Re:Introducing DBRX: A New State-of-the-Art Open LLM by Data...
by gerash on Wednesday March 27, 2024 @05:32PM
(#39844842)
The evaluations are not comprehensive either. All of them are improving and you can't expect any of them to hit 100% on the metrics (a la. bayes error rate). It gets increasingly difficult to move the metrics as they get better.
[ Parent
| on HN ]
There are no comments on this comment yet.