Edit model card

Model Card for mabel-bert-base-uncased

Model Description

This is the model for MABEL, as described in our paper, "MABEL: Attenuating Gender Bias using Textual Entailment Data". MABEL is trained from an underlying bert-base-uncased backbone, and demonstrates a good bias-performance tradeoff across a suite of intrinsic and extrinsic bias metrics.

Downloads last month
11
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.