{
  "model_cfg": {
    "embed_dim": 1152,
    "init_logit_bias": -10,
    "custom_text": true,
    "vision_cfg": {
      "image_size": 384,
      "timm_model_name": "vit_so400m_patch14_siglip_384",
      "timm_model_pretrained": false,
      "timm_pool": "map",
      "timm_proj": "none"
    },
    "text_cfg": {
      "context_length": 64,
      "vocab_size": 32000,
      "hf_tokenizer_name": "timm/ViT-B-16-SigLIP",
      "tokenizer_kwargs": {
        "clean": "canonicalize"
      },
      "width": 1152,
      "heads": 16,
      "layers": 27,
      "mlp_ratio": 3.7362,
      "no_causal_mask": true,
      "proj_bias": true,
      "pool_type": "last",
      "norm_kwargs": {
        "eps": 1e-06
      }
    }
  },
  "preprocess_cfg": {
    "mean": [
      0.48145466,
      0.4578275,
      0.40821073
    ],
    "std": [
      0.26862954,
      0.26130258,
      0.27577711
    ],
    "interpolation": "bicubic",
    "resize_mode": "shortest"
  }
}