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

gpt-4o equivalent model doesn't answer properly to text inputs (using docker aio-cpu images) #4644

Open
M0Rf30 opened this issue Jan 20, 2025 · 1 comment
Labels
bug Something isn't working unconfirmed

Comments

@M0Rf30
Copy link
Collaborator

M0Rf30 commented Jan 20, 2025

LocalAI version:
2.25.0-aio-cpu container image and all the versions that adopt bakllava-1 as gpt-4o alias

Environment, CPU architecture, OS, and Version:
Arch Linux and Fedora CoreOS

Describe the bug
aio-cpu sets bakllava-1 as vision model (gpt-4o). I tried it in many different releases and it always answers in weird ways with no logical correlation with the user input.

To Reproduce
Just select the gpt-4o model in Chat section (webui) and write "Hi" or something else. Images evaluation seems to not suffer of this. If I upload an image and ask for details about the image, it will answer properly.

Image

Expected behavior
I expect reasonable answers for both normal text input and images.

Suggestions
Look for other omni models to use for vision. Or maybe is a prompt issue?

@M0Rf30 M0Rf30 added bug Something isn't working unconfirmed labels Jan 20, 2025
@M0Rf30 M0Rf30 changed the title gpt4-o equivalent model doesn't answer properly to text inputs (using docker aio-cpu images) gpt-4o equivalent model doesn't answer properly to text inputs (using docker aio-cpu images) Jan 20, 2025
@ejalal
Copy link

ejalal commented Jan 25, 2025

Same here, installed localai:latest-cpu image and manually dowloaded qwen2.5-coder-14b model from the webui

docker run -p 8080:8080 --name local-ai -ti -v $PWD/models:/build/models localai/localai:latest-cpu
Image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working unconfirmed
Projects
None yet
Development

No branches or pull requests

2 participants