Comparison of Phi-3.5-vision-instruct vs Phi-3-vision-instruct
#1
by
Ghada
- opened
Hello Team,
Many thanks for your efforts.
It would be great if we could have ONNX version of Phi-3.5/ Phi-3 Vision model in addition to have multilingual support.
Aside from this, we noticed a decrease in the precision of the generated output of Phi-3.5/ compared to Phi-3 for the tasks of code and text translation on the content captured from the image.
Thank you.
kvaishnavi
changed discussion status to
closed