Running 92 Unlocking On-Policy Distillation for Any Model Family 📝 92 Visualize on-policy distillation for any model family
Running Featured 1.32k FineWeb: decanting the web for the finest text data at scale 🍷 1.32k Read a detailed overview of the FineWeb web‑scale text dataset
Running on CPU Upgrade Featured 3.07k The Smol Training Playbook 📚 3.07k The secrets to building world-class LLMs