Running on CPU Upgrade 877 877 The Smol Training Playbook: The Secrets to Building World-Class LLMs 📝
Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning Paper • 2510.25992 • Published 4 days ago • 27
moonshotai/Kimi-Linear-48B-A3B-Instruct Text Generation • 49B • Updated about 24 hours ago • 9.06k • 288