Add arxiv link

Will link the model to paper pages

README.md

@@ -1,13 +1,15 @@
+---
+{}
+---
 # Med-Flamingo-9B (CLIP ViT-L/14, Llama-7B)
 
 ![](logo.png)
 
-Med-Flamingo is a medical vision-language model with multimodal in-context learning abilities.   
+[Med-Flamingo](https://arxiv.org/abs/2307.15189) is a medical vision-language model with multimodal in-context learning abilities.   
 
 This model is based on the OpenFlamingo-9B V1 model which uses the CLIP ViT-L/14 vision encoder and the Llama-7B language model as frozen backbones.  
 
 Med-Flamingo was trained on paired and interleaved image-text from the medical literature.
 
 
-Check out our [git repo](https://github.com/snap-stanford/med-flamingo) for more details on setup & demo.
-
+Check out our [git repo](https://github.com/snap-stanford/med-flamingo) for more details on setup & demo.