Add citation for Thai dataset

README.md

@@ -52,7 +52,8 @@ SEA-LION was trained on 980B tokens of the following data:
 | mC4 - Filipino            |   5.3B |      0.54% |
 | mC4 - Burmese             |   4.9B |      0.49% |
 | mC4 - Vietnamese          |  63.4B |      6.46% |
-| mC4 - Thai                |  21.6B |      2.20% |
+| mC4 - Thai                |  11.6B |      1.18% |
+| WangChanBERTa - Thai      |    10B |      1.02% |
 | mC4 - Lao                 |   1.1B |      0.12% |
 | mC4 - Khmer               |   3.9B |      0.40% |
 | mC4 - Tamil               |  10.2B |      1.04% |
@@ -153,3 +154,16 @@ The model has _not_ been aligned for safety.
 Developers and users should perform their own safety fine-tuning and related security measures.
 In no event shall the authors be held liable for any claim, damages, or other liability
 arising from the use of the released weights and codes.
+
+## Citations
+
+```bibtex
+@misc{lowphansirikul2021wangchanberta,
+    title={WangchanBERTa: Pretraining transformer-based Thai Language Models},
+    author={Lalita Lowphansirikul and Charin Polpanumas and Nawat Jantrakulchai and Sarana Nutanong},
+    year={2021},
+    eprint={2101.09635},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```