Running Featured 35 Distilling 100B+ Models 40x Faster with TRL 📝 35 TRL distillation for 100B+ teachers, 40x faster
Running on CPU Upgrade 219 The Synthetic Data Playbook: Generating Trillions of the Finest Tokens 📝 219 Explore synthetic data experiments on a virtual bookshelf
Running 16 The Jagged AI Frontier is a Data Frontier 🧭 16 Why AI capabilities are shaped by data availability
Running on CPU Upgrade Featured 3.1k The Smol Training Playbook 📚 3.1k The secrets to building world-class LLMs
Running 94 Unlocking On-Policy Distillation for Any Model Family 📝 94 Visualize on-policy distillation for any model family