Fine-Tuning and Evaluating LLM Retrieval Models with Anyscale and Arize

​In the fast-evolving realm of machine learning, retrieval models are becoming a cornerstone for many applications, from search engines to chatbots — but harnessing their true potential demands precision in fine-tuning and evaluation. 

​Join us for a deep dive into the considerations when it comes to fine-tuning retrieval models and evaluating their efficacy carrying out RAG-based services. Through a fireside chat and hands-on workshop, we will explore:

• ​The intricacies of adapting these models to specific tasks and industries

• ​Deploying a system for fast, cost-efficient LLM fine-tuning

• ​Vetted approaches to evaluating performance of fine-tuned LLMs 

• ​Practical learnings from ML teams that have deployed these apps in production

​You will learn how to leverage the latest tools and pre-tested eval metrics to ensure your retrieval models are not just tailored, but fine-tuned for excellence. Whether you're a seasoned developer, an LLM enthusiast, or eager to learn about cutting-edge advancements, this event will deepen your understanding and appreciation of today's continuously evolving LLM landscape. 

​Agenda:

• ​5:30 PM - 6:00 PM: Arrival & Networking

• ​6:00 PM - 6:45 PM: Founders Discussion Panel + Q&A

• ​6:45 PM - 7:30 PM: Arize & Anyscale Workshop + Q&A

• ​7:30 PM - 8:30 PM: Networking