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。

Ask HN: Are you using a smaller LLM for anything?

9 点作者 emschwartz4 个月前
Have you had any luck using a smaller model (&lt;= 3B parameters) for anything? Every time I&#x27;ve poked around with them, they seem to stupid to follow the instructions I try to provide.<p>Curious if others have had any more luck and, if so, which model and for what use case.

1 comment

dimgl3 个月前
I&#x27;m currently using a 32B Qwen model for summarization and it&#x27;s pretty good.