This model is a fine-tune checkpoint of T5-base, fine-tuned on the Wiki Neutrality Corpus (WNC), a labeled dataset composed of 180,000 biased and neutralized sentence pairs that are generated from Wikipedia edits tagged for “neutral point of view”. This model reaches an accuracy of 0.39 on a dev split of the WNC.
For more details about T5, check out this model card.
- Downloads last month
- 2
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.