config.json

{
  "model_type": "tryon-safety-classifier",
  "version": "1.0.0",
  "base_model": "timm/ViT-SO400M-16-SigLIP2-384",
  "open_clip_name": "hf-hub:timm/ViT-SO400M-16-SigLIP2-384",
  "image_size": 384,
  "default_variant": "finetuned",
  "variants": {
    "finetuned": {
      "subfolder": null,
      "description": "SigLIP 2 vision tower fine-tuned (last 6 blocks) with four linear heads. Product score = mean of per-photo probabilities.",
      "embedding_scale": 10.0,
      "aggregation": "mean_of_photo_probabilities",
      "adult_threshold": 0.3
    },
    "frozen": {
      "subfolder": "frozen",
      "description": "Original SigLIP 2 vision tower with four linear heads on concat(mean, max) of L2-normalised photo embeddings.",
      "aggregation": "concat_mean_max_embeddings",
      "adult_threshold": 0.3
    }
  },
  "heads": {
    "safety": ["ok", "revealing", "lingerie", "adult"],
    "subject": ["human_clothing", "pet", "not_clothing"],
    "swim": ["not_swimwear", "regular", "near_micro", "micro"],
    "rave": ["no", "yes"]
  }
}