Update README.md

README.md

@@ -10,7 +10,7 @@ This version of DNABERT2 has been changed to be able to output the attention too
 
 **To the author of DNABERT2, feel free to use those modifications.**
 
-Use  ```--model_name_or_path jaandoui/DNABERT2_AttentionExtracted``` instead of the original repository to have access to the attention.
+Use  ```--model_name_or_path jaandoui/DNABERT2-AttentionExtracted``` instead of the original repository to have access to the attention.
 
 Most of the modifications were done in Bert_Layer.py. 
 It has been modified especially for fine tuning and hasn't been tried for pretraining.