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
- 228
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.