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: How are you using llama.cpp?

4 点作者 danielEM10 个月前
For what purposes you use llama.cpp?<p>What tools do you use with llama.cpp?<p>Is there anything you recommend to avoid when it comes to llama.cpp?<p>Want to collect your best practices&#x2F;experiences and advice around llama.cpp. Eg. if you work with Visual Studio Code - what plugins you recommend, and what not. Etc...

2 条评论

roosgit10 个月前
I use it to help me write text.<p>Don&#x27;t use any tools. I run it from the command line:<p>.&#x2F;main -f ~&#x2F;Desktop&#x2F;prompts&#x2F;multishot&#x2F;llama3-few-shot-prompt-10.txt -m ~&#x2F;Desktop&#x2F;models&#x2F;Meta-Llama-3-8B-Instruct-Q8_0.gguf --temp 0 --color -c 1024 -n -1 --repeat_penalty 1.2 -tb 8 --log-disable 2&gt;&#x2F;dev&#x2F;null<p>I prefer `main` to the new `llama-cli` because when searching history for &quot;llama&quot; I want to get commands that contain the &quot;llama&quot; models, not &quot;mistral&quot; ones, for example.
caprock10 个月前
I&#x27;ve not used it myself, but I see a lot of people referencing Ollama. It uses llama.cpp (and maybe more).