{
  "model_cfg": {
    "embed_dim": 768,
    "vision_cfg": {
      "width": 768,
      "layers": 12,
      "patch_size": 1,
      "image_size": 16,
      "no_ln_pre": true,
      "pool_type": "avg",
      "final_ln_after_pool": true,
      "norm_kwargs": {
        "eps": 1e-06
      },
      "output_tokens": true,
      "head_width": 64,
      "in_channels": 1024
    },
    "text_cfg": {
      "context_length": 77,
      "vocab_size": 49408,
      "width": 512,
      "heads": 8,
      "layers": 12
    }
  }
}