Update app.py

app.py

@@ -48,7 +48,7 @@ def load_qa_model():
             "text-generation",
             model=model,
             tokenizer=tokenizer,
-            max_new_tokens=256,  # Limit generation as needed
+            max_new_tokens=1024,  # Limit generation as needed
         )
         
         return qa_pipeline