Update README.md

README.md

@@ -2,6 +2,10 @@
 language: en
 datasets:
 - squad_v2
+tags:
+- QA
+- long context
+- Q&A
 ---
 
 # Longformer-base-4096 fine-tuned on SQuAD v2
@@ -18,20 +22,22 @@ Longformer uses a combination of a sliding window (local) attention and global a
 
 ## Details of the downstream task (Q&A) - Dataset 📚 🧐 ❓
 
-Dataset ID: ```squad_v2``` from  [HugginFace/NLP](https://github.com/huggingface/nlp)
+Dataset ID: ```squad_v2``` from  [HuggingFace/Datasets](https://github.com/huggingface/datasets)
 
 | Dataset  | Split | # samples |
 | -------- | ----- | --------- |
 | squad_v2 | train | 130319     |
 | squad_v2 | valid  | 11873     |
 
-How to load it from [nlp](https://github.com/huggingface/nlp)
+How to load it from [datasets](https://github.com/huggingface/datasets)
 
 ```python
-train_dataset  = nlp.load_dataset('squad_v2', split=nlp.Split.TRAIN)
-valid_dataset = nlp.load_dataset('squad_v2', split=nlp.Split.VALIDATION)
+!pip install datasets
+from datasets import load_dataset
+dataset = load_dataset('squad_v2')
 ```
-Check out more about this dataset and others in [NLP Viewer](https://huggingface.co/nlp/viewer/)
+
+Check out more about this dataset and others in [NLP Viewer](https://huggingface.co/datasets/viewer/)
 
 
 ## Model fine-tuning 🏋️‍