Summer

Well.. seems I need it for a project. I'll take a crack at it!

@ontocord Ok! Sounds good!

Sure! I'll add a test set to the dataset! My one concern for changing the name of the directory is that it seems that there is already another attempt at...

@yk It seems pre-commit (on github actions) continues to fail without any discernable error. I think this is because it's a notebook and something weird is going on. I can't...

Closing Pull due to large updates in the safety pipeline.

@ontocord apologies, im very busy this and next week so ill be offline for a bit. I did want to add this dataset here though https://github.com/michiyasunaga/DrRepair

@ontocord here are some implementations I have tested and know work: https://github.com/falcondai/lm-steganography https://github.com/ku-nlp/steganography-with-masked-lm https://github.com/mickeysjm/StegaText https://github.com/jumon/himitsu I personally like steganography-with-masked-lm so I put it up in this Kaggle notebook: https://www.kaggle.com/code/summerbreeze11/text-steganograpthy/edit

I’ll take a look at it further. I’ll put my updates here as I go.

Why does the safety label export need to go a seperate jsonl file? is it possible to export it with the rest of the data in the current jsonl file?...

that would be much appreciated! Thanks!