Update README.md

README.md

@@ -59,7 +59,7 @@ For instruction-tuned modesl, we adapt the [LLaMA2](https://huggingface.co/meta-
 {{ user_message }} [/INST]
 ```
 
-The model could be load via `AutoModelForCausalLM` and `text-generation-inference` with `trust_remote_code=True`:
+The model could be load via `AutoModelForCausalLM` or `text-generation-inference` with `trust_remote_code=True`:
 ```python
 taiwan_elm_270m = AutoModelForCausalLM.from_pretrained("liswei/Taiwan-ELM-270M", trust_remote_code=True)
 ```