Google DeepMind's Gemma Models: Making Open Language Models at a Practical Size

​This is an in person BuzzRobot event.

​​Agenda:
5:00pm – doors open
5:30pm – 6:30pm official talk and Q&A
6:30pm – 8:00pm networking

Join BuzzRobot Slack to connect with the community
--------------------------------------------------------
Description of the talk:
This presentation focuses on Gemma, Google’s family of open language models designed with a focus on practical size without sacrificing performance. We explore the architecture and training methodology behind Gemma, emphasizing techniques for efficient scaling and resource optimization.

​We present a comprehensive evaluation of Gemma across various benchmarks, demonstrating its competitive performance compared to larger open models while requiring significantly less computational resources for both training and inference.

​We will also discuss the implications of open-sourcing Gemma, fostering community-driven development and democratizing access to powerful language model technology. This work aims to bridge the gap between cutting-edge LLM capabilities and practical constraints.

Our guest speaker:
Kathleen Kenealy is a staff research engineer at Google DeepMind and is a technical lead on the Gemma team. At Google, she has worked on large-scale LLM training, AI infrastructure research, novel applications for diffusion models, and open model training + development.