feat: additional file types for uploading models

[officialsahyaboutorabi]

Pull Request Checklist

• Description: Briefly describe the changes in this pull request.
• Changelog: Ensure a changelog entry following the format of Keep a Changelog is added at the bottom of the PR description.
• Documentation: Have you updated relevant documentation?
• Dependencies: Are there any new dependencies? Have you updated the dependency versions in the documentation?

---

Description

[Insert a brief description of the changes made in this pull request]

---

Changelog Entry

Added

• [List any new features or additions]

Fixed

• [List any fixes or corrections]

Changed

• [List any changes or updates]

Removed

• [List any removed features or files]

[justinh-rahb]

Did you test this? Ollama only supports GGUF.

EDIT: I stand corrected, apparently it does support PyTorch now, but only as .bin files.. with a custom build of Ollama, maybe? Honestly it's unclear from their docs.

[tjbck]

Shouldn't this be .bin and not .safetensors?

[officialsahyaboutorabi]

Both of them might work. Although don't rely on me as I am not too sure. I will have a look into it.

[tjbck]

If you could check I'd greatly appreciate it!

[officialsahyaboutorabi]

Alright, let me know if there is anything else you need me to look at.

[officialsahyaboutorabi]

If you could check I'd greatly appreciate it!

@tjbck, So it looks like that the model I am trying to load uses .safetensors. However, a .bin is just a binary file and isn't really used for models other than the conversion process.

[tjbck]

I'll merge this to our dev branch but I'm pretty sure we can't just directly upload .safetensors files, feel free to try it out with dev branch docker image and let us know your results.

[officialsahyaboutorabi]

I'll merge this to our dev branch but I'm pretty sure we can't just directly upload .safetensors files, feel free to try it out with dev branch docker image and let us know your results.

How can I set up the dev branch docker image?

[justinh-rahb]

How can I set up the dev branch docker image?

docker pull ghcr.io/open-webui/open-webui:dev
docker rm -f open-webui
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:dev