added output print functionality for testing

app.py

@@ -33,16 +33,21 @@ llm = Llama(model_path=filename, n_ctx=512, n_batch=126)
 def generate_text(prompt="Who is the CEO of Apple?"):
     output = llm(
         prompt,
-        max_tokens=256,
+        max_tokens=256, # max tokens to generate
         temperature=0.1,
         top_p=0.5,
-        echo=False,
+        echo=False, # whether to repeat prompt in output
         stop=["#"],
     )
     output_text = output["choices"][0]["text"].strip()
+    
+    print(output_text)
 
     # Remove Prompt Echo from Generated Text
     cleaned_output_text = output_text.replace(prompt, "")
+    
+    print(cleaned_output_text) 
+    
     return cleaned_output_text