Murali Manohar Kondragunta

1. Input size limit. 2. Generate alignments with words along with indices

3

`run_train.py`: Skip parallel instances that have more than 512 tokens when combined. This is a problem considering the input limit of transformers. `run_align.py`: In addition to the word indices output...

I tried using it in a Flask app. There's a global variable issue, so model doesn't work for 2nd time initialization. 'nloaded' is saturated to '13' in 'load_params'. So, the...

In the documentation, [links](https://github.com/huggingface/nn_pruning/blob/main/docs/HOWTO.md) for examples are not working, I'm trying to find examples of nn_pruning for text_classification.