{ "architectures": [ "ViTForImageClassification" ], "attention_probs_dropout_prob": 0.0, "encoder_stride": 16, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "hidden_size": 1024, "id2label": { "0": "Crescente_AZAN", "1": "Crescente_HE", "2": "Crescente_PAMS", "3": "Crescente_PAS", "4": "Crescente_PICRO", "5": "Normal_AZAN", "6": "Normal_HE", "7": "Normal_PAMS", "8": "Normal_PAS", "9": "Normal_PICRO" }, "image_size": 224, "initializer_range": 0.02, "intermediate_size": 4096, "label2id": { "Crescente_AZAN": 0, "Crescente_HE": 1, "Crescente_PAMS": 2, "Crescente_PAS": 3, "Crescente_PICRO": 4, "Normal_AZAN": 5, "Normal_HE": 6, "Normal_PAMS": 7, "Normal_PAS": 8, "Normal_PICRO": 9 }, "layer_norm_eps": 1e-12, "model_type": "vit", "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 24, "patch_size": 16, "pooler_act": "tanh", "pooler_output_size": 1024, "problem_type": "single_label_classification", "qkv_bias": true, "torch_dtype": "float32", "transformers_version": "4.53.1" }