SESSION

In the Trenches with DBRX: Building a State-of-the-Art Open-Source Model (repeated)

Register or Login

OVERVIEW

EXPERIENCEIn Person
TYPEDeep Dive
TRACKGenerative AI
TECHNOLOGIESDatabricks Experience (DBX), AI/Machine Learning, GenAI/LLMs
SKILL LEVELIntermediate
DURATION90 min

This session is repeated.

 

In this session, we'll share the story behind the development of DBRX, a cutting-edge, open-source foundation model trained in-house by Databricks. We'll discuss the tools, methods, and lessons learned during the development process, providing an inside look at what it takes to train a high-quality LLM. Attendees will hear directly from the team that created DBRX, and learn how they can use the same tools and techniques to build their own custom state-of-the-art models that can reason on their data. This session will cover:

  • An overview of the DBRX development story
  • The tools and methods used to train DBRX
  • Lessons learned and best practices for building your own LLM
  • Real-world examples and use cases of successful LLM development

 

Join us for this behind-the-scenes look at the development of DBRX, and learn how to build your own custom state-of-the-art LLM using the same tools and techniques.

SESSION SPEAKERS

IMAGE COMING SOON

Jonathan Frankle

/Chief Scientist - Neural Networks
Databricks

Abhinav Venigalla

/NLP Architect
Databricks