{ "_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": "blues", "1": "classical", "2": "country", "3": "disco", "4": "hiphop", "5": "metal", "6": "pop", "7": "reggae", "8": "rock" }, "image_size": 224, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "blues": "0", "classical": "1", "country": "2", "disco": "3", "hiphop": "4", "metal": "5", "pop": "6", "reggae": "7", "rock": "8" }, "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": "4.38.2" }