| { | |
| "architectures": [ | |
| "ViTForImageClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "encoder_stride": 16, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "anger", | |
| "1": "surprise", | |
| "2": "contempt", | |
| "3": "happy", | |
| "4": "neutral", | |
| "5": "fear", | |
| "6": "sad", | |
| "7": "disgust" | |
| }, | |
| "image_size": 224, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "anger": 0, | |
| "contempt": 2, | |
| "disgust": 7, | |
| "fear": 5, | |
| "happy": 3, | |
| "neutral": 4, | |
| "sad": 6, | |
| "surprise": 1 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "model_type": "vit", | |
| "num_attention_heads": 12, | |
| "num_channels": 3, | |
| "num_hidden_layers": 12, | |
| "patch_size": 16, | |
| "pooler_act": "tanh", | |
| "pooler_output_size": 768, | |
| "qkv_bias": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.50.3" | |
| } | |