Running 8 Why Adaptive Optimizers Exist — a Tangible lesson. 🏔 8 Why momentum/AdamW can outperform SGD — a Tangible lesson.
Running Featured 84 QED-Nano: Teaching a Tiny Model to Prove Hard Theorems 📝 84 Who needs 1T parameters? Olympiad proofs with a 4B model
Running Agents Reachy 179 Baby Reachy-Mini Companion 🤖 179 A fully local Reachy Mini AI Companion for babies and kids.
Running on CPU Upgrade Featured 3.29k The Smol Training Playbook 📚 3.29k The secrets to building world-class LLMs
Running on CPU Spr Agents 5 Fast quantized SmolVLM2 ⚡ 5 Generate text descriptions from images and videos