RWKV Explainer: Interactive Learning of Text-Generative Models

RWKV Explainer is an interactive visualization tool designed to help anyone understand how RNN-based models like RWKV-4 work. It runs a live RWKV-4 model directly in your browser, allowing you to experiment with your own text and observe in real time how the internal components and operations of RWKV collaborate to predict the next tokens.

Try RWKV Explainer at http://playaswd.github.io/rwkv-explainer.

How to run locally

Prerequisites

• Node.js v20 or higher
• NPM v10 or higher

Steps

git clone https://github.com/playaswd/rwkv-explainer.git
cd rwkv-explainer
npm install
npm run dev

Then, on your web browser, access http://localhost:5173.

Credits

RWKV Explainer was developed by Ding Wang, based on the open-source transformer-explainer and rwkv-v4-web. It adapts the original by replacing GPT with RWKV, updating diagrams and logic, while keeping a similar UI and interactive features.

License

The software is available under the MIT License.

Contact

If you have any questions, feel free to open an issue.