Update app.py

by ybelkada HF staff - opened

What does this PR do?

This PR adds the LM detoxification example to this space!

Link to docs: https://huggingface.co/docs/trl/main/en/detoxifying_a_lm

Under the hood, we used RL (Reinforcement Learning), to teach the model on not to generate toxic contents, given toxic prompts!

cc @NimaBoscarino

Society & Ethics org

Woooo thanks for adding this!!

NimaBoscarino changed pull request status to merged

Sign up or log in to comment