LughMA to FuturologyEnglish · 1 year agoStarling-7B, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF), says it's almost as powerful as GPT-4.starling.cs.berkeley.eduexternal-linkmessage-square0fedilinkarrow-up14arrow-down10
arrow-up14arrow-down1external-linkStarling-7B, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF), says it's almost as powerful as GPT-4.starling.cs.berkeley.eduLughMA to FuturologyEnglish · 1 year agomessage-square0fedilink
