diff --git a/applications/Chat/README.md b/applications/Chat/README.md
index 2a9c916d4..9ba831973 100644
--- a/applications/Chat/README.md
+++ b/applications/Chat/README.md
@@ -59,7 +59,7 @@ The Coati package provides a unified large language model framework that has imp
    Image source: https://openai.com/blog/chatgpt
 </div>
 
-**As Colossa-AI is undergoing some major updates, this project will be actively maintained to stay in line with the Colossal-AI project.**
+**As Colossal-AI is undergoing some major updates, this project will be actively maintained to stay in line with the Colossal-AI project.**
 
 
 More details can be found in the latest news.
diff --git a/applications/Chat/examples/README.md b/applications/Chat/examples/README.md
index 3e85bfe2d..a466d415d 100644
--- a/applications/Chat/examples/README.md
+++ b/applications/Chat/examples/README.md
@@ -233,7 +233,7 @@ If you want to support your own model in Coati, please refer the pull request fo
 You should complete the implementation of four model classes, including Reward model, Critic model, LM model, Actor model
 
 here are some example code for a NewModel named `Coati`.
-if it is supported in huggingaface [transformers](https://github.com/huggingface/transformers), you can load it by `from_pretrained`, o
+if it is supported in huggingface [transformers](https://github.com/huggingface/transformers), you can load it by `from_pretrained`, o
 r you can build your own model by yourself.
 
 ### Actor model