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。

Vicuna: An Open Chatbot Impressing GPT-4

4 点作者 georgehill大约 2 年前

2 条评论

mromanuk大约 2 年前
I see two big constraints to use it right now:<p>- This runs on the CPU only and does not require GPU. It requires around 60GB of CPU memory for Vicuna-13B.<p>also<p>- We release Vicuna weights as delta weights to comply with the LLaMA model license. You can add our delta to the original LLaMA weights to obtain the Vicuna weights. Instructions:<p>...<p>This conversion command needs around 60 GB of CPU RAM.<p>Hope they can optimize it further, to make it work with lesser hardware.
评论 #35431122 未加载
评论 #35516640 未加载
mdaniel大约 2 年前
By far the more interesting link is last week&#x27;s announcement: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=35378683" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=35378683</a>