Create README.md

README.md

@@ -0,0 +1,2 @@
+This is the model for CL_Polarizer, as described in our paper, "Contrastive Learning as a Polarizer: Mitigating Gender Bias by Fair and
+Biased Sentences". CL_Polarizer is trained from an underlying bert-base-uncased backbone, and demonstrates sate-of-the-art performance in the ICAT score of the StereoSet.