In this session, you will explore different large language models (LLMs) available on AWS. You will gain insights into the capabilities and strengths of various LLMs from Amazon, Anthropic, Mistral, Meta and other model providers. Additionally, you will learn how to select the most suitable LLM for your specific generative AI projects, considering factors like model size, performance, and domain-specific knowledge. By understanding the available options and their suitability, you can make informed decisions when leveraging LLMs for tasks like content generation, language translation, question answering, etc.

Agenda:
- Models Available on Amazon Bedrock
- Model Evaluation
- Customizing Model Responses for Your Model and Customer Use Cases
- Available Model Benchmarks
- Pricing aspects related to the LLMs

Who should attend:
- AIML Engineers
- Developers
- CTOs

Takeaways:
- Understanding LLM Basics
- Essential criteria to evaluate an LLM
- Use case alignment
- Cost and Resource management knowledge to make informed decisions and harness the full potential of generative AI.

Prerequisites:
- Basic understanding of generative AI services on AWS
- On the day of the session, please bring your email registration confirmation for entry

Important: Sessions are focused on providing best practices, details of service features and demos for working professionals only. Attendance is subject to AWS Event Terms and Conditions.