mirror of
https://github.com/zenlm/zen-blog.git
synced 2026-11-02 17:28:53 +00:00
Root cause of HF + GitHub + section icons not appearing in the docs route: Next.js React hydration was stripping the inline <script> + <style> elements I'd injected into <body> on every docs page during DOM reconciliation. The script never registered its setInterval. Move the decorator to /zen-decorate.js loaded via <script defer src> in <head>. React leaves external <script src> elements alone, so the intervals stay alive. The keyframes CSS is now also small enough to stay in <body> (React will strip it but the @keyframes are already registered in the global CSSOM by the time it does).
146 lines
52 KiB
HTML
146 lines
52 KiB
HTML
<!DOCTYPE html><!--i_dnJM_MIpJSOCQWNJVMq--><html lang="en" class="dark"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="stylesheet" href="/_next/static/chunks/f2332aac77592f9d.css" data-precedence="next"/><link rel="preload" as="script" fetchPriority="low" href="/_next/static/chunks/e83606e8fa9cc796.js"/><script src="/_next/static/chunks/36d6595f0156cd7e.js" async=""></script><script src="/_next/static/chunks/040e9cea20a8d9c7.js" async=""></script><script src="/_next/static/chunks/d4dffb5a0973d49c.js" async=""></script><script src="/_next/static/chunks/turbopack-967f27a9fd33556d.js" async=""></script><script src="/_next/static/chunks/59d0ad1b64f8544e.js" async=""></script><script src="/_next/static/chunks/4d80e004cf4896dd.js" async=""></script><script src="/_next/static/chunks/350ee4303b732916.js" async=""></script><script src="/_next/static/chunks/8de849ca74fc071f.js" async=""></script><script src="/_next/static/chunks/e62b91212ee7f8ff.js" async=""></script><script src="/_next/static/chunks/f19fe44237e54646.js" async=""></script><script src="/_next/static/chunks/cb0a883bafeb6805.js" async=""></script><meta name="theme-color" media="(prefers-color-scheme: dark)" content="#0A0A0A"/><meta name="theme-color" media="(prefers-color-scheme: light)" content="#fff"/><title>Federated Learning for Open AI — Zen LM Blog | Zen LM</title><meta name="description" content="How federated learning enables collaborative model training while preserving data privacy."/><meta property="og:title" content="Zen LM - Open Foundation Models"/><meta property="og:description" content="Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks."/><meta property="og:url" content="https://zenlm.org"/><meta property="og:site_name" content="Zen LM"/><meta property="og:type" content="website"/><meta name="twitter:card" content="summary_large_image"/><meta name="twitter:site" content="@zenlmorg"/><meta name="twitter:creator" content="@zenlmorg"/><meta name="twitter:title" content="Zen LM - Open Foundation Models"/><meta name="twitter:description" content="Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks."/><script src="/_next/static/chunks/a6dad97d9634a72d.js" noModule=""></script><script defer src="/zen-decorate.js"></script></head><body class="antialiased"><div hidden=""><!--$--><!--/$--></div><script>((a,b,c,d,e,f,g,h)=>{let i=document.documentElement,j=["light","dark"];function k(b){var c;(Array.isArray(a)?a:[a]).forEach(a=>{let c="class"===a,d=c&&f?e.map(a=>f[a]||a):e;c?(i.classList.remove(...d),i.classList.add(f&&f[b]?f[b]:b)):i.setAttribute(a,b)}),c=b,h&&j.includes(c)&&(i.style.colorScheme=c)}if(d)k(d);else try{let a=localStorage.getItem(b)||c,d=g&&"system"===a?window.matchMedia("(prefers-color-scheme: dark)").matches?"dark":"light":a;k(d)}catch(a){}})("class","theme","system",null,["light","dark"],null,true,true)</script><!--$--><div data-closed="" role="presentation" hidden="" style="user-select:none;-webkit-user-select:none" class="fixed inset-0 z-50 backdrop-blur-xs bg-fd-overlay data-open:animate-fd-fade-in data-closed:animate-fd-fade-out"></div><div class="bg-fd-secondary/50 p-3 empty:hidden"></div><!--/$--><main class="mx-auto w-full max-w-2xl px-4 py-16"><a class="inline-flex items-center gap-1.5 text-sm text-fd-muted-foreground hover:text-fd-foreground mb-10 transition-colors" href="/blog">← Back to Blog</a><div class="mb-8"><time class="text-xs font-mono text-fd-muted-foreground uppercase tracking-wider">May 8, 2022</time><h1 class="text-3xl font-bold mt-2 mb-3">Federated Learning for Open AI</h1><p class="text-fd-muted-foreground text-lg mb-4">How federated learning enables collaborative model training while preserving data privacy.</p><div class="flex items-center gap-3 pt-4 border-t border-fd-border"><span class="text-sm text-fd-muted-foreground">By <!-- -->Zach Kelling</span><div class="flex gap-1.5 ml-auto"><span class="text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded">Research</span><span class="text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded">Training</span><span class="text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded">Privacy</span></div></div></div><div class="prose dark:prose-invert max-w-none"><p>Training large language models requires vast amounts of data. That data often contains sensitive information. Federated learning offers a path to train on distributed, private data without centralizing it.</p>
|
||
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="the-centralization-problem"><a data-card="" href="#the-centralization-problem" class="peer">The Centralization Problem</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
|
||
<p>Traditional ML training follows a simple pattern: collect data, aggregate it centrally, train models. This creates problems:</p>
|
||
<ul>
|
||
<li><strong>Privacy risk</strong> : Sensitive data leaves user control</li>
|
||
<li><strong>Legal barriers</strong> : Regulations prevent data movement across jurisdictions</li>
|
||
<li><strong>Trust requirements</strong> : Data holders must trust the training party</li>
|
||
<li><strong>Single points of failure</strong> : Central aggregation creates vulnerabilities</li>
|
||
</ul>
|
||
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="federated-learning-basics"><a data-card="" href="#federated-learning-basics" class="peer">Federated Learning Basics</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
|
||
<p>Federated learning inverts the pattern. Instead of bringing data to the model, we bring the model to the data.</p>
|
||
<figure dir="ltr" class="my-4 bg-fd-card rounded-xl shiki relative border shadow-sm not-prose overflow-hidden text-sm shiki shiki-themes github-light github-dark" style="--shiki-light:#24292e;--shiki-dark:#e1e4e8;--shiki-light-bg:#fff;--shiki-dark-bg:#24292e" tabindex="-1"><div class="empty:hidden absolute top-3 right-2 z-2 backdrop-blur-lg rounded-lg text-fd-muted-foreground"><button type="button" class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors duration-100 disabled:pointer-events-none disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-fd-ring p-1 [&_svg]:size-4 hover:text-fd-accent-foreground data-checked:text-fd-accent-foreground" aria-label="Copy Text"><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-clipboard" aria-hidden="true"><rect width="8" height="4" x="8" y="2" rx="1" ry="1"></rect><path d="M16 4h2a2 2 0 0 1 2 2v14a2 2 0 0 1-2 2H6a2 2 0 0 1-2-2V6a2 2 0 0 1 2-2h2"></path></svg></button></div><div role="region" tabindex="0" class="text-[0.8125rem] py-3.5 overflow-auto max-h-[600px] fd-scroll-container focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-inset focus-visible:ring-fd-ring" style="--padding-right:calc(var(--spacing) * 8)"><pre class="min-w-full w-max *:flex *:flex-col"><code><span class="line"><span></span></span>
|
||
<span class="line"><span> +-----------+</span></span>
|
||
<span class="line"><span> | Central |</span></span>
|
||
<span class="line"><span> | Server |</span></span>
|
||
<span class="line"><span> +-----+-----+</span></span>
|
||
<span class="line"><span> |</span></span>
|
||
<span class="line"><span> +--------------+--------------+</span></span>
|
||
<span class="line"><span> | | |</span></span>
|
||
<span class="line"><span> +-----v-----+ +-----v-----+ +-----v-----+</span></span>
|
||
<span class="line"><span> | Client 1 | | Client 2 | | Client N |</span></span>
|
||
<span class="line"><span> | (Data A) | | (Data B) | | (Data N) |</span></span>
|
||
<span class="line"><span> +-----------+ +-----------+ +-----------+</span></span>
|
||
<span class="line"><span> </span></span></code></pre></div></figure>
|
||
<ol>
|
||
<li>Central server distributes model weights</li>
|
||
<li>Clients train locally on their data</li>
|
||
<li>Clients send gradient updates (not data) back</li>
|
||
<li>Server aggregates updates into improved model</li>
|
||
<li>Repeat</li>
|
||
</ol>
|
||
<p>Data never leaves client devices. Only model updates travel.</p>
|
||
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="challenges-at-scale"><a data-card="" href="#challenges-at-scale" class="peer">Challenges at Scale</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
|
||
<p>Federated learning for LLMs faces unique challenges:</p>
|
||
<h3 class="flex scroll-m-28 flex-row items-center gap-2" id="communication-costs"><a data-card="" href="#communication-costs" class="peer">Communication Costs</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h3>
|
||
<p>Model gradients are large. With billions of parameters, naive federation is impractical. We address this through:</p>
|
||
<ul>
|
||
<li><strong>Gradient compression</strong> : Sparsification and quantization reduce bandwidth by 100-1000x</li>
|
||
<li><strong>Asynchronous updates</strong> : Clients contribute when convenient, not in synchronized rounds</li>
|
||
<li><strong>Hierarchical aggregation</strong> : Regional aggregators reduce central server load</li>
|
||
</ul>
|
||
<h3 class="flex scroll-m-28 flex-row items-center gap-2" id="heterogeneous-compute"><a data-card="" href="#heterogeneous-compute" class="peer">Heterogeneous Compute</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h3>
|
||
<p>Participants have varied hardware. A phone differs from a workstation differs from a server. Our approach:</p>
|
||
<ul>
|
||
<li><strong>Adaptive batch sizes</strong> : Smaller devices process smaller batches</li>
|
||
<li><strong>Model sharding</strong> : Large models split across capable participants</li>
|
||
<li><strong>Contribution weighting</strong> : Update importance scales with compute contributed</li>
|
||
</ul>
|
||
<h3 class="flex scroll-m-28 flex-row items-center gap-2" id="data-heterogeneity"><a data-card="" href="#data-heterogeneity" class="peer">Data Heterogeneity</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h3>
|
||
<p>Different participants have different data distributions. This creates convergence challenges. Solutions:</p>
|
||
<ul>
|
||
<li><strong>Personalization layers</strong> : Some parameters remain local</li>
|
||
<li><strong>Clustered federation</strong> : Similar participants form training groups</li>
|
||
<li><strong>Importance sampling</strong> : Under-represented distributions get higher weight</li>
|
||
</ul>
|
||
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="privacy-enhancements"><a data-card="" href="#privacy-enhancements" class="peer">Privacy Enhancements</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
|
||
<p>Basic federation protects raw data but gradients can leak information. We add:</p>
|
||
<h3 class="flex scroll-m-28 flex-row items-center gap-2" id="differential-privacy"><a data-card="" href="#differential-privacy" class="peer">Differential Privacy</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h3>
|
||
<p>Noise added to gradients provides mathematical privacy guarantees. Each participant’s contribution becomes statistically indistinguishable.</p>
|
||
<h3 class="flex scroll-m-28 flex-row items-center gap-2" id="secure-aggregation"><a data-card="" href="#secure-aggregation" class="peer">Secure Aggregation</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h3>
|
||
<p>Cryptographic protocols ensure the server only sees aggregated updates, not individual contributions. Even a compromised server learns nothing about specific participants.</p>
|
||
<h3 class="flex scroll-m-28 flex-row items-center gap-2" id="trusted-execution"><a data-card="" href="#trusted-execution" class="peer">Trusted Execution</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h3>
|
||
<p>Hardware enclaves (SGX, TrustZone) provide additional isolation. Computation occurs in protected memory regions.</p>
|
||
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="zen-federation-protocol"><a data-card="" href="#zen-federation-protocol" class="peer">Zen Federation Protocol</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
|
||
<p>We’ve developed a federation protocol specifically for language model training:</p>
|
||
<ol>
|
||
<li><strong>Enrollment</strong> : Participants register compute capacity and data characteristics</li>
|
||
<li><strong>Matching</strong> : Coordinator assigns participants to training cohorts</li>
|
||
<li><strong>Distribution</strong> : Model shards route to appropriate participants</li>
|
||
<li><strong>Training</strong> : Local training with privacy-preserving gradient computation</li>
|
||
<li><strong>Aggregation</strong> : Secure combination of participant updates</li>
|
||
<li><strong>Verification</strong> : Cryptographic proofs of correct computation</li>
|
||
</ol>
|
||
<p>Early benchmarks show we achieve 85% of centralized training efficiency while maintaining strong privacy guarantees.</p>
|
||
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="join-the-network"><a data-card="" href="#join-the-network" class="peer">Join the Network</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
|
||
<p>We’re opening the Zen federation network to participants. Contribute compute, contribute data (privately), contribute to open AI.</p>
|
||
<p>Requirements:</p>
|
||
<ul>
|
||
<li>Minimum 16GB RAM</li>
|
||
<li>Stable internet connection</li>
|
||
<li>Willingness to run our client software</li>
|
||
</ul>
|
||
<p>In return, participants receive:</p>
|
||
<ul>
|
||
<li>Governance tokens proportional to contribution</li>
|
||
<li>Early access to trained models</li>
|
||
<li>Recognition in model cards</li>
|
||
</ul>
|
||
<p>Details at zen.ai/federate.</p>
|
||
<hr/>
|
||
<p><em>Zach Kelling is a co-founder of Zoo Labs Foundation.</em></p></div></main><!--$--><!--/$--><script src="/_next/static/chunks/e83606e8fa9cc796.js" id="_R_" async=""></script><script>(self.__next_f=self.__next_f||[]).push([0])</script><script>self.__next_f.push([1,"1:\"$Sreact.fragment\"\n2:I[106,[\"/_next/static/chunks/59d0ad1b64f8544e.js\"],\"RootProvider\"]\n3:I[53113,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"default\"]\n4:I[73211,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"default\"]\n5:I[10086,[\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"/_next/static/chunks/8de849ca74fc071f.js\",\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"/_next/static/chunks/f19fe44237e54646.js\",\"/_next/static/chunks/cb0a883bafeb6805.js\"],\"\"]\n7:I[89923,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"OutletBoundary\"]\n8:\"$Sreact.suspense\"\na:I[89923,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"ViewportBoundary\"]\nc:I[89923,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"MetadataBoundary\"]\ne:I[6998,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"default\"]\n:HL[\"/_next/static/chunks/f2332aac77592f9d.css\",\"style\"]\n"])</script><script>self.__next_f.push([1,"0:{\"P\":null,\"b\":\"i-dnJM_MIpJSOCQWNJVMq\",\"c\":[\"\",\"blog\",\"federated-learning\"],\"q\":\"\",\"i\":false,\"f\":[[[\"\",{\"children\":[\"blog\",{\"children\":[[\"slug\",\"federated-learning\",\"d\"],{\"children\":[\"__PAGE__\",{}]}]}]},\"$undefined\",\"$undefined\",true],[[\"$\",\"$1\",\"c\",{\"children\":[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/chunks/f2332aac77592f9d.css\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-0\",{\"src\":\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"async\":true,\"nonce\":\"$undefined\"}]],[\"$\",\"html\",null,{\"lang\":\"en\",\"className\":\"dark\",\"suppressHydrationWarning\":true,\"children\":[\"$\",\"body\",null,{\"className\":\"antialiased\",\"children\":[\"$\",\"$L2\",null,{\"children\":[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"main\",null,{\"className\":\"flex min-h-screen flex-col items-center justify-center px-4 text-center\",\"children\":[[\"$\",\"div\",null,{\"className\":\"mb-8 opacity-20\",\"children\":[\"$\",\"svg\",null,{\"width\":\"120\",\"height\":\"120\",\"viewBox\":\"0 0 120 120\",\"fill\":\"none\",\"aria-hidden\":\"true\",\"children\":[\"$\",\"circle\",null,{\"cx\":\"60\",\"cy\":\"60\",\"r\":\"50\",\"stroke\":\"currentColor\",\"strokeWidth\":\"3\",\"strokeLinecap\":\"round\",\"strokeDasharray\":\"280 40\"}]}]}],[\"$\",\"p\",null,{\"className\":\"text-xs font-mono uppercase tracking-[0.3em] text-fd-muted-foreground mb-4\",\"children\":\"404\"}],[\"$\",\"h1\",null,{\"className\":\"text-3xl font-semibold mb-3\",\"children\":\"Page not found\"}],[\"$\",\"p\",null,{\"className\":\"text-fd-muted-foreground max-w-sm mb-10\",\"children\":\"This page doesn't exist, or it may have moved. Try the documentation or head home.\"}],[\"$\",\"div\",null,{\"className\":\"flex flex-wrap gap-3 justify-center\",\"children\":[[\"$\",\"$L5\",null,{\"href\":\"/\",\"className\":\"inline-flex items-center gap-2 rounded-lg bg-fd-primary text-fd-primary-foreground px-4 py-2 text-sm font-medium hover:opacity-90 transition\",\"children\":\"Go home\"}],[\"$\",\"$L5\",null,{\"href\":\"/docs\",\"className\":\"inline-flex items-center gap-2 rounded-lg border border-fd-border bg-fd-background px-4 py-2 text-sm font-medium hover:bg-fd-muted transition\",\"children\":\"Documentation\"}],[\"$\",\"$L5\",null,{\"href\":\"/docs/models\",\"className\":\"inline-flex items-center gap-2 rounded-lg border border-fd-border bg-fd-background px-4 py-2 text-sm font-medium hover:bg-fd-muted transition\",\"children\":\"Browse models\"}]]}],[\"$\",\"p\",null,{\"className\":\"mt-16 text-xs font-mono text-fd-muted-foreground opacity-50\",\"children\":\"zenlm.org\"}]]}],[]],\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]}]}]}]]}],{\"children\":[[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}],{\"children\":[[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}],{\"children\":[[\"$\",\"$1\",\"c\",{\"children\":[\"$L6\",[[\"$\",\"script\",\"script-0\",{\"src\":\"/_next/static/chunks/8de849ca74fc071f.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-1\",{\"src\":\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-2\",{\"src\":\"/_next/static/chunks/f19fe44237e54646.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-3\",{\"src\":\"/_next/static/chunks/cb0a883bafeb6805.js\",\"async\":true,\"nonce\":\"$undefined\"}]],[\"$\",\"$L7\",null,{\"children\":[\"$\",\"$8\",null,{\"name\":\"Next.MetadataOutlet\",\"children\":\"$@9\"}]}]]}],{},null,false,false]},null,false,false]},null,false,false]},null,false,false],[\"$\",\"$1\",\"h\",{\"children\":[null,[\"$\",\"$La\",null,{\"children\":\"$Lb\"}],[\"$\",\"div\",null,{\"hidden\":true,\"children\":[\"$\",\"$Lc\",null,{\"children\":[\"$\",\"$8\",null,{\"name\":\"Next.Metadata\",\"children\":\"$Ld\"}]}]}],null]}],false]],\"m\":\"$undefined\",\"G\":[\"$e\",[]],\"S\":true}\n"])</script><script>self.__next_f.push([1,"6:[\"$\",\"main\",null,{\"className\":\"mx-auto w-full max-w-2xl px-4 py-16\",\"children\":[[\"$\",\"$L5\",null,{\"href\":\"/blog\",\"className\":\"inline-flex items-center gap-1.5 text-sm text-fd-muted-foreground hover:text-fd-foreground mb-10 transition-colors\",\"children\":\"← Back to Blog\"}],[\"$\",\"div\",null,{\"className\":\"mb-8\",\"children\":[[\"$\",\"time\",null,{\"className\":\"text-xs font-mono text-fd-muted-foreground uppercase tracking-wider\",\"children\":\"May 8, 2022\"}],[\"$\",\"h1\",null,{\"className\":\"text-3xl font-bold mt-2 mb-3\",\"children\":\"Federated Learning for Open AI\"}],[\"$\",\"p\",null,{\"className\":\"text-fd-muted-foreground text-lg mb-4\",\"children\":\"How federated learning enables collaborative model training while preserving data privacy.\"}],[\"$\",\"div\",null,{\"className\":\"flex items-center gap-3 pt-4 border-t border-fd-border\",\"children\":[[\"$\",\"span\",null,{\"className\":\"text-sm text-fd-muted-foreground\",\"children\":[\"By \",\"Zach Kelling\"]}],[\"$\",\"div\",null,{\"className\":\"flex gap-1.5 ml-auto\",\"children\":[[\"$\",\"span\",\"Research\",{\"className\":\"text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded\",\"children\":\"Research\"}],[\"$\",\"span\",\"Training\",{\"className\":\"text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded\",\"children\":\"Training\"}],[\"$\",\"span\",\"Privacy\",{\"className\":\"text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded\",\"children\":\"Privacy\"}]]}]]}]]}],[\"$\",\"div\",null,{\"className\":\"prose dark:prose-invert max-w-none\",\"children\":[[\"$\",\"p\",null,{\"children\":\"Training large language models requires vast amounts of data. That data often contains sensitive information. Federated learning offers a path to train on distributed, private data without centralizing it.\"}],\"\\n\",[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"the-centralization-problem\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#the-centralization-problem\",\"className\":\"peer\",\"children\":\"The Centralization Problem\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}],\"\\n\",[\"$\",\"p\",null,{\"children\":\"Traditional ML training follows a simple pattern: collect data, aggregate it centrally, train models. This creates problems:\"}],\"\\n\",[\"$\",\"ul\",null,{\"children\":[\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Privacy risk\"}],\" : Sensitive data leaves user control\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Legal barriers\"}],\" : Regulations prevent data movement across jurisdictions\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Trust requirements\"}],\" : Data holders must trust the training party\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Single points of failure\"}],\" : Central aggregation creates vulnerabilities\"]}],\"\\n\"]}],\"\\n\",[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"federated-learning-basics\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#federated-learning-basics\",\"className\":\"peer\",\"children\":\"Federated Learning Basics\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],\"$Lf\",\"$undefined\"]}]]}],\"\\n\",\"$L10\",\"\\n\",\"$L11\",\"\\n\",\"$L12\",\"\\n\",\"$L13\",\"\\n\",\"$L14\",\"\\n\",\"$L15\",\"\\n\",\"$L16\",\"\\n\",\"$L17\",\"\\n\",\"$L18\",\"\\n\",\"$L19\",\"\\n\",\"$L1a\",\"\\n\",\"$L1b\",\"\\n\",\"$L1c\",\"\\n\",\"$L1d\",\"\\n\",\"$L1e\",\"\\n\",\"$L1f\",\"\\n\",\"$L20\",\"\\n\",\"$L21\",\"\\n\",\"$L22\",\"\\n\",\"$L23\",\"\\n\",\"$L24\",\"\\n\",\"$L25\",\"\\n\",\"$L26\",\"\\n\",\"$L27\",\"\\n\",\"$L28\",\"\\n\",\"$L29\",\"\\n\",\"$L2a\",\"\\n\",\"$L2b\",\"\\n\",\"$L2c\",\"\\n\",\"$L2d\",\"\\n\",\"$L2e\",\"\\n\",\"$L2f\",\"\\n\",\"$L30\",\"\\n\",\"$L31\",\"\\n\",\"$L32\",\"\\n\",\"$L33\"]}]]}]\n"])</script><script>self.__next_f.push([1,"34:I[51504,[\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"/_next/static/chunks/8de849ca74fc071f.js\",\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"/_next/static/chunks/f19fe44237e54646.js\",\"/_next/static/chunks/cb0a883bafeb6805.js\"],\"CodeBlock\"]\n35:I[51504,[\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"/_next/static/chunks/8de849ca74fc071f.js\",\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"/_next/static/chunks/f19fe44237e54646.js\",\"/_next/static/chunks/cb0a883bafeb6805.js\"],\"Pre\"]\nf:[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}]\n10:[\"$\",\"p\",null,{\"children\":\"Federated learning inverts the pattern. Instead of bringing data to the model, we bring the model to the data.\"}]\n"])</script><script>self.__next_f.push([1,"11:[\"$\",\"$L34\",null,{\"className\":\"shiki shiki-themes github-light github-dark\",\"style\":{\"--shiki-light\":\"#24292e\",\"--shiki-dark\":\"#e1e4e8\",\"--shiki-light-bg\":\"#fff\",\"--shiki-dark-bg\":\"#24292e\"},\"tabIndex\":\"0\",\"icon\":\"\u003csvg viewBox=\\\"0 0 24 24\\\"\u003e\u003cpath d=\\\"M 6,1 C 4.354992,1 3,2.354992 3,4 v 16 c 0,1.645008 1.354992,3 3,3 h 12 c 1.645008,0 3,-1.354992 3,-3 V 8 7 A 1.0001,1.0001 0 0 0 20.707031,6.2929687 l -5,-5 A 1.0001,1.0001 0 0 0 15,1 h -1 z m 0,2 h 7 v 3 c 0,1.645008 1.354992,3 3,3 h 3 v 11 c 0,0.564129 -0.435871,1 -1,1 H 6 C 5.4358712,21 5,20.564129 5,20 V 4 C 5,3.4358712 5.4358712,3 6,3 Z M 15,3.4140625 18.585937,7 H 16 C 15.435871,7 15,6.5641288 15,6 Z\\\" fill=\\\"currentColor\\\" /\u003e\u003c/svg\u003e\",\"children\":[\"$\",\"$L35\",null,{\"children\":[\"$\",\"code\",null,{\"children\":[[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{}]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"children\":\" +-----------+\"}]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"children\":\" | Central |\"}]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"children\":\" | Server |\"}]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"children\":\" +-----+-----+\"}]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"children\":\" |\"}]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"children\":\" +--------------+--------------+\"}]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"children\":\" | | |\"}]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"children\":\" +-----v-----+ +-----v-----+ +-----v-----+\"}]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"children\":\" | Client 1 | | Client 2 | | Client N |\"}]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"children\":\" | (Data A) | | (Data B) | | (Data N) |\"}]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"children\":\" +-----------+ +-----------+ +-----------+\"}]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"children\":\" \"}]}]]}]}]}]\n"])</script><script>self.__next_f.push([1,"12:[\"$\",\"ol\",null,{\"children\":[\"\\n\",[\"$\",\"li\",null,{\"children\":\"Central server distributes model weights\"}],\"\\n\",[\"$\",\"li\",null,{\"children\":\"Clients train locally on their data\"}],\"\\n\",[\"$\",\"li\",null,{\"children\":\"Clients send gradient updates (not data) back\"}],\"\\n\",[\"$\",\"li\",null,{\"children\":\"Server aggregates updates into improved model\"}],\"\\n\",[\"$\",\"li\",null,{\"children\":\"Repeat\"}],\"\\n\"]}]\n13:[\"$\",\"p\",null,{\"children\":\"Data never leaves client devices. Only model updates travel.\"}]\n14:[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"challenges-at-scale\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#challenges-at-scale\",\"className\":\"peer\",\"children\":\"Challenges at Scale\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n15:[\"$\",\"p\",null,{\"children\":\"Federated learning for LLMs faces unique challenges:\"}]\n16:[\"$\",\"h3\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"communication-costs\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#communication-costs\",\"className\":\"peer\",\"children\":\"Communication Costs\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n17:[\"$\",\"p\",null,{\"children\":\"Model gradients are large. With billions of parameters, naive federation is impractical. We address this through:\"}]\n18:[\"$\",\"ul\",null,{\"children\":[\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Gradient compression\"}],\" : Sparsification and quantization reduce bandwidth by 100-1000x\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Asynchronous updates\"}],\" : Clients contribute when convenient, not in synchronized rounds\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Hierarchical aggregation\"}],\" : Regional aggregators reduce central server load\"]}],\"\\n\"]}]\n19:[\"$\",\"h3\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"heterogeneous-compute\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#heterogeneous-compute\",\"className\":\"peer\",\"children\":\"Heterogeneous Compute\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n1a:[\"$\",\"p\",null,{\"children\":\"Participants have varied hardware. A phone differs from a workstation differs from a server. Our approach:\"}]\n1b:[\"$\",\"ul\",null,{\"children\":[\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Adaptive batch sizes\"}],\" : Smaller devices process smaller batches\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Model sharding\"}],\" : Large models split across capable"])</script><script>self.__next_f.push([1," participants\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Contribution weighting\"}],\" : Update importance scales with compute contributed\"]}],\"\\n\"]}]\n1c:[\"$\",\"h3\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"data-heterogeneity\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#data-heterogeneity\",\"className\":\"peer\",\"children\":\"Data Heterogeneity\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n1d:[\"$\",\"p\",null,{\"children\":\"Different participants have different data distributions. This creates convergence challenges. Solutions:\"}]\n1e:[\"$\",\"ul\",null,{\"children\":[\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Personalization layers\"}],\" : Some parameters remain local\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Clustered federation\"}],\" : Similar participants form training groups\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Importance sampling\"}],\" : Under-represented distributions get higher weight\"]}],\"\\n\"]}]\n1f:[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"privacy-enhancements\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#privacy-enhancements\",\"className\":\"peer\",\"children\":\"Privacy Enhancements\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n20:[\"$\",\"p\",null,{\"children\":\"Basic federation protects raw data but gradients can leak information. We add:\"}]\n21:[\"$\",\"h3\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"differential-privacy\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#differential-privacy\",\"className\":\"peer\",\"children\":\"Differential Privacy\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n22:[\"$\",\"p\",null,{\"children\":\"Noise added to gradients provides mathematical privacy guarantees. Each participant’s contribution becomes statistically indistinguishable.\"}]\n23:[\"$\",\"h3\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"secure-aggregation\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#secure-aggregation\",\"className\":\"peer\",\"children\":\"Secure Aggregation\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":"])</script><script>self.__next_f.push([1,"[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n24:[\"$\",\"p\",null,{\"children\":\"Cryptographic protocols ensure the server only sees aggregated updates, not individual contributions. Even a compromised server learns nothing about specific participants.\"}]\n25:[\"$\",\"h3\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"trusted-execution\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#trusted-execution\",\"className\":\"peer\",\"children\":\"Trusted Execution\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n26:[\"$\",\"p\",null,{\"children\":\"Hardware enclaves (SGX, TrustZone) provide additional isolation. Computation occurs in protected memory regions.\"}]\n27:[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"zen-federation-protocol\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#zen-federation-protocol\",\"className\":\"peer\",\"children\":\"Zen Federation Protocol\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n28:[\"$\",\"p\",null,{\"children\":\"We’ve developed a federation protocol specifically for language model training:\"}]\n29:[\"$\",\"ol\",null,{\"children\":[\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Enrollment\"}],\" : Participants register compute capacity and data characteristics\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Matching\"}],\" : Coordinator assigns participants to training cohorts\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Distribution\"}],\" : Model shards route to appropriate participants\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Training\"}],\" : Local training with privacy-preserving gradient computation\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Aggregation\"}],\" : Secure combination of participant updates\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"Verification\"}],\" : Cryptographic proofs of correct computation\"]}],\"\\n\"]}]\n2a:[\"$\",\"p\",null,{\"children\":\"Early benchmarks show we achieve 85% of centralized training efficiency while maintaining strong privacy guarantees.\"}]\n2b:[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"join-the-network\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#join-the-network\",\"className\":\"peer\",\"children\":\"Join the Network\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"])</script><script>self.__next_f.push([1,"\"}],\"$undefined\"]}]]}]\n2c:[\"$\",\"p\",null,{\"children\":\"We’re opening the Zen federation network to participants. Contribute compute, contribute data (privately), contribute to open AI.\"}]\n2d:[\"$\",\"p\",null,{\"children\":\"Requirements:\"}]\n2e:[\"$\",\"ul\",null,{\"children\":[\"\\n\",[\"$\",\"li\",null,{\"children\":\"Minimum 16GB RAM\"}],\"\\n\",[\"$\",\"li\",null,{\"children\":\"Stable internet connection\"}],\"\\n\",[\"$\",\"li\",null,{\"children\":\"Willingness to run our client software\"}],\"\\n\"]}]\n2f:[\"$\",\"p\",null,{\"children\":\"In return, participants receive:\"}]\n30:[\"$\",\"ul\",null,{\"children\":[\"\\n\",[\"$\",\"li\",null,{\"children\":\"Governance tokens proportional to contribution\"}],\"\\n\",[\"$\",\"li\",null,{\"children\":\"Early access to trained models\"}],\"\\n\",[\"$\",\"li\",null,{\"children\":\"Recognition in model cards\"}],\"\\n\"]}]\n31:[\"$\",\"p\",null,{\"children\":\"Details at zen.ai/federate.\"}]\n32:[\"$\",\"hr\",null,{}]\n33:[\"$\",\"p\",null,{\"children\":[\"$\",\"em\",null,{\"children\":\"Zach Kelling is a co-founder of Zoo Labs Foundation.\"}]}]\n"])</script><script>self.__next_f.push([1,"b:[[\"$\",\"meta\",\"0\",{\"charSet\":\"utf-8\"}],[\"$\",\"meta\",\"1\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}],[\"$\",\"meta\",\"2\",{\"name\":\"theme-color\",\"media\":\"(prefers-color-scheme: dark)\",\"content\":\"#0A0A0A\"}],[\"$\",\"meta\",\"3\",{\"name\":\"theme-color\",\"media\":\"(prefers-color-scheme: light)\",\"content\":\"#fff\"}]]\n"])</script><script>self.__next_f.push([1,"9:null\nd:[[\"$\",\"title\",\"0\",{\"children\":\"Federated Learning for Open AI — Zen LM Blog | Zen LM\"}],[\"$\",\"meta\",\"1\",{\"name\":\"description\",\"content\":\"How federated learning enables collaborative model training while preserving data privacy.\"}],[\"$\",\"meta\",\"2\",{\"property\":\"og:title\",\"content\":\"Zen LM - Open Foundation Models\"}],[\"$\",\"meta\",\"3\",{\"property\":\"og:description\",\"content\":\"Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks.\"}],[\"$\",\"meta\",\"4\",{\"property\":\"og:url\",\"content\":\"https://zenlm.org\"}],[\"$\",\"meta\",\"5\",{\"property\":\"og:site_name\",\"content\":\"Zen LM\"}],[\"$\",\"meta\",\"6\",{\"property\":\"og:type\",\"content\":\"website\"}],[\"$\",\"meta\",\"7\",{\"name\":\"twitter:card\",\"content\":\"summary_large_image\"}],[\"$\",\"meta\",\"8\",{\"name\":\"twitter:site\",\"content\":\"@zenlmorg\"}],[\"$\",\"meta\",\"9\",{\"name\":\"twitter:creator\",\"content\":\"@zenlmorg\"}],[\"$\",\"meta\",\"10\",{\"name\":\"twitter:title\",\"content\":\"Zen LM - Open Foundation Models\"}],[\"$\",\"meta\",\"11\",{\"name\":\"twitter:description\",\"content\":\"Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks.\"}]]\n"])</script><script>
|
||
(function(){
|
||
// After React renders the lotus emoji from RSC payload, walk the DOM
|
||
// and replace it with the enso SVG. Polls so subsequent React re-renders
|
||
// also get cleaned up.
|
||
function swap(){
|
||
// 1. Replace lotus + ' Zen LM' text inside <a> brand links
|
||
document.querySelectorAll('a').forEach(function(a){
|
||
if (a.dataset.zenLotusSwapped) return;
|
||
var t = (a.textContent || '');
|
||
if (!/.*Zen LM|Zen LM.*/.test(t)) return;
|
||
// Find the lotus text node specifically
|
||
var walker = document.createTreeWalker(a, NodeFilter.SHOW_TEXT, null);
|
||
var node;
|
||
while ((node = walker.nextNode())) {
|
||
if (node.nodeValue && node.nodeValue.indexOf('') !== -1) {
|
||
node.nodeValue = node.nodeValue.replace(/\s?/g, '');
|
||
}
|
||
}
|
||
// Inject enso SVG at start
|
||
if (!a.querySelector('svg[aria-label="Zen LM"]')) {
|
||
var ns = 'http://www.w3.org/2000/svg';
|
||
var svg = document.createElementNS(ns, 'svg');
|
||
svg.setAttribute('viewBox', '0 0 512 512');
|
||
svg.setAttribute('fill', 'none');
|
||
svg.setAttribute('width', '18');
|
||
svg.setAttribute('height', '18');
|
||
svg.setAttribute('aria-label', 'Zen LM');
|
||
svg.style.cssText = 'display:inline-block;vertical-align:-2px;margin-right:6px;flex-shrink:0';
|
||
var p = document.createElementNS(ns, 'path');
|
||
p.setAttribute('d', 'M 256 84 A 172 172 0 1 0 256 428 A 172 172 0 1 0 256 84 Z');
|
||
p.setAttribute('stroke', 'currentColor');
|
||
p.setAttribute('stroke-width', '26');
|
||
p.setAttribute('stroke-linecap', 'round');
|
||
p.setAttribute('stroke-linejoin', 'round');
|
||
svg.appendChild(p);
|
||
a.insertBefore(svg, a.firstChild);
|
||
}
|
||
a.dataset.zenLotusSwapped = '1';
|
||
});
|
||
}
|
||
function start(){ swap(); setInterval(swap, 600); }
|
||
if (document.readyState !== 'loading') start();
|
||
else document.addEventListener('DOMContentLoaded', start);
|
||
})();
|
||
</script>
|
||
|
||
<style id="zenlm-brand-anim">
|
||
@keyframes zenlm-brand-draw { to { stroke-dashoffset: 0; } }
|
||
svg.zenlm-brand-svg .zenlm-brand-path {
|
||
stroke-dasharray: 1100;
|
||
stroke-dashoffset: 1100;
|
||
animation: zenlm-brand-draw 1.4s cubic-bezier(.45,0,.2,1) 0.1s 1 forwards;
|
||
}
|
||
.zen-link-icon { display: inline-block; vertical-align: middle; flex-shrink: 0; }
|
||
</style></body></html> |