https://foojayio.github.io/website/today/author/guillaume-laforge/Articles written by Guillaume Laforge on foojay.io - Friends of OpenJDKHugoen-usFri, 12 Apr 2024 13:55:38 +0000https://foojayio.github.io/website/today/calling-gemma-with-ollama-testcontainers-and-langchain4j/Fri, 12 Apr 2024 13:55:38 +0000https://foojayio.github.io/website/today/calling-gemma-with-ollama-testcontainers-and-langchain4j/<p><strong>Lately, for my Generative AI powered Java apps, I&rsquo;ve used the <a href="https://deepmind.google/technologies/gemini/#introduction" target="_blank" rel="noopener noreferrer">Gemini</a> multimodal large language model from Google. But there&rsquo;s also <a href="https://blog.google/technology/developers/gemma-open-models/" target="_blank" rel="noopener noreferrer">Gemma</a> , its little sister model.</strong></p> <p>Gemma is a family of lightweight, state-of-the-art open models built from the same research and technology used to create the Gemini models.</p> <p>Gemma is available in two sizes: 2B and 7B. Its weights are freely available, and its small size means you can run it on your own, even on your laptop. So I was curious to give it a run with <a href="https://docs.langchain4j.dev/" target="_blank" rel="noopener noreferrer">LangChain4j</a> .</p>