-
|
Oobabooga allows setting the number of experts per token when loading a MOE model using ExLlamaV2. I can't seem to find the option to do this with KoboldCPP's GUI. Does anyone know if it's possible to do this in the latest release? |
Beta Was this translation helpful? Give feedback.
Answered by
LostRuins
Dec 24, 2023
Replies: 1 comment
-
|
Not currently possible. |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
tmsingson
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Not currently possible.