Update README.md

README.md

@@ -9,7 +9,7 @@ A semi custom network trained from scratch for 799 epochs based on the follow pa
 
 This network uses the optimal transport flow matching objective outlined [Flow Matching for Generative Modeling](https://arxiv.org/abs/2210.02747)
 
-This is using multi head attention with no positional embeddings. [The Impact of Positional Encoding on Length Generalization in Transformers](https://arxiv.org/abs/2305.19466)
+This is using multi head attention with no positional encodings. [The Impact of Positional Encoding on Length Generalization in Transformers](https://arxiv.org/abs/2305.19466)
 
 xATGLU Layers are used in some places [Expanded Gating Ranges Improve Activation Functions](https://arxiv.org/pdf/2405.20768)