With the release of OpenAI’s new finetuning endpoints, it’s worth asking the general question: how do I best use finetuning with my LLM app, especially if I’m building RAG systems? (search, chatbots, and more).
We’re excited to host Jo Bergum, distinguished engineer at Vespa, as well as Shishir Patil, PhD student at Berkeley and author of Gorilla, to discuss this.
We’ll talk about some how to plug in different aspects of finetuning to optimize your RAG system:
Timeline:
0:00: Opening presentation from Tenzin/Ali on their winning hackathon project at the Augment hackathon
8:00: Shishir (Berkeley) on finetuning + Gorilla
16:00: Jo (Vespa) on LLMs + synthetic queries
24:00: Panel with Shishir/Jo on RAG + finetuning
Add comment