← Dictionary / LoRA

LoRA

Appears in 2 tutorials

An efficient fine-tuning method that adjusts a small add-on set of weights instead of all of them.

As used in Retrieval-Augmented Generation (RAG) →

An efficient fine-tuning method that adjusts a small add-on set of weights instead of all of them.

As used in Fine-Tuning & Model Customization →

The leading PEFT method: freeze the model and train small low-rank "patch" matrices (A and B) added to the weights. (M07)

Appears in

Retrieval-Augmented Generation (RAG) → Fine-Tuning & Model Customization →