Comment by mike_hearn
2 hours ago
It's not that light on the details. I read the paper and they train several different models in parallel over a few different domains and then they distill from their own models to get the final model.
2 hours ago
It's not that light on the details. I read the paper and they train several different models in parallel over a few different domains and then they distill from their own models to get the final model.
No comments yet
Contribute on Hacker News ↗