Feature request: Add Contrastive Representation Distillation (CRD)

Requesting a built-in **Contrastive Representation Distillation (CRD)** strategy (Tian et al., 2019) for `tunix.distillation.DistillationTrainer`.

## What CRD does
Distills at the **representation level** using an InfoNCE/contrastive loss:
- positive pair: (student rep, teacher rep) from the **same sample**
- negatives: mismatched pairs (e.g., in-batch negatives)

Minimal form:
- `logits = (z_s @ z_t.T) / tau`
- `labels = arange(B)`
- `loss = CE(logits, labels)` (optional symmetric term on `logits.T`)

## Why this helps
- Complements / improves over logit-KD in many setups

## Reference
Tian et al., *Contrastive Representation Distillation*, arXiv:1910.10699 (2019): https://arxiv.org/pdf/1910.10699

I can contribute a PR + tests if you’re open to it.