Fine-tuning large-scale pretrained models is prohibitively expensive in terms of computational and memory costs. LoRA, as one of the most popular Parameter-Efficient Fine-Tuning (PEFT) methods, offers a cost-effective alternative by fine-tuning an auxiliary low-rank model that has significantly fewer parameters. Although LoRA reduces the computational and memory requirements significantly at each iteration, extensive empirical evidence indicates that it converges at a considerably slower rate...| papers.cool
To parameter-efficiently fine-tune (PEFT) large language models (LLMs), the low-rank adaptation (LoRA) method approximates the model changes $\Delta W \in \mathbb{R}^{m \times n}$ through the product of two matrices $A \in \mathbb{R}^{m \times r}$ and $B \in \mathbb{R}^{r \times n}$, where $r \ll \min(m, n)$, $A$ is initialized with Gaussian noise, and $B$ with zeros. LoRA freezes the original model $W$ and updates the "Noise & Zero" adapter, which may lead to slow convergence. To overcome th...| papers.cool
Among the widely used parameter-efficient fine-tuning (PEFT) methods, LoRA and its variants have gained considerable popularity because of avoiding additional inference costs. However, there still often exists an accuracy gap between these methods and full fine-tuning (FT). In this work, we first introduce a novel weight decomposition analysis to investigate the inherent differences between FT and LoRA. Aiming to resemble the learning capacity of FT from the findings, we propose Weight-Decomp...| papers.cool
As large language models (LLMs) have become increasingly compute and memory intensive, parameter-efficient fine-tuning (PEFT) methods are now a common strategy to fine-tune LLMs. A popular PEFT method is Low-Rank Adapters (LoRA), which adds trainable low-rank "adapters" to selected layers. Each adapter consists of a low-rank matrix product, multiplicatively scaled by a rank-dependent factor. This scaling factor, which divides adapters by a factor of the rank, results in slowed learning and st...| papers.cool
Fine-tuning large pre-trained language models on downstream tasks has become an important paradigm in NLP. However, common practice fine-tunes all of the parameters in a pre-trained model, which becomes prohibitive when a large number of downstream tasks are present. Therefore, many fine-tuning methods are proposed to learn incremental updates of pre-trained weights in a parameter efficient way, e.g., low-rank increments. These methods often evenly distribute the budget of incremental updates...| papers.cool
随着ChatGPT及其平替的火热，各种参数高效（Parameter-Efficient）的微调方法也“水涨船高”，其中最流行的方案之一就是本文的主角LoRA了，它出自论文《LoRA: Low-R...| kexue.fm
Technique in numerical linear algebra for approximating a given matrix by a matrix of lower rank| en.wikipedia.org
事实上，除了写博客内容，在这几年里，笔者是花了相当一部分时间来做科学空间的“表面功夫”，为此还专门学了一点php、css和js。虽然不敢说精益求精，但总体来说网站的浏览体验应该比前几年要好得多。...| kexue.fm
众所周知，LoRA是一种常见的参数高效的微调方法，我们在《梯度视角下的LoRA：简介、分析、猜测及推广》做过简单介绍。LoRA利用低秩分解来降低微调参数量，节省微调显存，同时训练好的权重可以合并...| kexue.fm
LoRA（Low-Rank Adaptation）是当前LLM的参数高效微调手段之一，此前我们在《梯度视角下的LoRA：简介、分析、猜测及推广》也有过简单讨论。这篇文章我们来学习LoRA的一个新...| kexue.fm