edit app.py

app.py

@@ -1,20 +1,36 @@
 import gradio as gr
 from transformers import pipeline
 
+# Load the question-answering pipeline
 question_answerer = pipeline("question-answering",
                              model='kaiku03/Q-andA-bert-finetuned-squad-accelerate',
                              tokenizer='kaiku03/Q-andA-bert-finetuned-squad-accelerate')
 
+# Example contexts and questions
 examples = [
-    ["The capital of France is Paris.", "What is the capital of France?"],
+    ['''Statistics is the branch of mathematics that deals with the collection, analysis, interpretation, presentation, and organization of data. Here are the key components:
+Descriptive Statistics: These summarize and describe the features of a dataset. Key tools include:
+Measures of Central Tendency: Mean (average), median (middle value), and mode (most frequent value).
+Measures of Spread: Range (difference between highest and lowest values), variance (average squared deviation from the mean), and standard deviation (square root of variance).
+Graphs and Charts: Histograms, bar charts, pie charts, and box plots.
+Inferential Statistics: These make predictions or inferences about a population based on a sample of data. Key concepts include:
+Hypothesis Testing: A method for testing a claim or hypothesis about a parameter in a population, using sample data.
+Confidence Intervals: A range of values, derived from the sample, that is likely to contain the value of an unknown population parameter.
+Regression Analysis: A statistical process for estimating the relationships among variables.''', 
+     "What do you call the statistical process for estimating the relationships among variables?"],
     ["J.K. Rowling is the author of Harry Potter books.", "Who is the author of Harry Potter?"],
     ["The largest mammal is the blue whale.", "What is the largest mammal?"]
 ]
 
-interface = gr.Interface.from_pipeline(question_answerer,
-    title='Question Answering demo with transformers and gradio',
+# Create and launch the Gradio interface
+interface = gr.Interface.from_pipeline(
+    question_answerer,
+    title='Question Answering Demo with Transformers and Gradio',
     theme="peach",
     description='Enter a context and a related question, and this demo will provide an answer.',
     article='This demo was trained on the SQuAD dataset using only 5% of the training data and 2% of the validation data for the sake of speed',
-                                       
-    examples=examples).launch()
+    examples=examples
+)
+
+# Launch the interface with share enabled
+interface.launch(share=False)