resta
resta copied to clipboard
Published
20 hours ago •
declare-lab
declare-lab
Restore safety in fine-tuned language models through task arithmetic
Results
1
resta issues
Sort by
recently updated
recently updated
newest added
How do we generate the unalignment dataset for (Step:2) Obtain safety vector Safety vector for PEFT?
Metadata
25
Stars
1
Forks
Watchers
Owner
Metadata
Restore safety in fine-tuned language models through task arithmetic