Update README.md

README.md

@@ -69,4 +69,4 @@ torchrun --nproc_per_node=8 --master_port=36646 train_alignment.py \
 
 Although this project aims to better align current LMs with social norms, inappropriate content and inherent biases in the training data will still impair the alignment of the model.
 
-SoGood LM should not be used directly in any application, without a prior assessment of safety and fairness concerns specific to the application.
+The model should not be used directly in any application, without a prior assessment of safety and fairness concerns specific to the application.