view article Article Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective 21 days ago • 55
VERL QA Datasets Collection High-quality QA generation datasets in VERL format: document QA, table reasoning, and multi-hop reasoning tasks. • 7 items • Updated Jan 8
Running Featured 1.29k FineWeb: decanting the web for the finest text data at scale 🍷 1.29k Explore the FineWeb dataset and its creation process
Running 3.69k The Ultra-Scale Playbook 🌌 3.69k The ultimate guide to training LLM on large GPU Clusters
Running on CPU Upgrade Featured 2.99k The Smol Training Playbook 📚 2.99k The secrets to building world-class LLMs