peft-main/examples/semantic_segmentation/README.md

Fine-tuning for semantic segmentation using LoRA and 🤗 PEFT

We provide a notebook (semantic_segmentation_peft_lora.ipynb) where we learn how to use LoRA from 🤗 PEFT to fine-tune an semantic segmentation by ONLY using 14%% of the original trainable parameters of the model.

LoRA adds low-rank "update matrices" to certain blocks in the underlying model (in this case the attention blocks) and ONLY trains those matrices during fine-tuning. During inference, these update matrices are merged with the original model parameters. For more details, check out the original LoRA paper.