Added link to the paper

README.md

@@ -17,5 +17,8 @@ The following corpora were used for training the model:
 * Slovenian parliamentary corpus siParl 2.0
 * slWaC
 
+## Evaluation
+The model is described in detail and evaluated in our paper ["*Sequence to sequence pretraining for a less-resourced Slovenian language*"](https://arxiv.org/abs/2207.13988)
+
 ## Changelog
 2022-07-21: updated with v2 of the model, the old one is still accesible at [cjvt/legacy-t5-sl-small](https://huggingface.co/cjvt/legacy-t5-sl-small).