great comparision. I have used gemini pro vision, and looking for simliar open source solution. can u plz suggest something for : "extracting data in key-value-pair from documents(images and pdfs) like invoice , forms , ids". a light model can help, so that it can run on less memory. thanks in advance . :)
I think to use a smaller model for a specific task we might want to fine tune something ourself with a bunch of images and the expected output. I read that PaliGemma is supposed to be a good base image for that, but I haven't tried fine tuning it myself - huggingface.co/google/paligemma-3b-mix-448
Would be very happy to see how you did the interface with streamlit.
Mark, I think Phi 3 got the answer for What is this *company* most famous for? Since the company in the image is Microsoft.
Ah you're right - I missed that!
This is good
great comparision.
I have used gemini pro vision, and looking for simliar open source solution.
can u plz suggest something for :
"extracting data in key-value-pair from documents(images and pdfs) like invoice , forms , ids".
a light model can help, so that it can run on less memory.
thanks in advance . :)
I think to use a smaller model for a specific task we might want to fine tune something ourself with a bunch of images and the expected output. I read that PaliGemma is supposed to be a good base image for that, but I haven't tried fine tuning it myself - huggingface.co/google/paligemma-3b-mix-448