Upload docs/index.html with huggingface_hub

Browse files

Files changed (1) hide show

docs/index.html +7 -7

docs/index.html CHANGED Viewed

@@ -3,17 +3,17 @@
 <head>
   <meta charset="UTF-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Pico-Type — Tiny, Byte-Level Content Classifier (1.5M params, 95.2% accuracy)</title>
-  <meta name="description" content="Pico-Type is a 1.5M-parameter byte-level multi-head classifier that identifies code language, content type, and more from raw bytes — no parsing needed. 95.2% real-world accuracy, ONNX export, open source." />
   <meta name="keywords" content="pico-type, byte-level classifier, content classification, machine learning, tiny model, open source, code language detection, multi-head classifier" />
   <meta property="og:title" content="Pico-Type — Tiny Byte-Level Content Classifier" />
-  <meta property="og:description" content="1.5M parameters, 95.2% real-world accuracy. Classifies raw bytes into code language, content modality, subtype, and more. No parsing, no dependencies." />
   <meta property="og:url" content="https://eulogik.github.io/pico-type/" />
   <meta property="og:type" content="website" />
   <meta property="og:image" content="https://eulogik.github.io/pico-type/logo.png" />
   <meta name="twitter:card" content="summary_large_image" />
   <meta name="twitter:title" content="Pico-Type — Tiny Byte-Level Content Classifier" />
-  <meta name="twitter:description" content="1.5M parameters, 95.2% real-world accuracy. Classifies raw bytes into code language, content modality, subtype, and more. Open source." />
   <link rel="canonical" href="https://eulogik.github.io/pico-type/" />
   <link rel="icon" type="image/x-icon" href="favicon.ico" />
   <link rel="icon" type="image/png" href="logo.png" />
@@ -236,7 +236,7 @@
   <!-- Stats -->
   <div class="stats container">
     <div><div class="stat-value">1.5M</div><div class="stat-label">Parameters</div></div>
-    <div><div class="stat-value">95.2%</div><div class="stat-label">Real-World Accuracy</div></div>
     <div><div class="stat-value">62</div><div class="stat-label">Code Languages</div></div>
     <div><div class="stat-value">7</div><div class="stat-label">Classification Heads</div></div>
     <div><div class="stat-value">2KB</div><div class="stat-label">Context Window</div></div>
@@ -318,9 +318,9 @@
     <!-- Real-world accuracy -->
     <section>
-      <h2>Real-World Accuracy: 20/21 (95.2%)</h2>
       <p style="text-align:center;color:var(--text-muted);margin-bottom:32px;">
-        Tested against a hand-curated set covering every coarse type &mdash; from Python and JavaScript to ZIP binaries and Hindi text.
       </p>
       <div class="table-wrap">
         <table>

 <head>
   <meta charset="UTF-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+  <title>Pico-Type — Tiny, Byte-Level Content Classifier (1.5M params, 98.3% text-lang accuracy)</title>
+  <meta name="description" content="Pico-Type is a 1.5M-parameter byte-level multi-head classifier that identifies code language, content type, and more from raw bytes — no parsing needed. 98.3% text-lang accuracy, ONNX export, open source." />
   <meta name="keywords" content="pico-type, byte-level classifier, content classification, machine learning, tiny model, open source, code language detection, multi-head classifier" />
   <meta property="og:title" content="Pico-Type — Tiny Byte-Level Content Classifier" />
+  <meta property="og:description" content="1.5M parameters, 98.3% text-lang accuracy. Classifies raw bytes into code language, content modality, subtype, and more. No parsing, no dependencies." />
   <meta property="og:url" content="https://eulogik.github.io/pico-type/" />
   <meta property="og:type" content="website" />
   <meta property="og:image" content="https://eulogik.github.io/pico-type/logo.png" />
   <meta name="twitter:card" content="summary_large_image" />
   <meta name="twitter:title" content="Pico-Type — Tiny Byte-Level Content Classifier" />
+  <meta name="twitter:description" content="1.5M parameters, 98.3% text-lang accuracy. Classifies raw bytes into code language, content modality, subtype, and more. Open source." />
   <link rel="canonical" href="https://eulogik.github.io/pico-type/" />
   <link rel="icon" type="image/x-icon" href="favicon.ico" />
   <link rel="icon" type="image/png" href="logo.png" />
   <!-- Stats -->
   <div class="stats container">
     <div><div class="stat-value">1.5M</div><div class="stat-label">Parameters</div></div>
+    <div><div class="stat-value">98.3%</div><div class="stat-label">Text-Lang Accuracy</div></div>
     <div><div class="stat-value">62</div><div class="stat-label">Code Languages</div></div>
     <div><div class="stat-value">7</div><div class="stat-label">Classification Heads</div></div>
     <div><div class="stat-value">2KB</div><div class="stat-label">Context Window</div></div>
     <!-- Real-world accuracy -->
     <section>
+      <h2>Real-World Accuracy: 60.3% code lang · 98.3% text lang</h2>
       <p style="text-align:center;color:var(--text-muted);margin-bottom:32px;">
+        Evaluated on real-world corpora &mdash; The Heap (1,200 code samples, 24 languages) and Wikipedia (1,500 articles, 30 languages).
       </p>
       <div class="table-wrap">
         <table>