Update README.md

README.md

@@ -11,6 +11,8 @@ license: cc-by-4.0
 
 # LTG-BERT for the BabyLM challenge
 
+This is the LTG-BERT baseline trained on [the 100MW BabyLM challenge dataset](https://babylm.github.io/).
+
 - Paper: [Trained on 100 million words and still in shape: BERT meets British National Corpus](https://arxiv.org/abs/2303.09859)
 - GitHub: [ltgoslo/ltg-bert](https://github.com/ltgoslo/ltg-bert)