Patrick Devine
Patrick Devine
Dupe of #6417
I'm going to go ahead and close the issue since it seems like a problem with access control on your machine.
This is definitely something I'd like to get done soon. I actually started a partial implementation the other day and it ended up being a bigger change than I was...
Let's track this in #4077
@nPHYN1T3 sorry, man. If you think it's a different bug and I closed it incorrectly, we can always reopen. I try to get the LLM to find the dupes of...
@Animaxx unfortunately backporting it to work with llama.cpp would be tricky because the image preparsing step is written in golang, and not c++. I'm going to go ahead and close...
@eulercat we don't support pulling images w/ `image_url`. You'll have to base64 encode your image, so it looks like: ``` curl http://localhost:11434/api/chat -d '{ "model": "x/llama3.2-vision", "messages": [ { "role":...
@ludos1978 you'll need `0.4.0` for it to work. Unfortunately we're still working through some issues w/ the release candidates.
Let's track this in #9659 . It is something we're looking at.
Can you post some steps (maybe with screenshots?) to reproduce? I was looking at this yesterday and it seemed to be working correctly.