You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
I want to use the orca-mini-3B model in interactive mode (chat mode) for question answering.
Specifically, I use the quants at
https://huggingface.co/Aryanne/Orca-Mini-3B-gguf
which are derived from the HF model at
https://huggingface.co/pankajmathur/orca_mini_3b
The doc for the HF model states that the right prompt is the following:
"### System:\n{system}\n\n### User:\n{instruction}\n\n### Response:\n"
What is the right way to call the llam.cpp executable ('main') so that it uses exactly this prompt (and is in interactive mode) ?
Beta Was this translation helpful? Give feedback.
All reactions