grigio@alien.topB to LocalLLaMAEnglish · 2 years agoIs Open LLM Leaderboard reliable source ? yi:34B is at the top but I get better results with neural-chat:7B modelmessage-squaremessage-square23linkfedilinkarrow-up11arrow-down10file-text
arrow-up11arrow-down1message-squareIs Open LLM Leaderboard reliable source ? yi:34B is at the top but I get better results with neural-chat:7B modelgrigio@alien.topB to LocalLLaMAEnglish · 2 years agomessage-square23linkfedilinkfile-text
minus-squarebacocololo@alien.topBlinkfedilinkEnglisharrow-up1·2 years agoTo stop any repetition. you could try to add a stop token in model as ‘### Human’ it works well for me
minus-squareTeamPupNSudz@alien.topBlinkfedilinkEnglisharrow-up1·2 years agoCapybara doesn’t use Alpaca format, so that wouldn’t do anything. Regardless, it’s not that type of repetition. It’s not speaking for the user, it’s literally just copy/pasting part of the conversation into the answer.
To stop any repetition. you could try to add a stop token in model as ‘### Human’ it works well for me
Capybara doesn’t use Alpaca format, so that wouldn’t do anything. Regardless, it’s not that type of repetition. It’s not speaking for the user, it’s literally just copy/pasting part of the conversation into the answer.