A two-level permutation strategy over attention heads and their inner units transfers task vectors from an old pretrained Transformer to a new one, data-free.
Git Re-Basin: Merging Models modulo Permutation Symmetries
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Update Your Transformer to the Latest Release: Re-Basin of Task Vectors
A two-level permutation strategy over attention heads and their inner units transfers task vectors from an old pretrained Transformer to a new one, data-free.