add citation

README.md

@@ -207,4 +207,16 @@ which points to meaningful limitations of the existing evaluation benchmarks for
 | dolly-v1-6b (10 epochs)     |        0.41  |   0.62963  |     0.643252 |    0.676758 |        0.384812 | 0.773667 | 0.687768 |
 | EleutherAI/gpt-neox-20b     |        0.402 |   0.683923 |     0.656669 |    0.7142   |        0.408703 | 0.784004 | 0.695413 |
 
+# Citation
+
+```
+@online{DatabricksBlog2023DollyV1,
+    author    = {Mike Conover and Matt Hayes and Ankit Mathur and Xiangrui Meng and Jianwei Xie and Jun Wan and Ali Ghodsi and Patrick Wendell and Matei Zaharia},
+    title     = {Hello Dolly: Democratizing the magic of ChatGPT with open models},
+    year      = {2023},
+    url       = {https://www.databricks.com/blog/2023/03/24/hello-dolly-democratizing-magic-chatgpt-open-models.html},
+    urldate   = {2023-06-30}
+}
+```
+
 # Happy Hacking!