Top-10 attention heads causing gender bias have been identified using DiffMask+, as proposed in the paper "Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model." The model was fine-tuned using the Balanced BUG dataset (Levy et al., 2021).

Downloads last month
7
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Space using iabhijith/GPT2-small-debiased 1