{
  "architectures": [
    "CLIPVisionModelWithProjection"
  ],
  "attention_dropout": 0.0,
  "dropout": 0.0,
  "dtype": "float32",
  "hidden_act": "quick_gelu",
  "hidden_size": 768,
  "image_size": 224,
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-05,
  "model_type": "clip_vision_model",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "paddlenlp_version": null,
  "patch_size": 32,
  "projection_dim": 512,
  "return_dict": true,
  "torch_dtype": null,
  "torchscript": false,
  "transformers_version": "4.16.0.dev0",
  "use_bfloat16": false
}