← Glossary
Glossary
What is LoRA?
Instead of updating all weights, insert small low-rank matrices alongside the original weights. Only these small matrices are trained, reducing memory by 10-100x
What people say
Efficient fine-tuning
Instead of updating all weights, insert small low-rank matrices alongside the original weights. Only these small matrices are trained, reducing memory by 10-100x
Efficient fine-tuning