| { | |
| "architectures": [ | |
| "ViTForImageClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.2, | |
| "dtype": "float32", | |
| "encoder_stride": 16, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.2, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "sad", | |
| "1": "angry", | |
| "2": "relaxed", | |
| "3": "happy" | |
| }, | |
| "image_size": 224, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "angry": "1", | |
| "happy": "3", | |
| "relaxed": "2", | |
| "sad": "0" | |
| }, | |
| "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, | |
| "transformers_version": "4.57.1" | |
| } | |