Running 15 Distilling 100B+ Models 40x Faster with TRL 📝 15 TRL distillation for 100B+ teachers, 40x faster
view article Article Waypoint-1.5: Higher-Fidelity Interactive Worlds for Everyday GPUs +3 4 days ago • 20
view article Article Multimodal Embedding & Reranker Models with Sentence Transformers 4 days ago • 36
view article Article TRL v1.0: Post-Training Library Built to Move with the Field +2 13 days ago • 47