mirror of
https://github.com/almet/notmyidea.git
synced 2025-04-28 19:42:37 +02:00
76 lines
No EOL
3.9 KiB
HTML
76 lines
No EOL
3.9 KiB
HTML
<!DOCTYPE html>
|
|
<html lang="fr">
|
|
<head>
|
|
<title>
|
|
llm - Alexis Métaireau </title>
|
|
<meta charset="utf-8" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1">
|
|
<link rel="stylesheet"
|
|
href="https://blog.notmyidea.org/theme/css/main.css?v2"
|
|
type="text/css" />
|
|
<link href="https://blog.notmyidea.org/feeds/all.atom.xml"
|
|
type="application/atom+xml"
|
|
rel="alternate"
|
|
title="Alexis Métaireau ATOM Feed" />
|
|
</head>
|
|
<body>
|
|
<div id="content">
|
|
<section id="links">
|
|
<ul>
|
|
<li>
|
|
<a class="main" href="/">Alexis Métaireau</a>
|
|
</li>
|
|
<li>
|
|
<a class=""
|
|
href="https://blog.notmyidea.org/journal/index.html">Journal</a>
|
|
</li>
|
|
<li>
|
|
<a class=""
|
|
href="https://blog.notmyidea.org/code/">Code, etc.</a>
|
|
</li>
|
|
<li>
|
|
<a class=""
|
|
href="https://blog.notmyidea.org/weeknotes/">Notes hebdo</a>
|
|
</li>
|
|
<li>
|
|
<a class=""
|
|
href="https://blog.notmyidea.org/lectures/">Lectures</a>
|
|
</li>
|
|
<li>
|
|
<a class=""
|
|
href="https://blog.notmyidea.org/projets.html">Projets</a>
|
|
</li>
|
|
</ul>
|
|
</section>
|
|
<h1>
|
|
Tag « llm » </h1>
|
|
<section class="section index">
|
|
<time datetime="2023-09-27T00:00:00+02:00">27 septembre 2023</time> <a class='tag' href="https://blog.notmyidea.org/tag/python.html">python</a>
|
|
, <a class='tag' href="https://blog.notmyidea.org/tag/llm.html">llm</a>
|
|
, <a class='tag' href="https://blog.notmyidea.org/tag/bash.html">bash</a>
|
|
, <a class='tag' href="https://blog.notmyidea.org/tag/sqlite.html">sqlite</a>
|
|
<h1>
|
|
<a href="https://blog.notmyidea.org/llm-command-line-tips.html" id="page-title">llm command-line tips</a>
|
|
</h1>
|
|
<p>I’m using <a href="https://llm.datasette.io">llm</a> more and more, and today I had to find back prompts I used in the past. Here is a command I’ve been using, which allows me to filter the results based on what I want. It leverages <a href="https://sqlutils.datasette.io">sql-utils</a>, a cli tool which is able to …</p>
|
|
</section>
|
|
<section class="section index">
|
|
<time datetime="2023-09-22T00:00:00+02:00">22 septembre 2023</time> <a class='tag' href="https://blog.notmyidea.org/tag/llm.html">llm</a>
|
|
<h1>
|
|
<a href="https://blog.notmyidea.org/how-to-run-the-vigogne-model-locally.html" id="page-title">How to run the vigogne model locally</a>
|
|
</h1>
|
|
|
|
<p><a href="https://github.com/bofenghuang/vigogne">Vigogne</a> is a <span class="caps">LLM</span> model based on <span class="caps">LLAMA2</span>, but trained with french data. As I’m working mostly in french, it might be useful. The current models that I can get locally are in english.</p>
|
|
<p>The information I’ve found online are scarse and not so easy to follow, so …</p>
|
|
</section>
|
|
<ul>
|
|
</ul>
|
|
</section>
|
|
<footer>
|
|
<a id="feed" href="/feeds/all.atom.xml">
|
|
<img alt="RSS Logo" src="/theme/rss.svg" />
|
|
</a>
|
|
</footer>
|
|
</div>
|
|
</body>
|
|
</html> |