{
  "model_type": "clip_vision_model",
  "architectures": ["CLIPVisionModel"],
  "hidden_size": 768,
  "intermediate_size": 3072,
  "num_hidden_layers": 12,
  "num_attention_heads": 12,
  "image_size": 224,
  "patch_size": 16,
  "num_channels": 3,
  "hidden_act": "gelu",
  "layer_norm_eps": 1e-12,
  "dropout": 0.0,
  "attention_dropout": 0.0,
  "initializer_range": 0.02,
  "initializer_factor": 1.0
}