| { | |
| "architectures": ["ViTModel"], | |
| "model_type": "vit", | |
| "num_channels": 1, | |
| "image_size": 224, | |
| "patch_size": 16, | |
| "hidden_size": 384, | |
| "num_hidden_layers": 12, | |
| "num_attention_heads": 6, | |
| "intermediate_size": 1536, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "attention_probs_dropout_prob": 0.0, | |
| "initializer_range": 0.02, | |
| "layer_norm_eps": 1e-6, | |
| "qkv_bias": true, | |
| "encoder_stride": 16 | |
| } |