TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

LORA: Low-Rank Adaptation of Large Language Models

42 点作者 LukeEF大约 2 年前

2 条评论

LukeEF大约 2 年前
From the google leaks paper:<p>&#x27;LoRA is an incredibly powerful technique we should probably be paying more attention to<p>LoRA works by representing model updates as low-rank factorizations, which reduces the size of the update matrices by a factor of up to several thousand. This allows model fine-tuning at a fraction of the cost and time. Being able to personalize a language model in a few hours on consumer hardware is a big deal, particularly for aspirations that involve incorporating new and diverse knowledge in near real-time. The fact that this technology exists is underexploited inside Google, even though it directly impacts some of our most ambitious projects.&#x27; [1]<p>[1] <a href="https:&#x2F;&#x2F;www.semianalysis.com&#x2F;p&#x2F;google-we-have-no-moat-and-neither" rel="nofollow">https:&#x2F;&#x2F;www.semianalysis.com&#x2F;p&#x2F;google-we-have-no-moat-and-ne...</a>
gdiamos大约 2 年前
Fine tuning where you freeze the weights of a neural network has been used for a long time in computer vision. There are many variations of these methods.<p>More recently there are some good libraries that make them easier to use. For example PEFT, which implements LoRA and several other related methods.<p><a href="https:&#x2F;&#x2F;huggingface.co&#x2F;blog&#x2F;peft" rel="nofollow">https:&#x2F;&#x2F;huggingface.co&#x2F;blog&#x2F;peft</a>
评论 #35846663 未加载