Added paper and citation info

README.md

@@ -6,4 +6,20 @@ pipeline_tag: text-generation
 ---
 # LLammas-base 🐑
 
-Llama-2-7B with continued pre-training of 5B tokens of CulturaX (Documents: 75% Estonian, 25% English).
+Llama-2-7B with continued pre-training of 5B tokens of CulturaX (75% Estonian, 25% English documents).
+
+This model is also instruction-tuned resulting in [Llammas](https://huggingface.co/tartuNLP/Llammas).
+
+More details in our [paper](https://arxiv.org/abs/2404.04042). 
+
+### Citation
+```
+@misc{kuulmets2024teaching,
+      title={Teaching Llama a New Language Through Cross-Lingual Knowledge Transfer}, 
+      author={Hele-Andra Kuulmets and Taido Purason and Agnes Luhtaru and Mark Fishel},
+      year={2024},
+      eprint={2404.04042},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```