Running 77 Unlocking On-Policy Distillation for Any Model Family ๐ 77 Improve model performance by transferring knowledge between different model families
Running 87 Scaling FineWeb to 1000+ languages: Step 1: finding signal in 100s of evaluation tasks ๐ 87 Evaluate multilingual models using FineTasks
Running on CPU Upgrade Featured 2.91k The Smol Training Playbook ๐ 2.91k The secrets to building world-class LLMs
Running 3.66k The Ultra-Scale Playbook ๐ 3.66k The ultimate guide to training LLM on large GPU Clusters