Single Matrix Lora

Replace LoRA's two-matrix decomposition with a single learnable matrix (AA⊤) to eliminate scale imbalances and improve training stability. Reduces parameters by ~50% while maintaining or exceeding LoRA performance.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit db26c38644

Frequently asked questions

npx get-skill add adu2021/single-matrix-lora