{ "_name_or_path": "google/vit-base-patch16-224-in21k", "architectures": [ "ViTForImageClassification" ], "attention_probs_dropout_prob": 0.0, "encoder_stride": 16, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "hidden_size": 768, "id2label": { "0": "Bread", "1": "Dairy product", "10": "Vegetable-Fruit", "2": "Dessert", "3": "Egg", "4": "Fried food", "5": "Meat", "6": "Noodles-Pasta", "7": "Rice", "8": "Seafood", "9": "Soup" }, "image_size": 224, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "Bread": "0", "Dairy product": "1", "Dessert": "2", "Egg": "3", "Fried food": "4", "Meat": "5", "Noodles-Pasta": "6", "Rice": "7", "Seafood": "8", "Soup": "9", "Vegetable-Fruit": "10" }, "layer_norm_eps": 1e-12, "model_type": "vit", "num_attention_heads": 12, "num_channels": 3, "num_hidden_layers": 12, "patch_size": 16, "problem_type": "single_label_classification", "qkv_bias": true, "torch_dtype": "float32", "transformers_version": "4.41.2" }