Update README.md

README.md

@@ -18,7 +18,7 @@ This is the single-dataset adapter for the TriviaQA partition of the MRQA 2019 S
 The UKP-SQuARE team created this model repository to simplify the deployment of this model on the UKP-SQuARE platform. The GitHub repository of the original authors is https://github.com/princeton-nlp/MADE
 
 # Usage
-This model contains the same weights as https://huggingface.co/princeton-nlp/MADE/resolve/main/single_dataset_ft/TriviaQA/model.pt. The only difference is that our repository follows the standard format of AdapterHub. Therefore, you could load this model as follows:
+This model contains the same weights as https://huggingface.co/princeton-nlp/MADE/resolve/main/single_dataset_adapters/TriviaQA/model.pt. The only difference is that our repository follows the standard format of AdapterHub. Therefore, you could load this model as follows:
 
 ```
 from transformers import RobertaForQuestionAnswering, RobertaTokenizerFast
@@ -36,7 +36,7 @@ pipe({"question": "What is the capital of Germany?",  "context": "The capital of
 Note you need the adapter-transformers library https://adapterhub.ml
 
 # Evaluation
-Friedman et al. report an F1 score of 79.6 on TriviaQA.
+Friedman et al. report an F1 score of **79.6 on TriviaQA**.
 
 Please refer to the original publication for more information.