Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing Paper • 2509.08721 • Published Sep 10 • 660
RL Swarm Collection RL Swarm is an open source system for peer-to-peer gossip-based reinforcement learning over the internet. • 5 items • Updated Apr 30 • 7
ubiqland/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-amphibious_stinky_clam Text Generation • Updated Apr 8 • 12
ubiqland/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-amphibious_stinky_clam Text Generation • Updated Apr 8 • 12