microsoft

/

Phi-3-vision-128k-instruct

like 782

While the model was able to provide proper answer for the textual questions(2 and 3), it gave wrong answers for the visual questions(4 and 5). It might also be the case that my question was not framed properly for the visual questions. So, please provide me guidance on how to get correct answers for questions 4 and 5 using this model.