+
Skip to content
@gemma-facet

Facet AI

Bringing out Gemma's best facet | Democratising SLM fine tuning

Facet AI -- Bringing out Gemma's best facet

A streamlined, customizable, no-code web platform to manage fine-tuning workflows of DeepMind's Gemma 3 family of multimodal models. From dataset formatting to deployment, Facet AI lets you focus on what matters for your use case, not writing boilerplate code and scrolling through pages of documentations and cookbook.

Whether you're a complete beginner to LLM fine tuning, or experienced engineer looking to build a platform for your team, Facet AI is here to democratize SLM fine-tuning for everyone.

Watch our demo video!! 👇👇

Demo Video

Getting Started

  • For personal users, access our service through our no-code intuitive web interface to start training models in minutes
  • For production and enterprise, easily deploy the entire platform on your cloud project with our Terraform IaC

Highlights

  • Powered by Google Cloud Platform (GCP), 100% open source and free to use!
  • Supports local + huggingface datasets, all Gemma 3 & 3n models (from 270M to 27B), SFT + RL (GRPO, DPO, ORPO) post-training, evaluation + benchmarks, export to deploy on Ollama / llama.cpp / vLLM / SGLang and more
  • Production-ready, robust, and centralized for your team to collaborate, unlike your pile of Colab notebooks
  • Highly integrated with HuggingFace ecosystem -- hub, datasets, transformers, trackio, evaluate, lighteval, trl, peft, bitsandbytes

Background

At Facet AI, we're on a journey to democratize small language model (SLM) fine-tuning. SLMs are geting more and more powerful, with new use caes emerging day by day. We hope that as more people start training SLM for their own task and domain specific adaptations, advancements in AI can more rapidly translate to real-world impact across industries and communities.

Authors

This project was built by Jet Chiang and Adarsh Dubey, two students developers from Canada and India, during the Google Summer of Code program in summer 2025. We would like to thank our organisation, Google DeepMind, our mentor, and the team at Google Cloud and Gemma for their continuous support throughout the term.

We also acknoweldge the team at transformers, TRL, Unsloth, vLLM, and much more open-source libraries that power our project. Facet AI would not exist without these amazing open-source AI communities.

image

Contributing

We welcome contributions!! Refer to CONTRIBUTING.md in each sub-directory that you wish to contribute to.

Pinned Loading

  1. frontend-ui frontend-ui Public

    Customize and manage multimodal datasets and fine tuning for DeepMind's Gemma SLM (GSoC '25)

    TypeScript 5 1

  2. cloud-services cloud-services Public

    Open-source no-code web platform to fine tune, evaluate, and ship customized Gemma VLM/SLM (Google Summer of Code '25)

    Python 9 2

Repositories

Showing 5 of 5 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…

点击 这是indexloc提供的php浏览器服务,不要输入任何密码和下载