refiners/docs/index.md

---
icon: material/water-outline
---

<h1 style="margin-bottom: 0;"></h1>
<img src="/assets/logo_light.png" alt="Refiners logo" width="400px" style="display: block; margin-left: auto; margin-right: auto"/>

<div style="text-align: center">
  <p>
    <strong>The simplest way to train and run <a href="/concepts/adapter/">adapters</a> on top of foundation models.</strong>
  </p>
  <a href="https://pypi.org/project/refiners/"><img alt="PyPI - Python Version" src="https://img.shields.io/pypi/pyversions/refiners"></a>
  <a href="https://badge.fury.io/py/refiners"><img alt="PyPI Status" src="https://badge.fury.io/py/refiners.svg"></a>
  <a href="https://github.com/finegrain-ai/refiners/blob/main/LICENSE"><img alt="license" src="https://img.shields.io/badge/license-MIT-blue"></a>
  <a href="https://finegrain.ai/bounties"><img alt="code bounties" src="https://img.shields.io/badge/code-bounties-blue"></a>
  <a href="https://discord.gg/mCmjNUVV7d"><img alt="chat" src="https://img.shields.io/discord/1179456777406922913?logo=discord&amp;logoColor=white&amp;color=%235765F2"></a>
  <p>
    At the era of foundation models, adaptation is quickly rising at the method of choice for bridging the last mile quality gap. We couldn't find a framework with first class citizen APIs for foundation model adaptation, so we created one. It's called Refiners, and we're building it on top of PyTorch, in the open, under the MIT License. <a href="/home/why/">Read our manifesto</a>.
  </p>
</div>