minus-squarebacocololoBtoLocalLLaMA@poweruser.forum•Is Open LLM Leaderboard reliable source ? yi:34B is at the top but I get better results with neural-chat:7B modellinkfedilinkEnglisharrow-up1·1 year agoTo stop any repetition. you could try to add a stop token in model as ‘### Human’ it works well for me linkfedilink
bacocololoB to LocalLLaMA@poweruser.forumEnglish · 1 year agoThree Laws for Large Language Models: An Ethical Frameworkplus-squaremessage-squaremessage-square4fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareThree Laws for Large Language Models: An Ethical Frameworkplus-squarebacocololoB to LocalLLaMA@poweruser.forumEnglish · 1 year agomessage-square4fedilink
To stop any repetition. you could try to add a stop token in model as ‘### Human’ it works well for me