Gathering & registration

Greetings

Local Execution: Running LLMs on Your Own Machines

As the demand for powerful language models continues to grow, so does the need for decentralized deployment solutions. This session provides a comprehensive exploration of the advantages and intricacies of hosting large language models locally. From installation and configuration to optimization and security considerations, this lecture equips attendees with the knowledge and tools necessary to leverage LLMs effectively within their own computing environments.

Break

Customizing the Power of LLMs: Tailoring Language Models to Your Enterprise Data

Large language models (LLMs) have revolutionized natural language processing (NLP) by exhibiting remarkable capabilities in understanding and generating human-like text. However, their effectiveness can be further amplified by connecting them to a custom datasets tailored to specific domains or applications. This session delves into the process of enhancing LLMs with personalized data, exploring techniques such as fine-tuning, RAG patttern, and domain adaptation. Join us to discover how leveraging LLMs with custom data can elevate the performance and applicability of your Gen-AI powered solutions.

Lunch

Enhance the Performance & Accuracy of LLMs

This session explores techniques to elevate the capabilities of Large Language Models. We'll delve into strategies for improving accuracy, reducing bias, and boosting overall performance. Learn about data selection, fine-tuning techniques, and evaluation practices that ensure your LLMs deliver reliable and high-performing results.

LLMOps - Building LLM applications for production

This session tackles the challenges of deploying Large Language Models (LLMs) in real-world applications. We'll explore the emerging field of LLMOps, a set of practices for bringing LLMs from development to production. Discover how LLMOps helps manage infrastructure, optimize resource allocation, and ensure ongoing model maintenance. By understanding LLMOps principles, you'll gain the knowledge to build and deploy to build and deploy LLMs at scale.