{ "architectures": [ "LevitForImageClassification" ], "attention_ratio": [ 2, 2, 2 ], "depths": [ 4, 4, 4 ], "down_ops": [ [ "Subsample", 32, 8, 4, 2, 2 ], [ "Subsample", 32, 12, 4, 2, 2 ], [ "" ], [ "" ] ], "drop_path_rate": 0, "dtype": "float32", "hidden_sizes": [ 256, 384, 512 ], "id2label": { "0": "eyelid", "1": "normal" }, "image_size": 224, "initializer_range": 0.02, "kernel_size": 3, "key_dim": [ 32, 32, 32 ], "label2id": { "eyelid": 0, "normal": 1 }, "mlp_ratio": [ 2, 2, 2 ], "model_type": "levit", "num_attention_heads": [ 4, 6, 8 ], "num_channels": 3, "padding": 1, "patch_size": 16, "problem_type": "single_label_classification", "stride": 2, "transformers_version": "5.22.1", "use_cache": false }