Anas Awadalla

I see. Could you try to run the command below and retrying? ``` from ipywidgets import IntProgress If ipywidgets is not found do: pip install ipywidgets jupyter nbextension enable --py...

If this is something you are interested in please get back to me before starting as this is a bigger task that may require exploring different methods with multiple people...

This relates to what I am currently doing so I'll do it in conjunction with the current task.

http://archive.ics.uci.edu/ml/index.php - Has some decent datasets from various categories https://github.com/beamandrew/medical-data - Really good medical datasets

Yeah I think we can default to the mmc4 code for all of these. For the first point this should be based on the image size. I think because most...

Great will check it tomorrow

What would the hook contain? The code formatting?

> > What would the hook contain? The code formatting? > > Yep, kind of like [this](https://github.com/run-llama/llama_index/blob/main/.pre-commit-config.yaml) or whatever else we want. This would be awesome!

Sorry @isaac-chung got busy with a paper I am pushing. I will definitely review and merge this week tho!

Hmm… hallucinations and repetitive outputs are still very possible with these models. Maybe you can try different decoding parameters to find something that works best for you?