kf_config.json

{
  "library_name": "kerasformers",
  "kerasformers_version": "1.2.1",
  "model_module": "kerasformers.models.owlvit",
  "model_class": "OwlViTDetect",
  "variant": "owlvit-base-patch16",
  "weights": "model.weights.h5",
  "schema_version": 2,
  "weight_dtype": "float32",
  "model_type": "owlvit",
  "text_config": {
    "hidden_dim": 512,
    "intermediate_size": 2048,
    "num_heads": 8,
    "num_layers": 12,
    "max_position_embeddings": 16,
    "vocab_size": 49408
  },
  "vision_config": {
    "image_size": 768,
    "patch_size": 16,
    "hidden_dim": 768,
    "intermediate_size": 3072,
    "num_layers": 12,
    "num_heads": 12
  },
  "projection_dim": 512,
  "image_size": null
}