Merging by Matching Models in Task Parameter Subspaces

arXiv:2312.04339v2 Announce Type: replace
Abstract: Model merging aims to cheaply combine individual task-specific models into a single multitask model. In this work, we view past merging methods as leveraging different notions of a ''task parameter subspace'' in which models are matched before being merged. We connect the task parameter subspace of a given model to its loss landscape and formalize how this approach to model merging can be seen as solving a linear system of equations. While past work has …

arxiv cs.cl cs.lg merging type