[FEAT] DEIMv2 implementation

Nobody has claimed this yet.

### 💡 Is your feature request related to a problem?

I would like to integrate DEIMv2 into lightly-train. DEIMv2 has 2 families of models,
**DINOv3** and **HGNetv2/LiteEncoder**, but I would suggest only DINOv3-based for now.

### 🧰 Describe the solution you'd like

A lot of code is already in place, though some will need divergence resolution.
**DEIMCriterion**(looks close, but differs from **DFINECriterion** with `mal_alpha=None`,
`use_uni_set=True` and loss `loss_mal` added) and **DEIMTransformer** will need to be added.

### 🛠 Alternatives you've considered

Not sure, if applicable

### 📝 Additional context
Some of code with divergence:
- when class LQE creates MLP, lightly just uses default "relu", while DEIM allows to create MLP with a different one.
- box_cxcywh_to_xyxy function in DEIM adds clamp(min=0.0) to width and height
- layer name converter will be required when loading checkpoints
- HybridEncoder:
- fusion of upsample_feat+feat_low and downsample_feat+feat_height in DEIMv2 can be via both sum and concatenation,
while Lighly always go for concatenation. And DEIMv2 pretrained models with sum
- DEIMv2 has larger encoder block variety covering RT-DETR, D-FINE and DEIM aggregation path.
- DEIMv2 uses 1x1 conv + depthwise spatial stride-2 conv for downsampling in both D-FINE and DEIM
- DEIMv2 does not always uses input projection and goes for nn.Identity when in_channels is equal to hidden_dim, which is the case for DINOv3
- DEIMv2 has additional parameters and imports in HungarianMatcher to accomodate late stage training, where it switches to class-score × IoU ranking objective.
- DEIMCriterion can inherit from DFINECriterion to add parameters and loss.

Start by reading the existing DFINECriterion, HybridEncoder, HungarianMatcher, LQE MLP, box_cxcywh_to_xyxy, and checkpoint layer-name conversion code. The work is done when the DINOv3-based DEIMv2 integration includes DEIMCriterion and DEIMTransformer and accounts for the listed model, loss, checkpoint, encoder, and matcher divergences.

Written by the indexing model from the issue text.