{ "architectures": [ "ConvNextV2ForImageClassification" ], "depths": [ 2, 2, 3, 2 ], "drop_path_rate": 0.0, "hidden_act": "gelu", "hidden_sizes": [ 10, 20, 30, 40 ], "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2", "3": "LABEL_3", "4": "LABEL_4", "5": "LABEL_5", "6": "LABEL_6", "7": "LABEL_7", "8": "LABEL_8", "9": "LABEL_9" }, "image_size": 224, "initializer_range": 0.02, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2, "LABEL_3": 3, "LABEL_4": 4, "LABEL_5": 5, "LABEL_6": 6, "LABEL_7": 7, "LABEL_8": 8, "LABEL_9": 9 }, "layer_norm_eps": 1e-12, "model_type": "convnextv2", "num_channels": 3, "num_stages": 4, "out_features": [ "stage2", "stage3", "stage4" ], "patch_size": 4, "stage_names": [ "stem", "stage1", "stage2", "stage3", "stage4" ], "torch_dtype": "float32", "transformers_version": "4.28.0.dev0" }