Degraded performance for multiple models
21–30 of 149 posts
Re: Degraded performance for multiple models
#22And we get our subscription usage cut in half tomorrow if I remember correctly? EDIT: By a third. Thx below.
Re: Degraded performance for multiple models
#23This age: we made the thing that codes faster before we made the thing that does QA faster.
Re: Degraded performance for multiple models
#24Re: Degraded performance for multiple models
#25ive found degraded performance on models larger than 4.7. i assume its model damage from overly self righteous post training resulting in false/feigned balance imported into any long running complex task. wish i was joking.
Aren't the model weights frozen?
Re: Degraded performance for multiple models
#26And we get our subscription usage cut in half tomorrow if I remember correctly? EDIT: By a third. Thx below.
Re: Degraded performance for multiple models
#27Re: Degraded performance for multiple models
#28And we get our subscription usage cut in half tomorrow if I remember correctly? EDIT: By a third. Thx below.
Source required here
Re: Degraded performance for multiple models
#29And we get our subscription usage cut in half tomorrow if I remember correctly? EDIT: By a third. Thx below.
Re: Degraded performance for multiple models
#30And we get our subscription usage cut in half tomorrow if I remember correctly? EDIT: By a third. Thx below.
Source required here