Add multi-scale feature support to all backbone packages

Description

Dense prediction tasks such as semantic segmentation and object detection need normalized intermediate feature maps from multiple backbone layers or stages. Multi-scale features can also be useful during pretraining and distillation, for example to define objectives or transfer representations at more than one level of the network, e.g. wanted in #628 .

LightlyTrain already defines a public interface for this:

• ForwardMultiScaleFeatures, MultiScaleFeatureDims, and MultiScaleFeatureStrides
• MultiScaleFeatureViT and MultiScaleFeatureCNN
• MultiScaleFeaturePackage

DINOv2 and DINOv3 provide reference implementations:

• DINOv2 ViT wrapper
• DINOv3 ViT wrapper
• DINOv3 ConvNeXt wrapper

We would like to extend this interface to the remaining model packages, starting with TIMM. The current TIMMModelWrapper already uses TIMM's forward_intermediates where available, which should provide a useful starting point.

EdgeCrafter is partially supported: ECViTModelWrapper.forward() already returns a three-level feature pyramid, but its wrapper and package do not yet implement the public multi-scale protocols.

Contributions can address one package at a time; there is no need to implement the whole checklist in a single PR. If you would like to work on one, please leave a comment so work is not duplicated.

Expected behavior

For each package:

• Make the package implement MultiScaleFeaturePackage.
• Make its wrapper implement forward_multiscale_features() and the applicable metadata methods.
• Return normalized NCHW feature tensors in the same order as the requested layer or stage indices.
• Expose correct feature dimensions and, depending on the architecture, patch size or feature strides.
• Fail with a clear error for models that cannot expose intermediate features instead of returning incorrect results.
• Add tests for metadata, output ordering and shapes, invalid indices, and consistency with forward_features() for the final layer or stage.

Package-specific implementations do not have to support every upstream architecture immediately. Clearly documented and tested support for a useful subset is welcome, provided unsupported models are handled explicitly.

Package checklist

• DINOv2
• DINOv3
• TIMM — first implementation target
• EdgeCrafter — adapt the existing feature pyramid to the public interface
• Torchvision
• Ultralytics
• SuperGradients
• RF-DETR

Custom model wrappers are not included in this checklist because they are user-defined, but they can implement the same protocols.

Start with src/lightly_train/_models/timm/timm.py and the multi-scale protocols in src/lightly_train/_models/model_wrapper.py and src/lightly_train/_models/package.py. Use TIMM's existing forward_intermediates support as the entry point, then add tests for metadata, ordering, shapes, invalid indices, and final-layer consistency. Done means a documented, tested TIMM subset implements the public package and wrapper protocols and rejects unsupported models clearly.