Modelpublic

ajagota71/toxicity-reward-model-output-max-margin-5-seed-200-unfrozen-layers-0-pythia-70m

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes6downloads

Model Card

toxicity-reward-model-output-max-margin-5-seed-200-unfrozen-layers-0-pythia-70m

This model was trained using max_margin IRL to learn toxicity reward signals.

Base model: EleutherAI/pythia-70M Original model: EleutherAI/pythia-70M Detoxified model: ajagota71/pythia-70m-detox-epoch-100

language: en tags:

—toxicity
—reward-model
—irl libraryname: transformers basemodel: pythia-70m pipeline_tag: text-classification ---