
Llama 2: Open Foundation and Fine-Tuned Chat Models
Deep Papers
The Importance of Supervised Fine Tuning in Language Models
The degree of human involvement in the supervised fine tuning is something that requires a large organization, maybe a state to work on. And they actually do state, at least if you sufficiently train for helpfulness. You can have a step that factors and safety and it does not significantly impact the helpfulness score which is, is nice to see. Yeah. The llama to those abilities to call API for external tools for me was just like another direction that LMS are definitely moving the directions of being able to call tools like that's becoming a common paradigm.
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.