Jitesh Pabla

The command line flags allow the user to install whatever version of luar or luarocks they want, but it downloads it from the internet directly. It would be great to...

The current code uses the built-in class for classification from the transformers library. Move away from that and introduce some of the deep learning options like [YCNNN](https://github.com/Shawn1993/cnn-text-classification-pytorch). Also look here...

Add option to save models

2

Saving the models after viewing the results is important for the user to be able to get any actual use out of this package.

Add arguments to accept text and label data from user

2

in basic_classification.py

add examples folder with .ipynb like other repos do

Add preprocessing for different datasets

1

The current implementation uses the datasets (or nlp) package from hugging face to load standard datasets. Make it so that different datasets can be input into this code.

fix CUDA memory issue for multiple runs

2

Running the code more than once leads to CUDA out of memory issues. Fix that