Update README.md

README.md

@@ -1,6 +1,6 @@
 This model has been pretrained on BEIR corpus without relevance-level supervision following the approach described in the paper **COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning**. The associated GitHub repository is available here https://github.com/OpenMatch/COCO-DR.
 
-This model is trained with BERT-laege as the backbone with 335M hyperparameters.
+This model is trained with BERT-large as the backbone with 335M hyperparameters.
 
 ---
 license: mit