Update README.md

README.md

@@ -52,9 +52,13 @@ Our codebase is hosted at https://github.com/VinAIResearch/DiMSUM.git. Please re
 
 To use DiMSUM pre trained model:
 ```python
-from dimsum.model_dims import DiM
+from huggingface_hub import hf_hub_download
 
-model = DiM.from_pretrained("haopt/dimsum-L2-imagenet256")
+# Assume model is already initiated
+ckpt_path = hf_hub_download("haopt/dimsum-L2-imagenet256")
+state_dict = torch.load(ckpt_path)
+model.load_state_dict(state_dict)
+model.eval()
 ```
 
 **Please CITE** our paper and give us a :star: whenever this repository is used to help produce published results or incorporated into other software.