ninjasaid13@alien.topB to LocalLLaMAEnglish · 2 years agoLoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70Barxiv.orgexternal-linkmessage-square13linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkLoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70Barxiv.orgninjasaid13@alien.topB to LocalLLaMAEnglish · 2 years agomessage-square13linkfedilink
minus-squaret0nychan@alien.topBlinkfedilinkEnglisharrow-up1·2 years agoI think Perplexity AI used the same technique to train their newly released model pplx-7b-chat and pplx-70b-chat
I think Perplexity AI used the same technique to train their newly released model pplx-7b-chat and pplx-70b-chat