Running Featured 87 QED-Nano: Teaching a Tiny Model to Prove Hard Theorems 📝 87 Who needs 1T parameters? Olympiad proofs with a 4B model
Running on CPU Upgrade Featured 3.4k The Smol Training Playbook 📚 3.4k The secrets to building world-class LLMs
Running 4.14k The Ultra-Scale Playbook 🌌 4.14k The ultimate guide to training LLM on large GPU Clusters
Running 301 The ultimate guide to multi-harness RL 🔀 301 Train open models with RL inside real agent harnesses
Running Featured 99 Flow Matching for Image Generation 🌊 99 Visualize how noise transforms into images in your browser
view article Article Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv sergiopaniego • Aug 5 • 32
Running Featured 72 How to turn a game into an RL environment 🌍 72 From an idea to a trained 4B, with the dead ends left in