ConceptAI & ML
QLoRA
An extension of LoRA that uses specific quantization and GPU paging tricks to drastically reduce the memory required for fine-tuning large language models.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Lecturers
1Connections
3The lectures that define it or assume it, and the concepts next to it.