diff --git a/CHANGELOG.md b/CHANGELOG.md
index 68288ec..66ae418 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -16,10 +16,10 @@
 
 ## Fixes and Improvements
 
-* Switch cpu backend to llama.cpp: https://github.com/TabbyML/tabby/pull/638
+* Cpu backend is switched to llama.cpp: https://github.com/TabbyML/tabby/pull/638
 * add `server.completion_timeout` to control the code completion interface timeout: https://github.com/TabbyML/tabby/pull/637
-* Switch cuda backend to llama.cpp: https://github.com/TabbyML/tabby/pull/656
-* Switch tokenizer to llama.cpp, so tabby no longer need to download additional tokenizer file: https://github.com/TabbyML/tabby/pull/683
+* Cuda backend is switched to llama.cpp: https://github.com/TabbyML/tabby/pull/656
+* Tokenizer implementation is switched to llama.cpp, so tabby no longer need to download additional tokenizer file: https://github.com/TabbyML/tabby/pull/683
 
 # v0.4.0