dingning97

Have anyone successfully reproduced the result 74.X% on VisDA ?!

Yeah, the same situation also happened to me. I got an average result of 86.5%. Guess the author might have applied some tricks during training process

I used a very old version of MiniGPT4, and the last commit might be "commit-22d8888" on May 1, 2023. You might access those lagacy codes throught this link: https://github.com/Vision-CAIR/MiniGPT-4/tree/22d8888ca2cf0aac862f537e7d22ef5830036808 Place...

Hi. Can you reproduce the 91.68% accuracy using T5-large model ? I tried to reproduce the experiments with "declare-lab/flan-alpaca-large" model, but only got ~90.5% accuracy for the test set of...