updated app

app.py

@@ -15,7 +15,12 @@ llm = Llama(
 )
 
 def respond(prompt):
-    out = llm(prompt, max_tokens=256)
+    out = llm.create_completion(
+        prompt=prompt,
+        max_tokens=256,
+        temperature=0.7,
+        top_p=0.9,
+    )
     return out["choices"][0]["text"]
 
-gr.Interface(fn=respond, inputs="text", outputs="text").launch()
+gr.Interface(fn=respond, inputs="text", outputs="text").launch()