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。

How would I go about finetuning Deep Seek or Llama to do this?

2 点作者 profsummergig大约 2 个月前
I want to make AI&#x27;s for the user manuals for specific products.<p>So that instead of a user looking in a manual they just ask the AI questions and it answers.<p>I think this will need the AI to do 3 things:<p>- general awareness of general manuals<p>- access to all the manual related documentation for a specific product (the specific product that we&#x27;re creating the AI for)<p>- understanding of all the synonyms etc. that could be used to seek information on an aspect of the product.<p>How would I go about finetuning the AI to do this? Please give me the exact steps you would use if you were to do it.<p>(I know that general purpose AI&#x27;s such as ChatGPT already do this. My focus is slightly different. I want to create AI&#x27;s that only do one thing, do it very well, and do it with sparse resources [memory&#x2F;disk space, low compute]).

暂无评论

暂无评论