VIT Adapter

Hello, I propose adding ViT adapter option in `TimmUniversalEncoder` for ViTs that does not have multi-scale features, so that SMP can now support a whole new set of backbones. The following links can be used as a reference/starting point. [DINOv3_Adapter](https://github.com/facebookresearch/dinov3/blob/main/dinov3/eval/segmentation/models/backbone/dinov3_adapter.py) [DINOv2_Adapter](https://github.com/facebookresearch/dinov2/blob/main/dinov2/eval/segmentation_m2f/models/backbones/vit_adapter.py) [Original VIT Adapter Repo](https://github.com/czczup/ViT-Adapter) [AdaptersHub](https://github.com/adapter-hub/adapters) [Adapters HF Version](https://huggingface.co/docs/hub/en/adapters) Or perhaps these type of adapters might actually better be on `timm`? @rwightman @qubvel