Spaces:
Running
Running
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
| <title>ModelDNA — AI Model Provenance</title> | |
| <style> | |
| :root { | |
| --bg: #030712; | |
| --bg2: #111318; | |
| --bg3: #1a1d27; | |
| --text: #C5C6C7; | |
| --text-dim: #7a7d85; | |
| --accent: #65D423; | |
| --accent2: #4aab1a; | |
| --border: #222530; | |
| --code-bg: #060709; | |
| --green: #4ade80; | |
| --yellow: #facc15; | |
| --red: #f87171; | |
| } | |
| * { margin:0; padding:0; box-sizing:border-box; } | |
| body { background:var(--bg); color:var(--text); font-family: 'IBM Plex Sans', system-ui, -apple-system, sans-serif, system-ui, -apple-system, sans-serif; line-height:1.6; } | |
| code, pre, .mono { font-family: 'Space Mono', Monaco, Menlo, Consolas, monospace, 'Fira Code', 'Cascadia Code', monospace; } | |
| /* NAV */ | |
| nav { border-bottom:1px solid var(--border); padding:1rem 2rem; display:flex; justify-content:space-between; align-items:center; background:var(--bg); position:sticky; top:0; z-index:100; } | |
| .logo { font-size:1.1rem; font-weight:700; color:var(--accent); letter-spacing:-0.02em; display:flex; align-items:center; gap:0.5rem; } | |
| .logo span { color:var(--text-dim); font-weight:400; font-size:0.85rem; } | |
| nav a { color:var(--text-dim); text-decoration:none; font-size:0.9rem; margin-left:1.5rem; transition:color .2s; } | |
| nav a:hover { color:var(--text); } | |
| .nav-cta { background:var(--accent); color:#030712; padding:0.4rem 1rem; border-radius:6px; font-weight:600; font-size:0.85rem; margin-left:1.5rem; } | |
| .nav-cta:hover { opacity:.9; color:#030712; } | |
| /* HERO */ | |
| .hero { max-width:860px; margin:0 auto; padding:5rem 2rem 4rem; text-align:center; } | |
| .badge { display:inline-block; background:rgba(101,212,35,0.1); border:1px solid rgba(101,212,35,0.3); color:var(--accent); padding:0.25rem 0.75rem; border-radius:999px; font-size:0.78rem; mono; margin-bottom:1.5rem; } | |
| h1 { font-size:clamp(2rem, 5vw, 3.2rem); font-weight:700; line-height:1.15; letter-spacing:-0.03em; margin-bottom:1rem; } | |
| h1 em { color:var(--accent); font-style:normal; } | |
| .hero-sub { color:var(--text-dim); font-size:1.1rem; max-width:580px; margin:0 auto 0.75rem; } | |
| .honest-line { color:var(--accent2); font-size:0.9rem; font-style:italic; margin-bottom:2rem; } | |
| .cta-group { display:flex; gap:1rem; justify-content:center; flex-wrap:wrap; } | |
| .btn-primary { background:var(--accent); color:#030712; padding:0.75rem 1.75rem; border-radius:8px; font-weight:700; text-decoration:none; font-size:0.95rem; display:inline-block; } | |
| .btn-secondary { background:transparent; color:var(--text); padding:0.75rem 1.75rem; border-radius:8px; font-weight:500; text-decoration:none; font-size:0.95rem; border:1px solid var(--border); display:inline-block; } | |
| .btn-primary:hover { opacity:.9; } .btn-secondary:hover { border-color:var(--text-dim); } | |
| .hero-note { font-size:0.8rem; color:var(--text-dim); margin-top:1rem; } | |
| /* STATS BAR */ | |
| .stats { border-top:1px solid var(--border); border-bottom:1px solid var(--border); padding:1.5rem 2rem; display:flex; justify-content:center; gap:4rem; flex-wrap:wrap; } | |
| .stat { text-align:center; } | |
| .stat-num { font-size:1.6rem; font-weight:700; color:var(--accent); mono; } | |
| .stat-label { font-size:0.78rem; color:var(--text-dim); margin-top:0.2rem; } | |
| /* SECTION */ | |
| section { max-width:920px; margin:0 auto; padding:4rem 2rem; } | |
| .section-label { color:var(--accent); font-size:0.78rem; font-weight:600; letter-spacing:0.1em; text-transform:uppercase; mono; margin-bottom:0.75rem; } | |
| h2 { font-size:1.9rem; font-weight:700; letter-spacing:-0.02em; margin-bottom:1rem; } | |
| h3 { font-size:1.1rem; font-weight:600; margin-bottom:0.5rem; } | |
| /* VALUE PROPS */ | |
| .props { display:grid; grid-template-columns:repeat(auto-fit, minmax(260px,1fr)); gap:1.5rem; margin-top:2rem; } | |
| .prop { background:var(--bg2); border:1px solid var(--border); border-radius:12px; padding:1.5rem; } | |
| .prop-icon { font-size:1.5rem; margin-bottom:0.75rem; } | |
| .prop h3 { color:var(--text); } | |
| .prop p { color:var(--text-dim); font-size:0.9rem; line-height:1.6; margin-top:0.4rem; } | |
| /* TERMINAL */ | |
| .terminal { background:var(--code-bg); border:1px solid var(--border); border-radius:12px; padding:1.5rem; margin-top:2rem; overflow-x:auto; } | |
| .terminal-bar { display:flex; gap:0.4rem; margin-bottom:1rem; } | |
| .dot { width:12px; height:12px; border-radius:50%; } | |
| .dot-r { background:#f87171; } .dot-y { background:#facc15; } .dot-g { background:#4ade80; } | |
| pre { color:var(--text); font-size:0.82rem; line-height:1.7; white-space:pre; } | |
| .t-cmd { color:var(--accent); } | |
| .t-dim { color:var(--text-dim); } | |
| .t-pass { color:var(--green); } | |
| .t-warn { color:var(--yellow); } | |
| .t-key { color:#a5b4fc; } | |
| .t-val { color:var(--accent2); } | |
| .t-verdict { color:var(--accent); font-weight:700; } | |
| /* HOW IT WORKS */ | |
| .steps { display:grid; grid-template-columns:repeat(auto-fit, minmax(220px,1fr)); gap:1.5rem; margin-top:2rem; } | |
| .step { position:relative; padding-left:2.5rem; } | |
| .step-num { position:absolute; left:0; top:0; width:1.75rem; height:1.75rem; background:rgba(101,212,35,0.15); border:1px solid rgba(101,212,35,0.3); border-radius:50%; display:flex; align-items:center; justify-content:center; color:var(--accent); font-size:0.78rem; font-weight:700; mono; } | |
| .step h3 { color:var(--text); font-size:1rem; } | |
| .step p { color:var(--text-dim); font-size:0.88rem; margin-top:0.3rem; } | |
| .step-tag { display:inline-block; background:rgba(101,212,35,0.1); color:var(--accent); font-size:0.7rem; padding:0.15rem 0.5rem; border-radius:4px; mono; margin-top:0.4rem; } | |
| /* PRICING */ | |
| .plans { display:grid; grid-template-columns:repeat(auto-fit, minmax(210px,1fr)); gap:1rem; margin-top:2rem; } | |
| .plan { background:var(--bg2); border:1px solid var(--border); border-radius:12px; padding:1.5rem; position:relative; } | |
| .plan.featured { border-color:var(--accent2); } | |
| .plan-badge { position:absolute; top:-0.6rem; left:50%; transform:translateX(-50%); background:var(--accent2); color:#030712; font-size:0.7rem; font-weight:700; padding:0.15rem 0.6rem; border-radius:999px; white-space:nowrap; } | |
| .plan-name { font-size:0.85rem; font-weight:600; color:var(--text-dim); text-transform:uppercase; letter-spacing:0.05em; } | |
| .plan-price { font-size:2rem; font-weight:700; mono; margin:0.5rem 0; color:var(--text); } | |
| .plan-price span { font-size:0.85rem; color:var(--text-dim); font-weight:400; } | |
| .plan ul { list-style:none; margin:1rem 0; font-size:0.85rem; color:var(--text-dim); } | |
| .plan ul li { padding:0.25rem 0; display:flex; align-items:flex-start; gap:0.5rem; } | |
| .plan ul li::before { content:'✓'; color:var(--accent); font-size:0.8rem; flex-shrink:0; margin-top:0.1rem; } | |
| .plan-btn { display:block; text-align:center; padding:0.6rem; border-radius:7px; font-size:0.85rem; font-weight:600; text-decoration:none; margin-top:1rem; border:1px solid var(--border); color:var(--text); transition:all .2s; } | |
| .plan-btn:hover, .plan.featured .plan-btn { background:var(--accent); color:#030712; border-color:var(--accent); } | |
| .lab-tag { background:var(--bg3); border:1px solid var(--border); color:var(--text-dim); font-size:0.78rem; padding:0.3rem 0.75rem; border-radius:20px; white-space:nowrap; font-family:var(--mono); } | |
| /* FAQ */ | |
| .faqs { margin-top:2rem; display:flex; flex-direction:column; gap:1rem; } | |
| .faq { background:var(--bg2); border:1px solid var(--border); border-radius:10px; padding:1.25rem; } | |
| .faq h3 { font-size:0.95rem; color:var(--text); } | |
| .faq p { color:var(--text-dim); font-size:0.88rem; margin-top:0.4rem; line-height:1.6; } | |
| /* FOOTER */ | |
| footer { border-top:1px solid var(--border); padding:2rem; text-align:center; } | |
| .footer-brand { font-size:0.9rem; color:var(--text); margin-bottom:0.5rem; } | |
| .footer-links { display:flex; gap:1.5rem; justify-content:center; flex-wrap:wrap; margin:0.75rem 0; } | |
| .footer-links a { color:var(--text-dim); text-decoration:none; font-size:0.82rem; } | |
| .footer-links a:hover { color:var(--accent); } | |
| .footer-copy { color:var(--text-dim); font-size:0.78rem; margin-top:0.75rem; } | |
| </style> | |
| </head> | |
| <body> | |
| <!-- NAV --> | |
| <nav> | |
| <div class="logo"> | |
| modeldna.ai | |
| <span>a RadicalNotion product</span> | |
| </div> | |
| <div style="display:flex; align-items:center; flex-wrap:wrap;"> | |
| <a href="#how">How It Works</a> | |
| <a href="#pricing">Pricing</a> | |
| <a href="#faq">FAQ</a> | |
| <a href="https://huggingface.co/spaces/RadicalNotionAI/modeldna" target="_blank" class="nav-cta">Scan a Model</a> | |
| </div> | |
| </nav> | |
| <!-- HERO --> | |
| <div class="hero"> | |
| <div class="badge mono">powered by ModelAtlas · 2,200+ models indexed</div> | |
| <h1>The <em>DNA test</em><br>for AI models.</h1> | |
| <p class="hero-sub">Identify model provenance, detect derivative lineage, and audit architecture before you deploy. Scan any HuggingFace model in seconds.</p> | |
| <p class="honest-line">No backdoor detection. No security claims. Just architectural truth.</p> | |
| <div class="cta-group"> | |
| <a href="https://huggingface.co/spaces/RadicalNotionAI/modeldna" target="_blank" class="btn-primary">Scan a Model Free</a> | |
| <a href="#how" class="btn-secondary">See How It Works</a> | |
| </div> | |
| <p class="hero-note">Stage 1 architecture screening is free and unlimited. No credit card required.</p> | |
| </div> | |
| <!-- STATS --> | |
| <div class="stats"> | |
| <div class="stat"><div class="stat-num mono">2,450+</div><div class="stat-label">Models in reference corpus</div></div> | |
| <div class="stat"><div class="stat-num mono">27</div><div class="stat-label">Base architecture families</div></div> | |
| <div class="stat"><div class="stat-num mono"><3s</div><div class="stat-label">Stage 1 screening latency</div></div> | |
| <div class="stat"><div class="stat-num mono">60+</div><div class="stat-label">Labs tracked</div></div> | |
| </div> | |
| <!-- LAB COVERAGE GRID --> | |
| <div style="background:var(--bg2);border-top:1px solid var(--border);border-bottom:1px solid var(--border);padding:2.5rem 2rem;"> | |
| <div style="max-width:960px;margin:0 auto;"> | |
| <div style="text-align:center;color:var(--text-dim);font-size:0.78rem;text-transform:uppercase;letter-spacing:0.1em;margin-bottom:1.5rem;">Labs covered in the ModelAtlas reference corpus</div> | |
| <div style="display:flex;flex-wrap:wrap;gap:0.6rem;justify-content:center;"> | |
| <span class="lab-tag">Meta · 661 models</span> | |
| <span class="lab-tag">Qwen · 227 models</span> | |
| <span class="lab-tag">Mistral · 212 models</span> | |
| <span class="lab-tag">Google · 76 models</span> | |
| <span class="lab-tag">Microsoft · 41 models</span> | |
| <span class="lab-tag">DeepSeek · 29 models</span> | |
| <span class="lab-tag">Zhipu AI · 23 models</span> | |
| <span class="lab-tag">IBM · 19 models</span> | |
| <span class="lab-tag">EleutherAI · 18 models</span> | |
| <span class="lab-tag">OpenAI · 16 models</span> | |
| <span class="lab-tag">Tencent · 12 models</span> | |
| <span class="lab-tag">NVIDIA · 11 models</span> | |
| <span class="lab-tag">MiniMax · 8 models</span> | |
| <span class="lab-tag">Cohere · 8 models</span> | |
| <span class="lab-tag">TII UAE · 9 models</span> | |
| <span class="lab-tag">StepFun · 7 models</span> | |
| <span class="lab-tag">AntGroup / inclusionAI · Bailing, Ling, LLaDA2</span> | |
| <span class="lab-tag">Moonshot · Kimi, Kimi-Linear, K2</span> | |
| <span class="lab-tag">ByteDance Seed · Seed-OSS</span> | |
| <span class="lab-tag">Baidu · ERNIE 4.5, Qianfan</span> | |
| <span class="lab-tag">Xiaomi · MiMo V2.x</span> | |
| <span class="lab-tag">BAAI · Emu3, Emu3.5</span> | |
| <span class="lab-tag">OpenBMB · MiniCPM</span> | |
| <span class="lab-tag">InternLM · S1</span> | |
| <span class="lab-tag">FreedomIntelligence · Pangu-R</span> | |
| <span class="lab-tag">+ 25 more labs</span> | |
| </div> | |
| </div> | |
| </div> | |
| <!-- VALUE PROPS --> | |
| <section> | |
| <div class="section-label">Why ModelDNA</div> | |
| <h2>More than a similarity score.</h2> | |
| <div class="props"> | |
| <div class="prop"> | |
| <div class="prop-icon">🧬</div> | |
| <h3>Deep Derivative Detection</h3> | |
| <p>We compare against 2,200+ verified architectures across 545 organizations. Identifies fine-tunes, distillations, and repackaged models that config checks miss.</p> | |
| </div> | |
| <div class="prop"> | |
| <div class="prop-icon">⚡</div> | |
| <h3>Two-Stage Analysis</h3> | |
| <p>Stage 1 screens architecture configs instantly (free, unlimited). Stage 2 computes five weight-level signals for definitive lineage determination.</p> | |
| </div> | |
| <div class="prop"> | |
| <div class="prop-icon">📋</div> | |
| <h3>Audit-Ready Output</h3> | |
| <p>Pro plans export SBOM-compatible reports and PDF audit trails with lineage origin, technique provenance, and compliance verdict — ready for governance review.</p> | |
| </div> | |
| </div> | |
| </section> | |
| <!-- TERMINAL DEMO --> | |
| <section> | |
| <div class="section-label">Live Example</div> | |
| <h2>See the analysis in action.</h2> | |
| <p style="color:var(--text-dim);font-size:0.85rem;margin-bottom:1.5rem;">Stage 1 output is live today. Stage 2 weight analysis shown below is a roadmap preview.</p> | |
| <div class="terminal"> | |
| <div class="terminal-bar"><div class="dot dot-r"></div><div class="dot dot-y"></div><div class="dot dot-g"></div></div> | |
| <pre><span class="t-cmd">$ modeldna scan poolside/Laguna-XS.2</span> | |
| <span class="t-dim">[INIT] Connecting to ModelAtlas reference database (2,241 models)</span> | |
| <span class="t-dim">[SCAN] Fetching config.json...</span> | |
| <span class="t-pass">── STAGE 1: Architectural Screening ──────────────────────────</span> | |
| <span class="t-key"> Architecture: </span><span class="t-val">LagunaForCausalLM</span> | |
| <span class="t-key"> Hidden size: </span><span class="t-val">2048</span> | |
| <span class="t-key"> Vocab size: </span><span class="t-val">100,352</span> | |
| <span class="t-key"> Lineage family: </span><span class="t-val">GQA+SWA Hybrid</span> | |
| <span class="t-key"> Stage 1 verdict: </span><span class="t-val">SIMILAR DESIGN → proceed to Stage 2</span> | |
| <span class="t-pass">── STAGE 2: Weight-Level DNA Fingerprint ─────────────────────</span> | |
| <span class="t-key"> EAS Embedding anchor similarity: </span><span class="t-val">0.12</span> <span class="t-dim">▪▪░░░░░░░░ low</span> | |
| <span class="t-key"> END Norm distribution: </span><span class="t-val">0.31</span> <span class="t-dim">▪▪▪░░░░░░░ low</span> | |
| <span class="t-key"> NLF Norm layer fingerprint: </span><span class="t-val">0.28</span> <span class="t-dim">▪▪░░░░░░░░ low</span> | |
| <span class="t-key"> LEP Layer energy profile: </span><span class="t-val">0.41</span> <span class="t-dim">▪▪▪▪░░░░░░ moderate</span> | |
| <span class="t-key"> WVC Weight cosine: </span><span class="t-val">0.18</span> <span class="t-dim">▪░░░░░░░░░ low</span> | |
| <span class="t-verdict">── VERDICT ────────────────────────────────────────────────────</span> | |
| <span class="t-key"> Composite DNA Score: </span><span class="t-verdict">0.26 / 1.00</span> | |
| <span class="t-key"> Classification: </span><span class="t-verdict">ARCHITECTURAL INSPIRATION (not weight-derived)</span> | |
| <span class="t-key"> Lineage: </span><span class="t-val">GQA+SWA Hybrid — adopted pattern from StepFun (Feb 2026)</span> | |
| <span class="t-key"> Weights: </span><span class="t-val">INDEPENDENT — different vocab rules out tokenizer inheritance</span> | |
| <span class="t-pass"> ✓ No weight inheritance detected</span> | |
| <span class="t-dim">Report saved: ./modeldna-report-laguna-xs2.json</span> | |
| <span class="t-dim">Powered by ModelAtlas · modeldna.ai · a RadicalNotion product</span></pre> | |
| </div> | |
| </section> | |
| <!-- HOW IT WORKS --> | |
| <section id="how"> | |
| <div class="section-label">Process</div> | |
| <h2>Two stages. One verdict.</h2> | |
| <div class="steps"> | |
| <div class="step"> | |
| <div class="step-num">1</div> | |
| <h3>Architecture Screening</h3> | |
| <p>We parse the model config to identify architecture family, vocab, and technique signatures. Resolves the majority of cases instantly.</p> | |
| <span class="step-tag">FREE · UNLIMITED · <3s</span> | |
| </div> | |
| <div class="step"> | |
| <div class="step-num">2</div> | |
| <h3>Weight-Level Analysis <span style="font-size:0.7rem;background:rgba(101,212,35,0.15);border:1px solid rgba(101,212,35,0.3);color:var(--accent);padding:0.1rem 0.5rem;border-radius:4px;vertical-align:middle;font-weight:600;">ROADMAP</span></h3> | |
| <p>Five statistical signals (EAS, END, NLF, LEP, WVC) will analyze weight distributions to detect derivative relationships configs can't reveal.</p> | |
| <span class="step-tag">STAGE 2 · Coming soon</span> | |
| </div> | |
| <div class="step"> | |
| <div class="step-num">3</div> | |
| <h3>Enriched Verdict</h3> | |
| <p>Composite DNA score, lineage classification, and optional ModelAtlas enrichment — VRAM estimates, ARS scores, and technique origin chain.</p> | |
| <span class="step-tag">PRO · JSON / PDF / SBOM</span> | |
| </div> | |
| </div> | |
| </section> | |
| <!-- PRICING --> | |
| <section id="pricing"> | |
| <div class="section-label">Pricing</div> | |
| <h2>Developer-priced. Enterprise-capable.</h2> | |
| <p style="color:var(--text-dim); font-size:0.9rem; margin-top:0.5rem;">The ModelAtlas knowledge engine runs on RadicalNotion infrastructure. You get enterprise-grade depth at a fraction of incumbent pricing.</p> | |
| <p style="color:var(--text-dim);font-size:0.82rem;margin-top:0.75rem;">All scanning is Stage 1 — architecture screening from config.json only. No weight download required. <span style="color:var(--accent);">Stage 2 weight-level analysis is on the roadmap.</span></p> | |
| <div class="plans" style="margin-top:2rem;grid-template-columns:repeat(auto-fit,minmax(260px,1fr));"> | |
| <div class="plan"> | |
| <div class="plan-name">Free</div> | |
| <div class="plan-price">$0<span>/mo</span></div> | |
| <p style="font-size:0.78rem;color:var(--text-dim);margin-bottom:0.75rem;">For anyone using open weights on HuggingFace.</p> | |
| <ul> | |
| <li>Unlimited Stage 1 scanning — all public HF models</li> | |
| <li>Architecture family identification</li> | |
| <li>Claim validation — flags unverifiable assertions</li> | |
| <li>Derivative discovery — find models sharing your base</li> | |
| <li>JSON output</li> | |
| </ul> | |
| <a href="https://huggingface.co/spaces/RadicalNotionAI/modeldna" target="_blank" class="plan-btn">Start Scanning</a> | |
| </div> | |
| <div class="plan featured"> | |
| <div class="plan-badge">For AI Infrastructure Engineers</div> | |
| <div class="plan-name">Pro</div> | |
| <div class="plan-price">$199<span>/mo</span></div> | |
| <p style="font-size:0.78rem;color:var(--text-dim);margin-bottom:0.75rem;">For MLOps and AI platform teams vetting models at scale.</p> | |
| <ul> | |
| <li>Everything in Free</li> | |
| <li>Full API access — bulk scanning for pipelines</li> | |
| <li>ModelAtlas enrichment — VRAM, ARS, technique chain</li> | |
| <li>Derivative alerts — notified when copies appear</li> | |
| <li>PDF + SBOM audit export for compliance review</li> | |
| <li>5 team seats + priority support</li> | |
| </ul> | |
| <a href="#" class="plan-btn">Get Pro</a> | |
| </div> | |
| <div class="plan"> | |
| <div class="plan-name">Custom</div> | |
| <div class="plan-price" style="font-size:1.4rem;">Contact Us</div> | |
| <p style="font-size:0.78rem;color:var(--text-dim);margin-bottom:0.75rem;">For open weight hosters, compliance teams, and enterprises.</p> | |
| <ul> | |
| <li>Everything in Pro</li> | |
| <li>Private model ingestion + on-premise deployment</li> | |
| <li>Custom ModelAtlas reference databases</li> | |
| <li>Automated moderation for model hosting platforms</li> | |
| <li>SLA guarantees + dedicated engineering</li> | |
| </ul> | |
| <a href="mailto:tim@radicalnotion.ai" class="plan-btn">Contact Sales</a> | |
| </div> | |
| </div> | |
| </section> | |
| <!-- FAQ --> | |
| <section id="faq"> | |
| <div class="section-label">Honest Answers</div> | |
| <h2>What modeldna does — and doesn't.</h2> | |
| <div class="faqs"> | |
| <div class="faq"> | |
| <h3>Does this detect backdoors or malware?</h3> | |
| <p>No. modeldna analyzes statistical fingerprints for provenance and derivative lineage. We do not perform security vulnerability scanning or malware detection. These are different problems requiring different tools.</p> | |
| </div> | |
| <div class="faq"> | |
| <h3>Is this cryptographic proof of ownership?</h3> | |
| <p>No. Our results are based on statistical fingerprinting — high-confidence evidence of lineage, not cryptographic signatures. Results are suitable for compliance review and audit documentation but not legal disputes over IP ownership.</p> | |
| </div> | |
| <div class="faq"> | |
| <h3>How does the ModelAtlas reference database work?</h3> | |
| <p>ModelAtlas continuously scans and indexes public model releases, extracting architecture signatures, technique taxonomies, and lineage relationships. The reference database is private and updated weekly. The CLI queries it via API — you never see the raw database.</p> | |
| </div> | |
| <div class="faq"> | |
| <h3>Can I scan quantized models (GGUF, AWQ, FP8)?</h3> | |
| <p>Stage 1 works on any model with a config.json. Stage 2 weight analysis requires dequantization to BF16 first — this is handled automatically for supported formats. GGUF Q4/Q8 and safetensors FP8 are supported; AWQ/GPTQ support is in development.</p> | |
| </div> | |
| </div> | |
| </section> | |
| <!-- FOOTER --> | |
| <footer> | |
| <div class="footer-brand">modeldna.ai · powered by ModelAtlas · a RadicalNotion product</div> | |
| <div class="footer-links"> | |
| <a href="#">Documentation</a> | |
| <a href="#">API Reference</a> | |
| <a href="#">Status</a> | |
| <a href="#">Privacy Policy</a> | |
| <a href="#">Terms of Service</a> | |
| <a href="https://radicalnotion.ai">RadicalNotion.ai</a> | |
| </div> | |
| <div class="footer-copy">© 2026 RadicalNotion.ai. All rights reserved.</div> | |
| </footer> | |
| </body> | |
| </html> | |