Update app.py

app.py

@@ -11,6 +11,7 @@ llm = Llama(
     model_path=model_path,
     n_ctx=2048,
     n_threads=4,
+    chat_format="llama-2",
     seed=42,
     f16_kv=True,
     logits_all=False,
@@ -27,14 +28,15 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
             messages.append({"role": "assistant", "content": assistant_msg})
     messages.append({"role": "user", "content": message})
     
-    response = llm.generate_chat(
-        messages,
+    response = llm.create_chat_completion(
+        messages=messages,
         max_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p
     )
     
-    return response
+    # Extract the assistant's message from the response
+    return response["choices"][0]["message"]["content"]
 
 demo = gr.ChatInterface(
     respond,
@@ -46,6 +48,5 @@ demo = gr.ChatInterface(
     ]
 )
 
-
 if __name__ == "__main__":
     demo.launch()