{
  "architectures": [
    "Blip2VisionModel"
  ],
  "attention_dropout": 0.0,
  "dropout": 0.0,
  "hidden_act": "gelu",
  "hidden_size": 1408,
  "image_size": 224,
  "initializer_factor": 1.0,
  "initializer_range": 1e-10,
  "intermediate_size": 6144,
  "layer_norm_eps": 1e-06,
  "model_type": "blip_2_vision_model",
  "num_attention_heads": 16,
  "num_channels": 3,
  "num_hidden_layers": 39,
  "patch_size": 14,
  "projection_dim": 512,
  "qkv_bias": true,
  "torch_dtype": "float32",
  "transformers_version": "4.34.1"
}