Replies: 1 comment
|
Hello, this feature is now implemented in v0.7.0. Thanks! |
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
I am running multiple local llms through llama.cpp, vllm, and mlc.
When I switch between different models on the server, the server program imports customized system prompts from the model file.
Current client system prompts override server system prompts, resulting in failure to achieve the best experience.
All reactions