Search for "gemma"

55 results

Clear filters
  • FEB. 13, 2025 / Gemma

    Beyond the Chatbot: Agentic AI with Gemma

    A practical guide to constructing a Gemma 2-based Agentic AI system – a type of AI that can make its own decisions and use external tools to achieve goals – that can generate dynamic content for a fictional game world.

    Gemma-Logo-Agentic-AI
  • NOV. 13, 2024 / Gemma

    Inference with Gemma using Dataflow and vLLM

    vLLM's continuous batching and Dataflow's model manager optimizes LLM serving and simplifies the deployment process, delivering a powerful combination for developers to build high-performance LLM inference pipelines more efficiently.

    Gemma-Dataflow-ML-vLLM
  • JULY 10, 2024 / Gemma

    3 fun Gemma project ideas

    Use Gemma models to translate an old language, brainstorm game design ideas, and write a letter to Santa.

    Gemma project ideas - Feature
  • JULY 9, 2024 / Gemma

    Get started with Gemma on Ray on Vertex AI

    Use Gemma Supervised tuning on Ray on Vertex AI to train and serve machine learning models efficiently and effectively.

    Gemma on Ray on Vertex AI - Featured
  • MARCH 12, 2025 / Gemma

    Gemma 3 on mobile and web with Google AI Edge

    Gemma 3 1B, a new small language model for mobile and web applications via Google AI Edge, is now available, with increased efficiency, improved performance, and offline availability.

    Gemma 3 - Google AI Edge
  • JULY 31, 2024 / Gemma

    Smaller, Safer, More Transparent: Advancing Responsible AI with Gemma

    ShieldGemma is a suite of safety content classifiers models built upon Gemma2 designed to keep users safe. GemmaScope is a new model interpretability tool that offers unparalleled insight into our models' inner workings.

    20240731-Gemma-Blog-ResponsibleAI
  • APRIL 9, 2024 / Gemini

    Gemma Family Expands with Models Tailored for Developers and Researchers

    Meet the new members of the Gemma family of open models, tailored to devs and researchers, offering new and innovative options.

    Gemma-social
  • JULY 9, 2025 / Gemma

    T5Gemma: A new collection of encoder-decoder Gemma models

    T5Gemma is a new family of encoder-decoder LLMs developed by converting and adapting pretrained decoder-only models based on the Gemma 2 framework, offering superior performance and efficiency compared to its decoder-only counterparts, particularly for tasks requiring deep input understanding, like summarization and translation.

    T5Gemma: A New Collection of Encoder-Decoder Gemma Models
  • DEC. 20, 2024 / Gemma

    Beyond English: How Gemma open models are bridging the language gap

    AI Singapore and INSAIT teams have leveraged Gemma, a family of open-source language models, to create LLMs tailored to the unique needs of their communities, in a show of innovation and inclusivity in AI.

    Gemma-SEALION
  • OCT. 2, 2024 / Gemma

    Announcing Build with Google AI release 3: A Season of Gemma!

    The season showcases new applications of Gemma, including a personal AI code assistant and projects for non-English tasks and business email processing.

    Build With Google AI Season 3 - Feature