Adding link to arxiv

README.md

@@ -9,6 +9,8 @@ license_link: https://ai.google.dev/gemma/terms
 
 _This model card corresponds to the 2B version of the model with the CLIP-based vision encoder._
 
+Preprint: [arxiv.org/abs/2404.01331](https://arxiv.org/abs/2404.01331)
+
 ## Overview
 
 `llava-gemma-2b` is a large multimodal model (LMM) trained using the [LLaVA-v1.5 framework](https://arxiv.org/abs/2310.03744) with the 2-billion parameter `google/gemma-2b-it` model as language backbone.