fix readme

README.md

@@ -40,7 +40,7 @@ Trying the following codes, you can perform the batched offline inference with t
 ```python
 from lmdeploy import pipeline, TurbomindEngineConfig
 engine_config = TurbomindEngineConfig(model_format='awq')
-pipe = pipeline("internlm/internlm2-chat-20b-4bits", engine_config)
+pipe = pipeline("internlm/internlm2-chat-20b-4bits", backend_config=engine_config)
 response = pipe(["Hi, pls intro yourself", "Shanghai is"])
 print(response)
 ```