QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models

Yuhui Xu, Lingxi Xie, Xiaotao Gu, Xin Chen, Heng Chang, Hengheng Zhang, Zhengsu Chen, XIAOPENG ZHANG, Qi Tian

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Large Language Models, Quantization, LoRA, Instruct Fine-tuning

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: An efficient quantization-aware LoRA algorithm for fine-tuning LLMs; no post-training quantization is required and accuracy is improved

Abstract: Recently years have witnessed a rapid development of large language models (LLMs). Despite the strong ability in many language-understanding tasks, the heavy computational burden largely restricts the application of LLMs especially when one needs to deploy them onto edge devices. In this paper, we propose a quantization-aware low-rank adaptation (QA-LoRA) algorithm. The motivation lies in the imbalanced degrees of freedom of quantization and adaptation, and the solution is to use group-wise operators which increase the degree of freedom of quantization meanwhile decreasing that of adaptation. QA-LoRA is easily implemented with a few lines of code, and it equips the original LoRA with two-fold abilities: (i) during fine-tuning, the LLM's weights are quantized (e.g., into INT4) to reduce time and memory usage; (ii) after fine-tuning, the LLM and auxiliary weights are naturally integrated into a quantized model without loss of accuracy. We apply QA-LoRA to the LLaMA and LLaMA2 model families and validate its effectiveness in different fine-tuning datasets and downstream scenarios. The code is made available at https://github.com/yuhuixu1993/qa-lora.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 2414