Fix hubconf example in README

README.md

@@ -107,10 +107,10 @@ The pre-trained models can be accessed via [PyTorch Hub](https://pytorch.org/hub
 ```python
 import torch
 
-aim_600m = torch.hub.load("apple/ml-aim", "aim-600M")
-aim_1b   = torch.hub.load("apple/ml-aim", "aim-1B")
-aim_3b   = torch.hub.load("apple/ml-aim", "aim-3B")
-aim_7b   = torch.hub.load("apple/ml-aim", "aim-7B")
+aim_600m = torch.hub.load("apple/ml-aim", "aim_600M")
+aim_1b   = torch.hub.load("apple/ml-aim", "aim_1B")
+aim_3b   = torch.hub.load("apple/ml-aim", "aim_3B")
+aim_7b   = torch.hub.load("apple/ml-aim", "aim_7B")
 ```
 
 ### Pre-trained backbones