0.4578275,
      0.40821073
    ],
    "std": [
      0.26862954,
      0.26130258,
      0.27577711
    ]
  }
}