Update README.md

README.md

@@ -6,4 +6,4 @@ pipeline_tag: text2text-generation
 
 Model from the preprint [Unlimiformer: Long-Range Transformers with Unlimited Length Input](https://arxiv.org/abs/2305.01625).
 
-This model was finetuned from a BART-base model using the retrieval-augmented training strategy described in section 3.2. It was finetuned on the dataset BookSum (full-book setting).
+This model was finetuned from a BART-base model using the retrieval-augmented training strategy described in section 3.2 of the paper. It was finetuned on the dataset BookSum (full-book setting).