{ "architectures": [ "ConvNextForImageClassification" ], "depths": [ 3, 3, 27, 3 ], "drop_path_rate": 0.0, "dtype": "float32", "hidden_act": "gelu", "hidden_sizes": [ 128, 256, 512, 1024 ], "id2label": { "0": "0", "1": "1", "2": "2", "3": "3", "4": "4", "5": "5", "6": "6", "7": "7", "8": "8", "9": "9" }, "image_size": 224, "initializer_range": 0.02, "label2id": { "0": 0, "1": 1, "2": 2, "3": 3, "4": 4, "5": 5, "6": 6, "7": 7, "8": 8, "9": 9 }, "layer_norm_eps": 1e-12, "layer_scale_init_value": 1e-06, "model_type": "convnext", "num_channels": 3, "num_stages": 4, "out_features": [ "stage4" ], "out_indices": [ 4 ], "patch_size": 4, "stage_names": [ "stem", "stage1", "stage2", "stage3", "stage4" ], "transformers_version": "4.57.3" }