description updated

app.py

@@ -6,11 +6,14 @@ qa_pipeline = pipeline(task="question-answering",model="Intel/bert-base-uncased-
 def greet(name):
     return "Hello " + name + "!!"
 
-def predict(context="There are seven continents in the world.",question="How many continents are there in the world?"):
+def predict(context,question):
     '''
     Sample prediction should return a dictionary of the form:
     {'score': 0.9376363158226013, 'start': 10, 'end': 15, 'answer': 'seven'}
-    
+    Score is the probability confidence score
+    Start is the starting character where it found the answer
+    End is the ending character where it found the answer
+    Answer is the part of the text it drew its answer from.
     '''
     predictions = qa_pipeline(context=context,question=question)
     print(f'predictions={predictions}')
@@ -21,11 +24,14 @@ def predict(context="There are seven continents in the world.",question="How man
     return score,answer,start
 
 md = """
-If you came looking for chatGPT, sorry to disappoint, but this is different. This prediction model is designed to answer a question about a text. It is designed to do reading comprehension. The model does not just answer questions in general -- it only works from the text that you provide. However, accomplishing accurate reading comprehension can be a very valuable task, especially if you are attempting to get quick answers from a large (and maybe boring!) document.
+Author of Hugging Face Space: Benjamin Consolvo, AI Solutions Engineer Manager at Intel \n
+Date last updated: 01/05/2023
 
-The model is based on the Zafrir et al. (2021) paper: [Prune Once for All: Sparse Pre-Trained Language Models](https://arxiv.org/abs/2111.05754) paper.
-Training dataset: SQuADv1.1, based on the Rajpurkar et al. (2016) paper: [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://aclanthology.org/D16-1264/)
+[b]Introduction[\b]: If you came looking for chatGPT, sorry to disappoint, but this is different. This prediction model is designed to answer a question about a text. It is designed to do reading comprehension. The model does not just answer questions in general -- it only works from the text that you provide. However, accomplishing accurate reading comprehension can be a very valuable task, especially if you are attempting to get quick answers from a large (and maybe boring!) document.
 
+The model is based on the Zafrir et al. (2021) paper: [Prune Once for All: Sparse Pre-Trained Language Models](https://arxiv.org/abs/2111.05754).
+
+The training dataset used is the English Wikipedia dataset (2500M words), followed by the SQuADv1.1 dataset containing 89K training examples by Rajpurkar et al. (2016): [100, 000+ questions for machine comprehension of text](https://arxiv.org/abs/1606.05250) 
 """
 
 # predict()
@@ -39,6 +45,7 @@ iface = gr.Interface(
     fn=predict, 
     inputs=[context,question],
     outputs=[score,start,answer],
+    examples=[],
     title = "Question & Answer with Sparse BERT using the SQuAD dataset",
     description = md
     )