VELMA Project Page

This repository contains the source code for the official project page of VELMA (Vision-Enabled Large Multilingual Model for All). The website is designed to highlight the paper's core contributions, modular model architecture, benchmark evaluations, and interactive qualitative case studies.

The page is hosted on GitHub Pages at:
👉 https://RISys-Lab.github.io/VELMA-Page

---

📁 Repository Structure

├── assets/                  # Images used in qualitative case studies
├── index.html               # Main entrypoint of the project page (HTML, Tailwind CSS, JS)
└── README.md                # Project page documentation (this file)

---

💻 Local Development

Since the page uses a Tailwind CSS CDN and is written in vanilla HTML/JavaScript, it can be run locally without any compilation. To avoid CORS issues when loading image assets, it is recommended to run the page using a lightweight local web server.

Option 1: Python (Built-in)

If you have Python installed, run this command in your terminal:

python3 -m http.server 8000

Then open your browser and navigate to: http://localhost:8000

Option 2: Node.js / npm

If you prefer Node.js, you can use npx to spin up a quick server:

npx serve .

Then navigate to the URL provided in the console (usually http://localhost:3000 or http://localhost:5000).

---

🚀 Hosting on GitHub Pages

Follow these steps to host this project page on GitHub:

1. Create a GitHub Repository: Create a new public repository on GitHub (e.g., VELMA-Page).
2. Push the Code:

   git init
   git add .
   git commit -m "Initial commit of VELMA project page"
   git branch -M main
   git remote add origin https://github.com/<username>/VELMA-Page.git
   git push -u origin main

3. Enable GitHub Pages:
   • Go to your repository page on GitHub.
   • Click on Settings (gear icon) -> Pages in the left sidebar.
   • Under Build and deployment -> Source, select Deploy from a branch.
   • Under Branch, select main and / (root), then click Save.
4. View the Site: Within a few minutes, GitHub Actions will deploy your page. It will be accessible at:
   https://<your-username>.github.io/VELMA-Page/

---

📝 Acknowledgments

• Computing Resources: We acknowledge the EuroHPC Joint Undertaking for awarding access to the Leonardo supercomputer hosted at CINECA, Italy.