Update README.md

README.md

@@ -37,7 +37,7 @@ The results below measure the diversity between models' outputs. For each label,
 
 The results below demonstrate the efficiency of our generated synthetic dataset to train an NER model compared to when using real data.
 
-![Downstream NER Evaluation](docs/imgs/NER_Results_Graph.png)
+![Downstream NER Evaluation](NER_Results_Graph.png)
 
 ## Thank you
 Feel free to use LT3 for any research purpose.