LoRA

A parameter-efficient technique for adapting large pretrained models.

LoRA keeps the original model weights frozen and introduces small trainable low-rank matrices into selected layers. Only these added parameters are updated during fine-tuning.

This greatly reduces memory and storage requirements compared with updating the complete model. Multiple LoRA adapters can also be created for different tasks while sharing the same base model.

Also in

Diffusion Models Small Language Models Retrieval-Augmented Generation Prompt Engineering Context Engineering Few-Shot Learning

JOIN NOW

Begin the first module

It is free, it is the real curriculum, and if it is not for you, you have lost nothing but an evening.

See the curriculum

Join any time · Build AI skills at your pace