mneedham / LearnDataWithMark

Code and scripts behind the @LearnDataWithMark YouTube channel
https://learndatawithmark.com
135 stars 38 forks source link

[Content] What is LLaVA not good at? #40

Closed mneedham closed 10 months ago

mneedham commented 10 months ago

Might be interesting to do a video showing what types of things the open source multi modals can't do very well. We could use GPT4-V as the ground truth as it seems to be able to handle pretty much any images.

mneedham commented 10 months ago

I kinda did this in my latest video.