Stefano Fiorucci is a software engineer passionate about language models, open-source development, and knowledge sharing. As a Fellow of the tenth session of the Pi School of AI, he is now contributing to Haystack, an open-source LLM orchestration framework at Deepset, while actively engaging with a global community of developers and researchers.
Stefano will walk us through his low-cost fine-tuning approach to improving Gemma 2, Google’s family of open models, for the Italian language. The session will cover:
He’ll also introduce Spectrum, a memory-efficient fine-tuning method that allows selective updating of model parameters. While the focus is on Italian, these strategies offer valuable insights for adapting LLMs to other languages.
Date: Thursday, February 6, 2025
Time: 4:00 PM CET
Location: Online (Google Meet)
Don’t miss this opportunity to learn, ask questions, and connect with the AI community!
Join us on February 6 at 4:00 pm.