Gemma3 with tool calling capability #13084
Unanswered
outerbound
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I am trying to run gemma-3-27b-it-q4_0.gguf model on docker with ghcr.io/ggerganov/llama.cpp:server-cuda image. I want tool calling capability. From documents, I have gathered that I should supply --jinja and --chat-template arguments.
What should be jinja file template I can supply to --chat-template ?
Beta Was this translation helpful? Give feedback.
All reactions