{
  "model_cfg": {
    "embed_dim": 512,
    "vision_cfg": {
      "timm_model_name": "vit_base_mci_224",
      "timm_model_pretrained": false,
      "timm_pool": "token",
      "timm_proj": null,
      "timm_drop": 0.0,
      "timm_drop_path": 0.0,
      "image_size": 224
    },
    "text_cfg": {
      "context_length": 77,
      "vocab_size": 49408,
      "width": 512,
      "heads": 8,
      "layers": 12,
      "no_causal_mask": false
    },
    "custom_text": true
  },
  "preprocess_cfg": {
    "mean": [
      0.0,
      0.0,
      0.0
    ],
    "std": [
      1.0,
      1.0,
      1.0
    ],
    "interpolation": "bilinear",
    "resize_mode": "shortest"
  }
}