Model Card for Wiguel-AI Core Engine
This Model Card details the integration, features, and usage of the main artificial intelligence model used in the Wiguel-AI application, supported by an intelligent local execution and offline fallback system.
Model Details
The Wiguel-AI engine is a highly efficient and low-latency conversational model. It is highly optimized for local processing directly on the user's device, ensuring excellent performance and maximum privacy.
In this implementation, it works as follows:
- Local Mode (In-Browser/WebGPU): Executes artificial intelligence processing and weights storage via WebWorker and WebGPU directly on your machine. Everything happens within the browser without sending any data to the cloud or central servers.
- Hybrid/Bridge Mode: By using the local connection script, the system can expand its capabilities to interact locally, manage model downloads, and ensure absolute and uninterrupted availability of your AI assistant.
AI URL
You can access the application at the following link: https://wiguel-ai.vercel.app/
How It Works
This model is used as the conversational brain of Wiguel-AI to:
- Answer direct queries quickly.
- Serve as an interactive assistant through a Progressive Web App (PWA) web interface.
- Process natural language keeping all context private and secure.
- Operate offline once the necessary files have been temporarily stored or cached.
The ecosystem encapsulates this model in asynchronous workflows and real-time streams, allowing fluent text generation.
1. Wiguel-AI
How to use: Wiguel-AI is designed to be a personal assistant that runs directly in your browser or through a local bridge for greater system access. To use the AI functionality, the interface connects seamlessly and downloads the resources needed to operate. All computation is optimized so as not to depend on large data centers when using offline mode.
Bridge Link (Wiguel Bridge): For advanced capabilities and local environment control, Wiguel-AI uses a bridge script. This bridge allows the application to securely communicate with local resources, handle background downloads, and provide offline inference without complications.
You can download the synchronization script from here: wiguel-bridge.py (GitHub)
Once downloaded, place it in your working folder and run it in your terminal:
python wiguel-bridge.py
The bridge script will start a local server that will automatically communicate with the Wiguel-AI web interface. Furthermore, when necessary, the bridge automatically downloads the model to your machine in the background, allows you to chat offline, and at the end of the session when closing the process, it performs an automatic cleanup to delete temporary files and the downloaded model from your hard drive.