Peft

LoRA+: why does B want a higher learning rate than A?

Why is LoRA's B initialised to zero and A to Gaussian. What breaks if both are Gaussian?

LoRA init: why B = 0 and A ~ Gaussian (not both Gaussian)?

Explain why a rank-r B·A update captures most of full fine-tuning's signal

What does LoRA's α/r ratio control, and why is α = 2r a common default?

If you change LoRA's rank from 16 to 64 with α fixed, what actually happens?

IA3 vs LoRA: what does IA3 parameterise, and what's the param-count win?

What does DoRA decompose, and why does it beat LoRA at the same rank?

DoRA: which component does LoRA actually adapt?

AdaLoRA: how does adaptive rank allocation across layers work?

What does LoRA do, and why is it popular for fine-tuning?