roymiles

Hi, thank you for releasing this project! I was wondering if you happen to have the pre-trained weights for the models finetuned on the different downstream tasks (QQP, MNLI.. etc)....

Training code

2

Hi, Will you provide the training code to replicate the results from the paper and generate the frozen Tensorflow graph model? Thanks

Could you include a comparison with Information theoretic representation distillation. Paper: https://bmvc2022.mpi-inf.mpg.de/0385.pdf Code: https://github.com/roymiles/ITRD

Could you add Information theoretic representation distillation. Paper: https://bmvc2022.mpi-inf.mpg.de/0385.pdf Code: https://github.com/roymiles/ITRD

Replicating results

1

Hi, I was just wondering, were you able to replicate the results in the original paper using this implementation? Thanks

A few questions regarding the results and methodology.

1

Hi, thanks for releasing this work! it has all been very interesting to read. However, I do have a few questions regarding your results and methodology. 1. For table 4....