Update README.md

README.md

@@ -1,2 +1,15 @@
-This model uses pretrained distilroberta-base weights, fine tuned on the WNC wiki edits corpus to detect biased language. See https://github.com/rpryzant/neutralizing-bias for more details.
+---
+language: en
+datasets:
+- valurank/wikirev-bias
+---
+# DistilROBERTA fine-tuned for bias detection
+
+This model is based on [distilroberta-base](https://huggingface.co/distilroberta-base) pretrained weights, with a classification head fine-tuned to classify text into 2 categories (neutral, biased).
+
+## Training data
+The dataset used to fine-tune the model is [wikirev-bias](https://huggingface.co/datasets/valurank/wikirev-bias), extracted from English wikipedia revisions, see https://github.com/rpryzant/neutralizing-bias for details on the WNC wiki edits corpus.
+
+## Inputs
+Similar to its base model, this model accepts inputs with a maximum length of 512 tokens.