Workshop

MLOps for LLMs: How To Build, Tune, and Test a Chatbot Without Hating Your Life

Thursday, 16. May 2024 | 09:00 - 17:00

Description

When you work with large machine learning models (like LLMs), the development process can get messy, fast. To address this, the workshop equipped them with MLOps practices and tools to maintain reproducibility, automation, and testability.

It began with the fundamentals of building a chatbot using LLMs. Then, it transitioned to demonstrating how to take a prototype and iteratively adapt it to a real-world scenario using software like data version control (DVC). By the workshop's conclusion, attendees had built a working pipeline that connected LLMs, a custom dataset, and crucial performance metrics.

Topics

Requirements

Target audience

Anyone who wants to learn how to practically build an AI application like a chatbot, and how to incorporate MLOps tools into its development. No previous AI or ML experience is required.

Speaker

Joshua Starmer
Elle O'Brien
Lecturer and Research Investigator at University of Michigan
Joshua Starmer
Dave Berenbaum
Technical Product Manager at Iterative.ai