Update README.md

README.md

@@ -10,6 +10,7 @@ library_name: adapter-transformers
 pipeline_tag: question-answering
 ---
 
+# Description
 This is the MADE encoder model created by Friedman et al. (2021). This encoder should be used along with the following dataset-specific adapters. 
 - https://huggingface.co/UKP-SQuARE/MADE_HotpotQA_Adapter
 - https://huggingface.co/UKP-SQuARE/MADE_TriviaQA_Adapter
@@ -18,6 +19,11 @@ This is the MADE encoder model created by Friedman et al. (2021). This encoder s
 - https://huggingface.co/UKP-SQuARE/MADE_NewsQA_Adapter
 - https://huggingface.co/UKP-SQuARE/MADE_NaturalQuestions_Adapter
 
+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
+
+
+
+# Evaluation Results
 Friedman et al. (2021) reported the following results:
 
 - SQuAD v1.1: 92.4
@@ -29,10 +35,7 @@ Friedman et al. (2021) reported the following results:
 - Avg: 82.2
 
 
-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
-
-
 Please refer to the original publication for more information.
 
-Citation: 
+# Citation
 Single-dataset Experts for Multi-dataset Question Answering (Friedman et al., EMNLP 2021)