Using LLMs with Beam and RunInference


Speaker(s):
Reza Rokni

Using LLMs with Beam and RunInference

By Reza Rokni
Sep-4 16:30-16:55 in Mariposa Grove
Add to Calendar 09/04/2024 4:30 PM 09/04/2024 4:55 PM America/Los_Angeles AS24: Using LLMs with Beam and RunInference

This session will provide an overview of how to utilize large language models (LLMs) using Apache Beam’s RunInference framework. The prime example for the talk will be running the Gemma open model on Dataflow, outlining considerations and common pitfalls when writing pipelines with LLMs.

 Mariposa Grove

  Download slides

This session will provide an overview of how to utilize large language models (LLMs) using Apache Beam’s RunInference framework. The prime example for the talk will be running the Gemma open model on Dataflow, outlining considerations and common pitfalls when writing pipelines with LLMs.