Next upHack for Humanity: San Francisco (powered by Google Gemini)
1:10:29

Leveraging open-source LLMs for production

This talk examines using open-source LLMs for real-world purposes. It compares the benefits and drawbacks of open-source LLMs to proprietary options like OpenAI. The discussion covers the economics of hosting open-source LLMs, highlights serving frameworks, explores cloud GPU availability, gives an overview of key open-source LLMs, and shows how to run and refine these models using the dstack open-source tool. Speaker: Andrey is the founder of dstack, an open-source toolkit for orchestr

Dmytro Spodarets
Dmytro Spodarets
Dec 4, 2023
Summary

An examination of using open-source LLMs in production versus proprietary options like OpenAI, covering hosting economics, serving frameworks, cloud GPU availability, key open-source models, and running and refining them with the dstack open-source tool.