Update README.md

README.md

@@ -32,7 +32,7 @@ see the [paper](https://arxiv.org/abs/2203.05437).
 <li >Supported languages: Assamese, Bengali, Gujarati, Hindi, Marathi, Odiya, Punjabi, Kannada, Malayalam, Tamil, and Telugu. Not all of these languages are supported by mBART50 and mT5. </li>
 <li >The model is much smaller than the mBART and mT5(-base) models, so less computationally expensive for decoding. </li>
 <li> Trained on large Indic language corpora (5.53 million sentences). </li>
-<li> Unlike [MultiIndicParaphraseGeneration](https://huggingface.co/ai4bharat/MultiIndicParaphraseGeneration) each language is written in its own script, so you do not need to perform any script mapping to/from Devanagari. </li>
+<li> Unlike <a href="https://huggingface.co/ai4bharat/MultiIndicParaphraseGeneration">MultiIndicParaphraseGeneration</a> each language is written in its own script, so you do not need to perform any script mapping to/from Devanagari. </li>
 </ul>