<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
    <title>open-weight</title>
    <link rel="self" type="application/atom+xml" href="https://links.biapy.com/guest/tags/3301/feed"/>
    <updated>2026-06-06T03:03:54+00:00</updated>
    <id>https://links.biapy.com/guest/tags/3301/feed</id>
            <entry>
            <id>https://links.biapy.com/links/10740</id>
            <title type="text"><![CDATA[Paris]]></title>
            <link rel="alternate" href="https://huggingface.co/bageldotcom/paris" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10740"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A Decentralized Trained Open-Weight Diffusion Model.

The world&amp;#039;s first open-weight diffusion model trained entirely through decentralized computation. The model consists of 8 expert diffusion models (129M-605M parameters each) trained in complete isolation with no gradient, parameter, or intermediate activation synchronization, achieving superior parallelism efficiency over traditional methods while using 14× less data and 16× less compute than baselines.

- [Paris: A Decentralized Trained Open-Weight Diffusion Model @ GitHub](https://github.com/bageldotcom/paris/tree/main).

Related contents:

- [Introducing Paris @ BagelLABS](https://blog.bagel.com/p/paris).]]>
            </summary>
            <updated>2025-10-21T05:36:57+00:00</updated>
        </entry>
    </feed>
