Paper Explainers
audio21 MIN PREMIUM

LoRA: Low-Rank Adaptation of Large Language Models

Hu, Shen, Wallis, Allen-Zhu, Li, Wang, Wang, Chen · 2021 · DOI 10.48550/arXiv.2106.09685
Read original paper
SUMMARY

Parameter-efficient fine-tuning via low-rank decomposition of weight deltas, reducing trainable parameters by 10,000× with no inference latency cost.

Unlock the full explainer

Premium subscribers get the full audiobook, transcript, and code repository.

View pricing plans

Made with Emergent