Update README.md

README.md

@@ -26,3 +26,12 @@ Labels:
 2: Offensive or Hateful
 Training Data: Augmented version of [this dataset](TLeonidas/twitter-hate-speech-en-240ksamples) (279k+ rows)
 
+## Dataset
+The model was trained on a concatenated dataset from three distinct sources, curated to encompass a wide range of linguistic expressions and contexts. 
+The datasets were preprocessed and balanced to ensure fair representation across all categories.
+
+## Performance
+The model achieves an accuracy of 92.5%, evaluated on a held-out test set.
+
+## Contributing
+We welcome contributions to improve the model and extend its applicability.