Inference Settings
#1
by MedicSaver - opened
Hello everyone,
this is a very good model to experiment and put to good use.
Anyone able to share some of the Inference settings suggested?
LM Studio or OpenClaw specifics?
Appreciate it!
@MedicSaver as per the original model repo from NVIDIA "Use temperature=1.0 and top_p=0.95 across all tasks and serving backends — reasoning, tool calling, and general chat alike."
I was looking for personal experience...different settings suggestions. I have been using it without issues.
Cheers!
MedicSaver changed discussion status to closed