Update README.md

README.md

@@ -14,8 +14,8 @@ information and tips on how to best run the model.
 
 ## Usage
 The default adapter uses cosine distance training, while an alternative variant
-trained with MSE can be loaded by specifying `variant="mse"` in the
-`load_adapter` function.
+trained with MSE can be loaded by specifying
+`adapter_kwargs=dict(revision="mse")` in the `load_adapter` function.
 
 ```python
 from detikzify.model import load, load_adapter
@@ -30,7 +30,7 @@ pipeline = DetikzifyPipeline(
             torch_dtype="bfloat16",
         ),
         adapter_name_or_path="nllg/tikzero-adapter",
-        #variant="mse" # load variant trained with MSE
+        adapter_kwargs=dict(revision="mse") # load variant trained with MSE
     )
 )