ninjasaid13@alien.topB to LocalLLaMA@poweruser.forumEnglish · 1 year agoLoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70Barxiv.orgexternal-linkmessage-square13fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkLoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70Barxiv.orgninjasaid13@alien.topB to LocalLLaMA@poweruser.forumEnglish · 1 year agomessage-square13fedilink
minus-squarea_beautiful_rhind@alien.topBlinkfedilinkEnglisharrow-up1·1 year agoYea, no shit. I did it to vicuna using proxy logs. The LLM attacks are waaaay more effective once you find the proper string. I’d run the now working 4-bit version on more models, it’s just that I tend to boycott censored weights instead.
Yea, no shit. I did it to vicuna using proxy logs. The LLM attacks are waaaay more effective once you find the proper string.
I’d run the now working 4-bit version on more models, it’s just that I tend to boycott censored weights instead.