LLM Meetup with Predibase, LlamaIndex, Guardrails and Tryolabs | San Francisco

​LLMOps: From Prototype To Production | Developer Meetup

​Join Predibase, LlamaIndex, Guardrails AI, and Tryolabs for an evening of food, drinks, and discussions on all things LLMOps while taking in the view of the SF Bay from the 17th floor of our office.

​​LLMs have huge potential, but when it’s time to move from a simple prototype to production application, the challenges stack up: What technique should I use to customize my LLM? What are the best open-source tools and models? How do I cost-efficiently serve at scale? And most importantly, how do I make sure my model outputs are responsible and reliable?

​Good news: we brought together founders and engineers from leading LLM startups and open-source projects for one night to share their insights and best practices for building LLM applications at scale. You’ll have a chance to hear from them and network with your peers working on LLM projects.

​​Event Agenda:

• ​​4:30-6:00: Pizza, Drinks and Networking

• ​​6:00-7:30: Lightning Talks and Demos

  • ​Predibase: How to Fine-tune and Serve LLMs that Rival GPT4

  • ​LlamaIndex: RAG in Production: What Can Go Wrong and How to Fix It

  • ​Tryolabs: From Lab to Launch: MLOps for Effective LLM Implementation

  • ​Guardrails: Building the Next Generation of Responsible AI

• ​​7:30-8:30: Drinks and Networking

​​Must register to attend. Save your spot as space is limited.

​Invite your friends: https://lu.ma/SFMeetupLLMs.