LoRA fine-tunes a frozen weight matrix W∈Rdout×dinW \in \mathbb{R}^{d_{out} \times d_{in}}W∈Rdout×din by learning a low-rank update ΔW=BA\Delta W = BAΔW=BA where B∈Rdout×rB \in \mathbb{R}^{d_{out} \times r}B∈Rdout×r and A∈Rr×dinA \in \mathbb{R}^{r \times d_{in}}A∈Rr×din.
Unlock this and every premium problem across all tracks — plus hidden-test grading, advanced AI engineering modules and new content every week.