{ "model_type": "vit", "architectures": [ "ViTForImageClassification" ], "image_size": 512, "patch_size": 16, "num_channels": 3, "hidden_size": 768, "num_attention_heads": 12, "num_hidden_layers": 12, "intermediate_size": 3072, "num_labels": 14, "task": "medical_imaging_classification" }