Files
skills/public/hanzo-jin.html
zeekayandHanzo Dev 9e10c1c10e Each llms index points at the other two
hanzoskills.com/llms.txt now opens with the install line, the API
reference index and the company index, so an agent that lands on any
one of the three can find the rest.

robots.txt claimed 537 documents while llms.txt counts 920. The number
is gone from robots.txt; llms.txt derives it.

public/ is regenerated from scripts/site.py, which it had fallen
behind: the copy-prompt menu and agent bar were in the generator and
not in the committed pages. tests/site.mjs passes against the result.

Co-authored-by: Hanzo Dev <[email protected]>
2026-09-11 00:27:59 -07:00

339 lines
20 KiB
HTML

<!doctype html>
<html lang="en"><head>
<meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
<title>hanzo-jin</title>
<meta name="color-scheme" content="dark">
<style>
/* Committed to one visual world: a dark instrument panel. No light variant —
the dot field and the hairline rules only read on black, and a naive
inversion would wash both out. Every colour is painted explicitly so the page
never borrows a host background. */
@font-face{font-family:'Zen';src:url('/fonts/Zen-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen';src:url('/fonts/Zen-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Pixel Square';src:url('/fonts/ZenPixel-Square.woff2') format('woff2');font-style:normal;font-display:swap}
:root{
--ink:#f4f4f2; --soft:#9c9c98; --faint:#6a6a66; --ground:#000; --panel:#0a0a0a;
--line:#232323; --line-hi:#3a3a3a; --accent:#f4f4f2;
--font-zen-sans:'Zen',-apple-system,BlinkMacSystemFont,"Segoe UI",Helvetica,Arial,sans-serif;
--font-zen-mono:'Zen Mono',ui-monospace,"SF Mono",SFMono-Regular,Menlo,Consolas,monospace;
--font-zen-pixel-square:'Zen Pixel Square',monospace;
--mono:var(--font-zen-mono);
--sans:var(--font-zen-sans);
/* Controls are pills and surfaces are soft, as on hanzo.ai. */
--r:999px; --r-soft:14px;
}
*{box-sizing:border-box}
html{-webkit-text-size-adjust:100%}
body{margin:0;background:var(--ground);color:var(--ink);font-family:var(--sans);
font-size:16px;line-height:1.65;-webkit-font-smoothing:antialiased}
.wrap{max-width:60rem;margin:0 auto;padding:0 1.75rem}
/* The dot field. A halftone made of one repeating radial-gradient, faded out
along the diagonal by a mask so it reads as a wave rather than wallpaper. */
/* No overflow clip here: the dot field is inset to the box already, and a clip
would cut off the copy-prompt menu. */
.hero{position:relative;border-bottom:1px solid var(--line)}
.hero::before{content:"";position:absolute;inset:0;
background-image:radial-gradient(var(--line-hi) 1px, transparent 1px);
background-size:7px 7px;
-webkit-mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
pointer-events:none}
.hero .wrap{position:relative;padding-top:5.5rem;padding-bottom:4rem}
nav{border-bottom:1px solid var(--line)}
nav .in{max-width:60rem;margin:0 auto;padding:1.1rem 1.75rem;display:flex;
justify-content:space-between;align-items:center;gap:1rem}
.brand{font-family:var(--mono);font-size:.85rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--ink);text-decoration:none;
display:inline-flex;align-items:center;gap:.6rem}
.brand i{font-style:normal;color:var(--faint)}
.mark{width:1.15em;height:1.15em;display:block;flex:0 0 auto}
nav a.up{font-family:var(--mono);font-size:.72rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--soft);text-decoration:none}
nav a.up:hover{color:var(--ink)}
h1{font-family:var(--mono);font-size:clamp(2rem,5.4vw,3.4rem);line-height:1.12;
letter-spacing:-.02em;margin:0 0 1.1rem;font-weight:500;text-wrap:balance}
h1 em{font-style:normal;color:var(--faint)}
.lede{color:var(--soft);font-size:1.05rem;max-width:52ch;margin:0 0 2.25rem}
.btns{display:flex;flex-wrap:wrap;gap:.7rem;margin:0 0 .5rem;align-items:center}
.btn{display:inline-flex;align-items:center;gap:.5rem;font-family:var(--mono);
font-size:.72rem;letter-spacing:.14em;text-transform:uppercase;
padding:.8rem 1.4rem;border:1px solid var(--line-hi);border-radius:var(--r);
color:var(--ink);text-decoration:none;background:transparent;cursor:pointer;
line-height:1.2;font-weight:400}
.btn:hover{background:#141414;text-decoration:none;border-color:var(--soft)}
.btn.solid{background:var(--ink);color:#000;border-color:var(--ink)}
.btn.solid:hover{background:#d8d8d4}
.btn .chev{width:.7em;height:.7em;flex:0 0 auto;transition:transform .15s ease}
.btn[aria-expanded="true"] .chev{transform:rotate(180deg)}
/* Copy-prompt selector. Each row copies the prompt for its own target. */
.copy{position:relative;display:inline-flex}
.menu{position:absolute;top:calc(100% + .5rem);left:0;z-index:20;min-width:21rem;
background:var(--panel);border:1px solid var(--line-hi);border-radius:var(--r-soft);
padding:.4rem;display:flex;flex-direction:column;
box-shadow:0 12px 32px rgba(0,0,0,.75)}
.menu[hidden]{display:none}
.mi{display:flex;align-items:center;gap:.7rem;width:100%;text-align:left;
padding:.62rem .8rem;border:0;border-radius:calc(var(--r-soft) - .35rem);
background:transparent;color:var(--ink);font-family:var(--mono);font-size:.76rem;
letter-spacing:.04em;text-decoration:none;cursor:pointer;line-height:1.3;
white-space:nowrap}
.mi:hover,.mi:focus-visible{background:#181818;outline:none}
.mi .mark{width:1.05rem;height:1.05rem;color:var(--soft)}
.mi:hover .mark{color:var(--ink)}
.mi u{margin-left:auto;color:var(--faint);text-decoration:none;font-size:.68rem;
letter-spacing:.1em;text-transform:uppercase}
/* Works-with bar: one scrolling row, name and mark per agent. */
.strip{border-bottom:1px solid var(--line);background:var(--panel)}
.strip .in{max-width:60rem;margin:0 auto;padding:.9rem 1.75rem;display:flex;
align-items:center;gap:1.25rem;font-family:var(--mono);font-size:.72rem;
letter-spacing:.1em;text-transform:uppercase;color:var(--faint)}
.strip b{color:var(--soft);font-weight:400;flex:0 0 auto;
border-right:1px solid var(--line);padding-right:1.25rem;align-self:stretch;
display:flex;align-items:center}
.bar{display:flex;align-items:center;gap:.5rem;flex:1 1 auto;min-width:0;
overflow-x:auto;scrollbar-width:none;scroll-snap-type:x proximity;
-webkit-overflow-scrolling:touch;
-webkit-mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent);
mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent)}
.bar::-webkit-scrollbar{display:none}
.agent{display:inline-flex;align-items:center;gap:.45rem;flex:0 0 auto;
padding:.4rem .85rem;border:1px solid var(--line);border-radius:var(--r);
color:var(--soft);white-space:nowrap;scroll-snap-align:start;
text-decoration:none;background:var(--ground)}
.agent:hover{color:var(--ink);border-color:var(--line-hi);text-decoration:none}
.agent .mark{width:.95rem;height:.95rem}
h2{font-family:var(--mono);font-size:1.1rem;letter-spacing:-.01em;margin:2.75rem 0 .75rem;font-weight:500}
h3{font-size:1rem;margin:2rem 0 .5rem;font-weight:600}
h4,h5,h6{font-size:.94rem;margin:1.5rem 0 .5rem;font-weight:600}
p{margin:0 0 1rem;max-width:70ch}
ul,ol{margin:0 0 1rem;padding-left:1.35rem;max-width:70ch}
li{margin:.22rem 0}
a{color:var(--ink);text-decoration:underline;text-underline-offset:3px;
text-decoration-color:var(--line-hi)}
a:hover{text-decoration-color:var(--ink)}
a:focus-visible{outline:1px solid var(--ink);outline-offset:3px}
code{font-family:var(--mono);font-size:.85em;background:var(--panel);
border:1px solid var(--line);border-radius:5px;padding:.1em .36em}
pre{background:var(--panel);border:1px solid var(--line);padding:1rem 1.1rem;
border-radius:var(--r-soft);overflow-x:auto;margin:0 0 1.25rem}
pre code{background:none;border:0;padding:0;font-size:.82rem;line-height:1.7}
blockquote{margin:0 0 1rem;padding-left:1rem;border-left:1px solid var(--line-hi);color:var(--soft)}
hr{border:0;border-top:1px solid var(--line);margin:2.5rem 0}
table{border-collapse:collapse;width:100%;margin:0 0 1.25rem;font-size:.92rem;
display:block;overflow-x:auto}
th,td{border:1px solid var(--line);padding:.5rem .7rem;text-align:left}
.curl{display:block;background:var(--panel);border:1px solid var(--line);
border-radius:var(--r-soft);padding:.95rem 1.1rem;font-family:var(--mono);
font-size:.8rem;color:var(--soft);overflow-x:auto;margin:0 0 2.5rem;
white-space:pre;line-height:1.9}
.curl b{color:var(--ink);font-weight:400}
.curl i{font-style:normal;color:var(--faint)}
/* index */
#q{width:100%;padding:.85rem 1.2rem;font-family:var(--mono);font-size:.85rem;color:var(--ink);
background:var(--panel);border:1px solid var(--line);border-radius:var(--r);margin:0 0 .6rem}
#q::placeholder{color:var(--faint);text-transform:uppercase;letter-spacing:.1em;font-size:.72rem}
#q:focus{outline:none;border-color:var(--soft)}
#count{color:var(--faint);font-family:var(--mono);font-size:.72rem;letter-spacing:.1em;
text-transform:uppercase;margin:0 0 2rem}
.cat{margin:2.5rem 0 .5rem;font-family:var(--mono);font-size:.7rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);border-bottom:1px solid var(--line);
padding-bottom:.45rem}
.row{display:block;padding:.6rem .9rem;margin:0 -.9rem;border-bottom:1px solid var(--line);
border-radius:var(--r-soft);text-decoration:none}
.row:hover{background:#0a0a0a}
.nm{font-family:var(--mono);font-size:.84rem;color:var(--ink);display:block}
.ds{color:var(--soft);font-size:.9rem;display:block;margin-top:.12rem}
footer{margin-top:4rem;padding:2rem 0 4rem;border-top:1px solid var(--line);
color:var(--faint);font-size:.85rem}
footer a{color:var(--soft)}
.fmap{display:grid;gap:1.75rem;grid-template-columns:repeat(auto-fit,minmax(11rem,1fr));
margin:0 0 2rem;font-size:.85rem}
.fmap b{display:block;font-family:var(--mono);font-size:.68rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);font-weight:400;margin:0 0 .6rem;
border-bottom:1px solid var(--line);padding-bottom:.4rem}
.fmap a{display:inline-block;color:var(--ink);text-decoration:none;margin:.3rem .35rem 0 0}
.fmap a:hover{text-decoration:underline}
.fmap div{color:var(--faint);line-height:1.5}
.fend{border-top:1px solid var(--line);padding-top:1.25rem;font-size:.82rem}
@media (max-width:640px){
.hero .wrap{padding-top:3.25rem;padding-bottom:2.75rem}
.btns{gap:.5rem}
.btn{padding:.75rem 1.15rem;font-size:.68rem}
.copy,.copy .btn{width:100%;justify-content:center}
.menu{left:0;right:0;min-width:0}
.strip .in{flex-direction:column;align-items:flex-start;gap:.6rem;padding:.9rem 1.75rem}
.strip b{border-right:0;padding-right:0}
.bar{width:100%}
}
</style>
<link rel="alternate" type="text/markdown" href="/hanzo-jin.md">
<link rel="icon" href="/favicon.svg">
<link rel="canonical" href="https://hanzoskills.com/hanzo-jin">
</head>
<!-- Reading this with a machine? Every page here is also plain markdown.
This one: https://hanzoskills.com/hanzo-jin.md
Index: https://hanzoskills.com/llms.txt
Corpus: https://hanzoskills.com/all.md
Append .md to any path for the markdown twin. -->
<body>
<nav><div class="in">
<a class="brand" href="/"><svg class="mark" viewBox="0 0 67 67" fill="currentColor" aria-hidden="true"><path d="M22.21 67V44.6369H0V67H22.21Z"/><path d="M66.7038 22.3184H22.2534L0.0878906 44.6367H44.4634L66.7038 22.3184Z"/><path d="M22.21 0H0V22.3184H22.21V0Z"/><path d="M66.7198 0H44.5098V22.3184H66.7198V0Z"/><path d="M66.7198 67V44.6369H44.5098V67H66.7198Z"/></svg> HANZO<i>SKILLS</i></a>
<a class="up" href="/">All skills</a>
</div></nav>
<div class="wrap">
<h1>hanzo-jin</h1><p class="lede">Jin is a research-stage visual self-supervised learning framework implementing Joint Embedding Predictive Architectures (JEPA).</p><h1>Hanzo Jin - Visual Self-Supervised Learning Framework</h1>
<p><strong>Category</strong>: Hanzo Ecosystem <strong>Related Skills</strong>: <code>hanzo/hanzo-engine.md</code>, <code>hanzo/hanzo-candle.md</code>, <code>hanzo/zenlm.md</code></p>
<h2>Overview</h2>
<p>Jin is a <strong>research-stage visual self-supervised learning framework</strong> implementing Joint Embedding Predictive Architectures (JEPA). Python + PyTorch. Implements I-JEPA, Saccade JEPA (novel variant), and Self-Distillation MAE.</p>
<p><strong>NOTE</strong>: Jin is vision-only. The &quot;multimodal&quot; roadmap (text + audio + 3D) exists in grant proposals but is not yet implemented in code. Current codebase is image-patch JEPA training only — no inference API, no published weights.</p>
<h3>Why Jin?</h3>
<ul><li><strong>JEPA architecture</strong>: Self-supervised visual representation learning</li><li><strong>Novel Saccade JEPA</strong>: Inspired by mammalian saccadic eye movement</li><li><strong>Self-Distillation MAE</strong>: Masked autoencoder with DINO-style centering</li><li><strong>Energy I-JEPA</strong>: Alternative using Hopfield-based energy attention</li><li><strong>Research tool</strong>: Benchmarking, visualization, attention maps</li></ul>
<h3>OSS Base</h3>
<p>Originated from <strong>LumenPallidium/jepa</strong>, adopted under Zen LM org. Repo: <code>github.com/hanzoai/jin</code> (redirects to <code>zenlm/jin</code>). Package name: <code>jin-tac</code>.</p>
<h2>When to use</h2>
<ul><li>Research into visual self-supervised learning</li><li>Training JEPA models on image datasets (ImageNet)</li><li>Experimenting with novel JEPA variants</li><li>Benchmarking visual representation quality</li><li>NOT for production multimodal inference (not yet implemented)</li></ul>
<h2>Hard requirements</h2>
<ol><li><strong>Python 3.8+</strong> with PyTorch</li><li><strong>GPU recommended</strong> for training (ImageNet-scale)</li></ol>
<h2>Quick reference</h2>
<p>| Item | Value | |------|-------| | Language | Python (PyTorch) | | Package | <code>jin-tac</code> | | Repo | <code>github.com/hanzoai/jin</code> (→ <code>zenlm/jin</code>) | | Train | <code>python jepa/train.py</code> | | Config | <code>config/training.yml</code> |</p>
<h2>Model Variants (Implemented)</h2>
<p>| Model | Class | Backbone | Description | |-------|-------|----------|-------------| | I-JEPA | <code>ViTJepa</code> | ViT (Transformer) | Paper implementation (arXiv:2301.08243) | | Energy I-JEPA | <code>EnergyIJepa</code> | Energy Transformer | Hopfield-based energy attention | | Saccade JEPA | <code>SaccadeJepa</code> | ConvNeXT tiny | Novel: mammalian saccadic eye movement | | Self-Distillation MAE | <code>SelfDistillMAE</code> | ViT + cross-attention | Masked autoencoder with DINO centering |</p>
<h2>Architecture</h2>
<pre><code>┌─────────────────────────────────────────┐
│ Jin JEPA Architecture │
├──────────────────────────────────────────┤
│ │
│ Image ──▶ Patcher ──▶ Patch Embeddings │
│ ┌──────────┐ │
│ Context patches ──│ Context │ │
│ │ Encoder │── EMA ──▶ Target Encoder
│ └────┬─────┘ │
│ │ │
│ ┌────┴─────┐ │
│ │Predictor │ │
│ └────┬─────┘ │
│ │ │
│ Predict target embeddings │
│ from context embeddings │
│ │
│ Loss: MSE(predicted, target_stopped) │
│ + VICReg (variance + covariance) │
│ + Cycle consistency (Saccade only) │
└──────────────────────────────────────────┘</code></pre>
<h2>One-file quickstart</h2>
<pre><code class="lang-python"># Training (the only supported mode)
import yaml
from jepa.train import train
from jepa.jepa import ViTJepa
# Load config
with open(&quot;config/training.yml&quot;) as f:
config = yaml.safe_load(f)
# Create model
model = ViTJepa(
image_size=224,
patch_size=16,
embed_dim=768,
depth=12,
num_heads=12,
)
# Train on ImageNet
train(model, config)</code></pre>
<h3>Training Configuration (config/training.yml)</h3>
<pre><code class="lang-yaml">model:
type: &quot;vit_jepa&quot; # or &quot;saccade_jepa&quot;, &quot;energy_ijepa&quot;, &quot;self_distill_mae&quot;
image_size: 224
patch_size: 16
embed_dim: 768
depth: 12
num_heads: 12
training:
dataset: &quot;imagenet&quot;
batch_size: 128
gradient_accumulation: 128
learning_rate: 1.5e-4
warmup_epochs: 40
total_epochs: 300
weight_decay: 0.05
ema_momentum: 0.996 # Target encoder EMA
schedule:
type: &quot;cosine&quot;
min_lr: 1e-6</code></pre>
<h3>Saccade JEPA (Novel Variant)</h3>
<pre><code class="lang-python">from jepa.jepa import SaccadeJepa
model = SaccadeJepa(
image_size=224,
patch_size=16,
embed_dim=768,
# Uses ConvNeXT tiny backbone
# NeRF-like positional encoding of rotation/translation affine transforms
# VICReg loss + cycle consistency
)
# Cycle consistency: forward-backward saccade prediction must reconstruct original
# Mimics mammalian visual system&#x27;s saccadic eye movements</code></pre>
<h2>Evaluation</h2>
<p>| Method | Purpose | |--------|---------| | Linear probes | Evaluate frozen representations | | KNN (k-nearest neighbors) | Non-parametric evaluation | | Correlation dimension | Representation geometry | | UMAP visualization | Embedding space visualization | | Attention map dashboard | Interactive Dash visualization |</p>
<h2>Dependencies</h2>
<ul><li><code>torch</code>, <code>torchvision</code> — core framework</li><li><code>einops</code> — tensor operations</li><li><code>pyyaml</code> — config parsing</li><li><code>tqdm</code>, <code>numpy</code>, <code>matplotlib</code> — utilities</li><li><code>sklearn</code> (optional) — KNN evaluation</li><li><code>umap-learn</code> (optional) — visualization</li><li><code>energy_transformer</code> (optional) — for Energy I-JEPA variant</li></ul>
<h2>Project Structure</h2>
<pre><code>jin/
├── jepa/
│ ├── jepa.py # Core models (ViTJepa, SaccadeJepa, EnergyIJepa)
│ ├── masked_autoencoder.py # Self-Distillation MAE
│ ├── train.py # Training loop
│ ├── patcher.py # Image patch embedding (Conv, Hybrid, Conv3d)
│ ├── saccade.py # Saccade cropper (NeRF positional encoding)
│ └── vicreg.py # VICReg loss terms
├── config/
│ └── training.yml # Training configuration
├── papers/ # Research papers and grant proposals
├── pyproject.toml
└── LLM.md</code></pre>
<h2>Roadmap (Aspirational — NOT in code)</h2>
<p>Grant proposals describe future multimodal expansion:</p>
<ul><li>Text encoder (not implemented)</li><li>Audio encoder (not implemented)</li><li>Diffusion Transformer MoE (not implemented)</li><li>Cross-modal alignment (not implemented)</li></ul>
<h2>Related Skills</h2>
<ul><li><code>hanzo/hanzo-engine.md</code> - Inference engine (future: serve trained Jin models)</li><li><code>hanzo/hanzo-candle.md</code> - Rust ML framework</li><li><code>hanzo/zenlm.md</code> - Text-only Zen models</li><li><code>hanzo/hanzo-gym.md</code> - Training infrastructure</li></ul>
<hr>
<p><strong>Last Updated</strong>: 2026-03-13 <strong>Category</strong>: Hanzo Ecosystem <strong>Related</strong>: jepa, self-supervised, vision, research <strong>Prerequisites</strong>: Python, PyTorch, self-supervised learning concepts</p>
<footer>
<div class="fmap">
<div><b>Build</b>
<a href="https://hanzo.app">hanzo.app</a> app builder
<a href="https://hanzo.codes">hanzo.codes</a> code with an agent
<a href="https://hanzoskills.com">hanzoskills.com</a> what an agent reads</div>
<div><b>Run</b>
<a href="https://console.hanzo.ai">console.hanzo.ai</a> cloud console
<a href="https://api.hanzo.ai">api.hanzo.ai</a> the API</div>
<div><b>Account</b>
<a href="https://hanzo.id">hanzo.id</a> sign in
<a href="https://pay.hanzo.ai">pay.hanzo.ai</a> top up
<a href="https://billing.hanzo.ai">billing.hanzo.ai</a> invoices and usage</div>
<div><b>Company</b>
<a href="https://hanzo.ai">hanzo.ai</a> canonical
<a href="https://hanzo.ventures">hanzo.ventures</a> ventures</div>
</div>
<div class="fend"><a href="/hanzo-jin.md">This page as plain text</a> · <a href="/llms.txt">Index for agents</a></div>
</footer>
</div></body></html>