Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

not working for me #2

Open
stygmate opened this issue May 16, 2024 · 2 comments
Open

not working for me #2

stygmate opened this issue May 16, 2024 · 2 comments

Comments

@stygmate
Copy link

stygmate commented May 16, 2024 •
edited
Loading

I have tried the code in init.py
the llm seems to never include the closing tag </tool_call>
So functions are never called.
@stygmate
Copy link
Author

Seems that system prompt have all line break converted to space (yaml related).
Seems to alter the function calling quality of the model.

@fabbricca
Copy link
Owner

I've been tied up with a couple of projects lately, leaving me with no free time for the past few weeks. Have you experienced any odd behavior with Llama3 NousResearch Hermes 2 Pro or with MistralAI NousResearch Hermes 2 Pro? I found Llama3 to exhibit similar quirks to the one you described. On the other hand my experience with MistralAI was pretty good actually.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@stygmate @fabbricca