Minor

Author: DomInvivo

docs/design.md

@@ -4,6 +4,7 @@
 
 
 The library is designed with 3 things in mind:
+
 - High modularity and configurability with *YAML* files
 - Contain the state-of-the art GNNs, including positional encodings and graph Transformers
 - Massively multitasking across diverse and sparse datasets

graphium/trainer/predictor.py

@@ -682,9 +682,7 @@ def load_pretrained_models(name: str, device: str = None):
                 GRAPHIUM_PRETRAINED_MODELS_DICT[name], map_location=device
             )
         else:
-            return PredictorModule.load_from_checkpoint(
-                name, map_location=device
-            )
+            return PredictorModule.load_from_checkpoint(name, map_location=device)
 
     def set_max_nodes_edges_per_graph(self, datamodule: BaseDataModule, stages: Optional[List[str]] = None):
         datamodule.setup()