Update tagline: Various LoRA adapters. One shared basis.

Author: tveseli

README.md

@@ -3,10 +3,10 @@
 </p>
 
 <p align="center">
-  <strong>Shared low-rank subspaces for efficient LoRA adapter management.</strong>
+  <strong>Various LoRA adapters. One shared basis.</strong>
 </p>
 
-Based on the [Share paper](https://arxiv.org/abs/2602.06043): LoRA adapters across tasks share a common low-rank subspace. Instead of storing *N* separate adapters, maintain **one shared basis** and **per-task coefficient vectors** — achieving up to 122× compression at scale.
+Your adapters share more structure than you think. vLoRA finds the common basis and stores each adapter as a tiny coefficient vector — up to 122× compression at scale. Based on the [Share paper](https://arxiv.org/abs/2602.06043).
 
 ## Install
 

docs/index.md

@@ -1,8 +1,8 @@
 # vlora
 
-**Shared low-rank subspaces for efficient LoRA adapter management.**
+**Various LoRA adapters. One shared basis.**
 
-Based on the [Share paper](https://arxiv.org/abs/2602.06043): LoRA adapters across tasks share a common low-rank subspace. Instead of storing *N* separate adapters, maintain **one shared basis** and **per-task coefficient vectors** — achieving up to 122× compression at scale.
+Your adapters share more structure than you think. vLoRA finds the common basis and stores each adapter as a tiny coefficient vector — up to 122× compression at scale. Based on the [Share paper](https://arxiv.org/abs/2602.06043).
 
 ## Install
 

pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "hatchling.build"
 [project]
 name = "vlora-dev"
 version = "0.2.1"
-description = "Shared low-rank subspaces for efficient LoRA adapter management"
+description = "Various LoRA adapters. One shared basis. Up to 122x compression at scale."
 readme = "README.md"
 license = "Apache-2.0"
 requires-python = ">=3.9"

website/public/og-card.png

@@ -8,7 +8,7 @@ const currentYear = new Date().getFullYear();
       <!-- Logo -->
       <div class="flex flex-col items-center md:items-start gap-2">
         <img src="/logo.png" alt="vLoRA" class="h-8" />
-        <p class="text-sm text-navy-muted">Shared low-rank subspaces for efficient LoRA adapter management.</p>
+        <p class="text-sm text-navy-muted">Various LoRA adapters. One shared basis.</p>
       </div>
 
       <!-- Links -->

website/src/components/Footer.astro

@@ -17,13 +17,13 @@
 
       <!-- Tagline -->
       <h1 class="text-3xl md:text-4xl lg:text-5xl font-bold tracking-tight mb-4 text-balance">
-        Shared low-rank subspaces for efficient
-        <span class="gradient-text">LoRA adapter management.</span>
+        Various LoRA adapters.
+        <span class="gradient-text">One shared basis.</span>
       </h1>
 
       <!-- Sub-tagline -->
       <p class="max-w-2xl text-lg md:text-xl text-navy-muted mb-10 text-balance">
-        One shared basis. Per-task coefficients. Up to <strong class="text-magenta font-semibold">122× compression</strong> at scale.
+        Your adapters share more structure than you think. vLoRA finds the common basis and stores each adapter as a tiny coefficient vector — up to <strong class="text-magenta font-semibold">122× compression</strong> at scale.
       </p>
 
       <!-- Install command -->

website/src/components/Hero.astro

@@ -5,8 +5,8 @@ interface Props {
 }
 
 const {
-  title = "vLoRA — Shared low-rank subspaces for efficient LoRA adapter management",
-  description = "One shared basis. Per-task coefficients. Up to 122× compression at scale. Open-source Python library based on arXiv:2602.06043."
+  title = "vLoRA — Various LoRA adapters. One shared basis.",
+  description = "Your adapters share more structure than you think. vLoRA finds the common basis and stores each adapter as a tiny coefficient vector — up to 122× compression at scale."
 } = Astro.props;
 ---