
02: Unleashing LLMs in Production: Challenges and Opportunities with Chip Huyen
Replit AI Podcast
The Slow Ramp Up of Open Source Modeling
The core model that we release open source was trained in three days on 256 GPUs. It would have not been the case, you know, if you're working on a 7B or a 13B. So it's very exciting to see how accessible the lams have become for smaller teams. The performance that we got was surprising in terms of positively surprising.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.