| { | |
| "_name_or_path": "aesthetic", | |
| "architectures": [ | |
| "ViTForImageClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "encoder_stride": 16, | |
| "hidden_act": "gelu_new", | |
| "hidden_dropout_prob": 0.15, | |
| "hidden_size": 1536, | |
| "id2label": { | |
| "0": "hight", | |
| "1": "low" | |
| }, | |
| "image_size": 1024, | |
| "initializer_range": 0.15, | |
| "intermediate_size": 4192, | |
| "label2id": { | |
| "hight": "0", | |
| "low": "1" | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "model_type": "vit", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 48, | |
| "patch_size": 64, | |
| "problem_type": "single_label_classification", | |
| "qkv_bias": true, | |
| "transformers_version": "4.36.2" | |
| } | |