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.

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

Reasoning UI Bugs #3447

Open
AndriyMulyar opened this issue Jan 31, 2025 · 2 comments
Open

Reasoning UI Bugs #3447

AndriyMulyar opened this issue Jan 31, 2025 · 2 comments
Labels
bug-unconfirmed chat gpt4all-chat issues

Comments

@AndriyMulyar
Copy link
Contributor

Bug Report

Image
  • Chat summary (top left) includes tokens for R1 reasoning models
  • When the model doesn't think the thinking, animation still shows up

Steps to Reproduce

Try the prompt in the image.

@AndriyMulyar AndriyMulyar added bug-unconfirmed chat gpt4all-chat issues labels Jan 31, 2025
@manyoso
Copy link
Collaborator

manyoso commented Jan 31, 2025

The model is producing this:

<think></think>Deepseek Artificial Intelligence Co., Ltd ...

That's why the think part still shows up. I'll see if I can delay it a bit to see if it has any content before showing it

@brankoradovanovic-mcom
Copy link

My autosummary is always "<think> Alright, so I", i.e. it is the beginning of the thinking phase which always seems to be the same. I don't see a good solution for this. AFAIK one cannot tell a reasoning model not to use thinking for a particular response. Otherwise, generating the final answer (i.e. the actual summary) may take too long.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug-unconfirmed chat gpt4all-chat issues
Projects
None yet
Development

No branches or pull requests

3 participants