If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs Paper • 2412.04144 • Published 20 days ago • 4
RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs Paper • 2407.02552 • Published Jul 2 • 4
Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning Paper • 2309.05444 • Published Sep 11, 2023 • 1
Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs Paper • 2402.14740 • Published Feb 22 • 11
Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning Paper • 2402.06619 • Published Feb 9 • 54