<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: dataversity</title><link>https://news.ycombinator.com/user?id=dataversity</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 17 Apr 2026 09:55:44 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=dataversity" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by dataversity in "Show HN: Run Hugging Face models with a single command"]]></title><description><![CDATA[
<p>The goal is to make working with local models easier for developers, especially when experimenting with different models or sharing setups with others.<p>Would love to hear back from the community</p>
]]></description><pubDate>Thu, 12 Mar 2026 16:17:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=47353130</link><dc:creator>dataversity</dc:creator><comments>https://news.ycombinator.com/item?id=47353130</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47353130</guid></item><item><title><![CDATA[New comment by dataversity in "Show HN: Run Hugging Face models with a single command"]]></title><description><![CDATA[
<p>Some of the features llmpm supports today:<p>• Install and run open-source models (almost all Hugging Face models)<p>• Package models with projects so environments are reproducible<p>• Serve models through an OpenAI compatible API<p>• Built-in chat UI for interacting with running models<p>• CLI workflow designed for developers<p>• Model benchmarking and rankings to help choose models
Example:<p>llmpm serve llama3<p>This exposes an API endpoint similar to:<p>http://localhost:8080/v1/chat/completions</p>
]]></description><pubDate>Thu, 12 Mar 2026 16:10:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=47352982</link><dc:creator>dataversity</dc:creator><comments>https://news.ycombinator.com/item?id=47352982</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47352982</guid></item><item><title><![CDATA[New comment by dataversity in "Show HN: Run Hugging Face models with a single command"]]></title><description><![CDATA[
<p>Hi folks, I’ve been working on llmpm, a CLI tool that makes open-source LLMs installable like packages.
The idea came from the frustration of trying to run different models locally. Every model tends to have slightly different instructions, dependencies, or runtimes. I wanted something that worked more like npm or pip, install a model and run it immediately.
With llmpm you can do things like:<p>llmpm install llama3<p>llmpm run llama3</p>
]]></description><pubDate>Thu, 12 Mar 2026 16:05:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=47352884</link><dc:creator>dataversity</dc:creator><comments>https://news.ycombinator.com/item?id=47352884</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47352884</guid></item><item><title><![CDATA[Show HN: Run Hugging Face models with a single command]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.llmpm.co/">https://www.llmpm.co/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47352754">https://news.ycombinator.com/item?id=47352754</a></p>
<p>Points: 2</p>
<p># Comments: 3</p>
]]></description><pubDate>Thu, 12 Mar 2026 15:59:07 +0000</pubDate><link>https://www.llmpm.co/</link><dc:creator>dataversity</dc:creator><comments>https://news.ycombinator.com/item?id=47352754</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47352754</guid></item><item><title><![CDATA[New comment by dataversity in "Show HN: Llmpm – NPM for LLMs"]]></title><description><![CDATA[
<p>Tried this out this morning. It’s a pretty powerful CLI tool for developers working with open-source LLMs.</p>
]]></description><pubDate>Mon, 09 Mar 2026 16:02:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=47310843</link><dc:creator>dataversity</dc:creator><comments>https://news.ycombinator.com/item?id=47310843</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47310843</guid></item><item><title><![CDATA[New comment by dataversity in "Ask HN: What Are You Working On? (March 2026)"]]></title><description><![CDATA[
<p>Also, is there is way I can invoke the models or is there an API which your tool exposes?</p>
]]></description><pubDate>Mon, 09 Mar 2026 08:22:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=47306182</link><dc:creator>dataversity</dc:creator><comments>https://news.ycombinator.com/item?id=47306182</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47306182</guid></item><item><title><![CDATA[New comment by dataversity in "Ask HN: What Are You Working On? (March 2026)"]]></title><description><![CDATA[
<p>Looks crazy! Thanks for building it, there is indeed a need for a npm or pip like package manager for AI Models.</p>
]]></description><pubDate>Mon, 09 Mar 2026 06:19:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=47305423</link><dc:creator>dataversity</dc:creator><comments>https://news.ycombinator.com/item?id=47305423</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47305423</guid></item></channel></rss>