view article Article We Got Claude to Build CUDA Kernels and teach open models! +2 10 days ago β’ 123
view article Article Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective 11 days ago β’ 48
VERL QA Datasets Collection High-quality QA generation datasets in VERL format: document QA, table reasoning, and multi-hop reasoning tasks. β’ 7 items β’ Updated 30 days ago
Running Featured 1.28k FineWeb: decanting the web for the finest text data at scale π· 1.28k Generate high-quality text data for LLMs using FineWeb
Running 3.67k The Ultra-Scale Playbook π 3.67k The ultimate guide to training LLM on large GPU Clusters
Running on CPU Upgrade Featured 2.96k The Smol Training Playbook π 2.96k The secrets to building world-class LLMs