Update README.md

README.md

@@ -260,7 +260,7 @@ The instruction format is as follows:
 
 # Reproducing the Results
 
-We will realize the training code and the training data soon. Our training code is based on [Megatron-LM](https://github.com/NVIDIA/Megatron-LM), with some modifications to support our training data format and Maximal Update Parametrization (μP).
+We will release the training code and the training data soon. Our training code is based on [Megatron-LM](https://github.com/NVIDIA/Megatron-LM), with some modifications to support our training data format and Maximal Update Parametrization (μP).
 
 # CrystalChat Performance