Update README.md

README.md

@@ -1,3 +1,16 @@
 ---
-license: unlicense
+license: apache-2.0
 ---
+
+We created **Starling** by fine-tuning Vicuna-7B on HarmfulQA, a ChatGPT-distilled dataset. More details are on our paper [**Red-Teaming Large~Language~Models using Chain of Utterances for Safety-Alignment**](https://openreview.net/pdf?id=jkcHYEfPv3)
+
+Experimental results on several safety benchmark datasets indicate that **Starling** is a safer model compared to the baseline model, Vicuna.
+
+<img src="https://declare-lab.net/assets/images/logos/method.png" alt="Image" width="200" height="335">
+
+<h2>Experimental Results</h2>
+
+<img src="https://declare-lab.net/assets/images/logos/starling-results.png" alt="Image" width="200" height="335">
+
+<img src="https://declare-lab.net/assets/images/logos/starling-results2.png" alt="Image" width="200" height="335">
+