Update README.md

README.md

@@ -11,4 +11,20 @@ metrics:
 - accuracy
 pipeline_tag: sentence-similarity
 ---
-This model card provides a detailed overview of the Bloomz model fine-tuned for automated essay grading in Arabic, using the enhanced Open Orca dataset. The integration of advanced data processing techniques and multilingual support ensures high accuracy and reliable performance for educational applications.
+We are thrilled to introduce our graduation project, the EM5 model, designed for automated essay grading in both Arabic and English. 📝✨
+
+To develop this model, we first created a custom dataset for training. We adapted the QuAC and OpenOrca datasets to make them suitable for our automated essay grading application.
+
+Our model utilizes the following impressive models:
+
+    Mistral: 96%
+    LLaMA: 93%
+    FLAN-T5: 93%
+    BLOOMZ (Arabic): 86%
+    MT0 (Arabic): 84%
+
+You can try our models for auto-grading on Hugging Face! 🌐
+
+We then deployed these models for practical use. We are proud of our team's hard work and the potential impact of the EM2 model in the field of education. 🌟
+
+#MachineLearning #AI #Education #EssayGrading #GraduationProject