Update README.md

README.md

@@ -15,9 +15,9 @@ We set the learning rate to 5e-5, with a batch size of 128 and a maximum length
 
 Load the model via the transformers library:
 ```python
-from transformers import AutoTokenizer, AutoModel
+from transformers import AutoTokenizer, AutoModelForCausalLM
 tokenizer = AutoTokenizer.from_pretrained("medicalai/ClinicalGPT-base-zh")
-model = AutoModel.from_pretrained("medicalai/ClinicalGPT-base-zh")
+model = AutoModelForCausalLM.from_pretrained("medicalai/ClinicalGPT-base-zh")
 ```
 
 ## Limitations