Want to deploy open source models efficiently? Join this session for a technical deep dive into best practices for deploying and optimizing models like Llama and Gemma on Vertex AI.

Vertex AI offers a range of Gemini models, each with different capabilities. Learn how to pick the right Gemini model for your use case and how to get the best performance. First, we explain how to map the modalities and properties of each model to your use case and functional requirements. Then we provide an overview of prompt design principles and how to craft effective prompts based on business requirements and language engineering considerations. Finally, we present prompt engineering strategies to ensure robustness and scalability of your prompts. This session is ideal for developers and prompt engineers seeking to maximize the value of Gemini on Vertex AI.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.