Update README.md

README.md

@@ -39,6 +39,10 @@ My research goals are that:
 
 P.S: it is an intial release of model, and it is expected not to perform very well. But as we have more data, we will see if it can stand a battle with MCTS based engine like [Leela Zero](https://github.com/leela-zero/leela-zero).
 
+## How to Play against GoFormer?
+I've written an UI, please visit [https://github.com/kenhktsui/goformer](https://github.com/kenhktsui/goformer).
+
+
 ## Data Preprocessing
 We take the leftmost variation of the game tree in SGF format and translate it into PGN. 
 
@@ -85,5 +89,11 @@ This model achieves an eval_loss of 0.419 at step 7,600 (approximately 10.90 epo
 [10] Radford, Alec et al. “Language Models are Unsupervised Multitask Learners.” (2019).  
 
 ## Citation
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+If you find this work, please use:
+```
+@misc{ktsui2024goformer,
+      title={GoFormer - Language Model That Plays Go}, 
+      author={Ken Tsui},
+      year={2024},
+}
+```