Glossary
LoRA
Low-rank adaptation: freeze the base weights and train a small low-rank update, a tiny fraction of the parameters. Adapters are small, swappable and mergeable.
Where it is explained
See also
Terms explained in the same lessons.
Glossary
Low-rank adaptation: freeze the base weights and train a small low-rank update, a tiny fraction of the parameters. Adapters are small, swappable and mergeable.
Terms explained in the same lessons.