Running 79 Unlocking On-Policy Distillation for Any Model Family π 79 Improve model performance by transferring knowledge between different model families
Running 3.67k The Ultra-Scale Playbook π 3.67k The ultimate guide to training LLM on large GPU Clusters
Running on CPU Upgrade 13.8k Open LLM Leaderboard π 13.8k Track, rank and evaluate open LLMs and chatbots