toxicity-reward-model-max-margin-epoch-100-s-nlp-tox-p9-1800-pythia-410m
This model was trained using max_margin IRL to learn toxicity reward signals.
Base model: EleutherAI/pythia-410m
Original model: EleutherAI/pythia-410m
Detoxified model: ajagota71/pythia-410m-s-nlp-detox-checkpoint-epoch-100
language: en
tags:
- toxicity
- reward-model
- irl
library_name: transformers
base_model: pythia-410m
pipeline_tag: text-classification
