view article Article Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries +7 3 days ago • 32
Running Featured 65 QED-Nano: Teaching a Tiny Model to Prove Hard Theorems 📝 65 Who needs 1T parameters? Olympiad proofs with a 4B model
edbeeching/fixed-Qwen3-30B-A3B-Thinking-2507-SFT-v03.01-step-000000062 Text Generation • 31B • Updated Jan 23 • 3
edbeeching/fixed-Qwen3-30B-A3B-Thinking-2507-SFT-v03.01-step-000000062 Text Generation • 31B • Updated Jan 23 • 3