Fine Tuning Gemma-3 using Flower Federated Learning

This repository contains the code for tuning Gemma 3 using Flower, the federated learning framework

=======

gemma-3-fine-tuning: A Flower / PyTorch app

Install dependencies and project

pip install -e .

Run with the Simulation Engine

In the gemma-3-fine-tuning directory, use flwr run to run a local simulation:

flwr run .

Refer to the How to Run Simulations guide in the documentation for advice on how to optimize your simulations.

Run with the Deployment Engine

Follow this how-to guide to run the same app in this example but with Flower's Deployment Engine. After that, you might be interested in setting up secure TLS-enabled communications and SuperNode authentication in your federation.

You can run Flower on Docker too! Check out the Flower with Docker documentation.

Resources

• Flower website: flower.ai
• Check the documentation: flower.ai/docs
• Give Flower a ⭐️ on GitHub: GitHub
• Join the Flower community!
  • Flower Slack
  • Flower Discuss

main