Update README.md

README.md

@@ -32,10 +32,10 @@ The model is mostly meant to be fine-tuned on a supervised dataset. See the [mod
 ### How to use
 
 ```python
-from transformers import AutoTokenizer, BartModel
+from transformers import AutoTokenizer, LongT5Model
 
 tokenizer = AutoTokenizer.from_pretrained("google/longt5-tglobal-large")
-model = BartModel.from_pretrained("google/longt5-tglobal-large")
+model = LongT5Model.from_pretrained("google/longt5-tglobal-large")
 
 inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
 outputs = model(**inputs)