Running Featured 93 Distilling 100B+ Models 40x Faster with TRL 📝 93 TRL distillation for 100B+ teachers, 40x faster
moonshine-ai/moonshine-tiny-vi Automatic Speech Recognition • 27.1M • Updated Sep 3, 2025 • 2.11k • 3
nvidia/Nemotron-Research-Reasoning-Qwen-1.5B Text Generation • 2B • Updated Nov 21, 2025 • 1.63k • 244