Gemma is a family of generative artificial intelligence (ai) models and you can use them in a wide variety of generation tasks, including question answering, summarization, and reasoning. This repository contains the implementation of the gemma pypi package. It is based on similar technologies as gemini The first version was released in february 2024, followed by gemma 2 in june 2024 and gemma 3 in march 2025. Deploy gemma 3, google's open model, to production on google cloud Serverless cloud run for simplicity or gke for robust orchestration.
In this section, we focus on some key diferences from pr 5:1 interleaving of local/global layers Discover gemma 3, google's advanced ai model with enhanced math, coding, and vision capabilities Learn how it was built, trained, and more. Gemma models demonstrate strong performance across academic benchmarks for language understanding, reasoning, and safety. Gemma models are available in two sizes
WATCH
