How to Fine Tune Open Source Models

LinkedIn is trying to make it as easy as possible to develop LML applications and a big blocker for people that we are hearing is cost, latency of models. So I think fine tuning does solve those problems. It's like maybe not the easiest thing to do right now. And so I think that's where if the technology is there, that's maybe something that we could help with because I think it's pretty consistent with kind of like our goal and mission.

Transcript

Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.