{
  "architecture": "two linear projection heads (img, txt) -> L2-normalised shared space",
  "image_encoder": "google/siglip-base-patch16-224",
  "text_encoder": "Modularcomputing/Native-Bird",
  "text_encoder_frozen": true,
  "d_img": 768,
  "d_txt": 768,
  "proj_dim": 512,
  "proj_hidden": 0,
  "logit_scale_log": 2.903928756713867,
  "logit_scale": 18.24568748474121,
  "best_epoch": 3,
  "max_text_len": 64,
  "text_prompt": "",
  "weights": {
    "img.net.weight": "[proj_dim, d_img]",
    "img.net.bias": "[proj_dim]",
    "txt.net.weight": "[proj_dim, d_txt]",
    "txt.net.bias": "[proj_dim]",
    "logit_scale": "scalar, log space"
  }
}