view article Article Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective 5 days ago β’ 42
Running on CPU Upgrade Featured 2.95k The Smol Training Playbook π 2.95k The secrets to building world-class LLMs
π¨βπ³Cooking with HF: HPO with Transformers and Optuna Collection My HF recipe space and model. β’ 2 items β’ Updated Dec 10, 2025