Update app.py

app.py

@@ -101,8 +101,9 @@ def qa(question):
         Query: {question}
         Answer:
         """
-    
-    return prompt
+    max_new_tokens = 2048
+    outputs =  model.generate(prompt=prompt, temp=0.5, top_k = 40, top_p = 1, max_tokens = max_new_tokens)
+    return outputs
 
 
 with gr.Blocks() as demo: