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

Updated to AI Playground version 2.2.0-beta and having issues with LLM models - not found but can't download the model #214

Open
js333031 opened this issue Mar 6, 2025 · 2 comments

Comments

@js333031
Copy link

js333031 commented Mar 6, 2025

I upgraded from I believe 2.0.0-alpha to 2.2.0-beta version. I selected model backup during the upgrade process but those models are not found. This appears to be a known issue. Regardless, I proceeded to download the microsoft/phi3-mini-4k-instruct model via the UI settings --> Models menu under Answer section.

After downloading the model, I restarted the application. The application GUI shows "model not found" and the refresh/dropdown menu does not show the model.

If I go to Settings --> Models under Answer section and attempt to down the model again, a popup is shown that "The model already exists. Reloading the model is unnecessary."

Where is the model supposed to be saved? The Settings --> Models --> LLM Model Path (and other paths) are all blank.

@bobduffy
Copy link
Contributor

bobduffy commented Mar 7, 2025

Thanks for the feedback. I suspect the backend is not selected. Go to Basic settings, the select the backend that matches the model formats you are using

IPEX-LLM for safetensors
Llama.cpp for GGUF

The model list should shoe the models for that backend

@js333031
Copy link
Author

js333031 commented Mar 8, 2025

Thanks, that was it. It would still be good to know where the models are downloaded using the UI.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants