{ "_name_or_path": "google/vit-base-patch16-224", "_num_labels": 6, "architectures": [ "ViTForImageClassification" ], "attention_probs_dropout_prob": 0.0, "encoder_stride": 16, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "hidden_size": 768, "id2label": { "0": "action", "1": "frameset", "2": "geometry", "3": "placeholder", "4": "studio-other", "5": "studio-side" }, "image_size": 224, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "action": 0, "frameset": 1, "geometry": 2, "placeholder": 3, "studio-other": 4, "studio-side": 5 }, "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": "4.36.1" }