🚨 One model, high correctness:
With low-threshold tuning, we take Llama3-70B from:
➡️ 51% → 87% correctness
➡️ Retaining 53% of the original completeness
Tim Franzmeyer
@timlive.bsky.social
27 followers 54 following 6 posts
Machine Learning PhD student @UniofOxford interested in reinforcement learning, multi-agent systems, and LLMs. Previously @GoogleDeepMind, @MetaAI and @ETH.
