diff --git a/python/llm/example/CPU/Speculative-Decoding/baichuan2/README.md b/python/llm/example/CPU/Speculative-Decoding/baichuan2/README.md
index 91f2ca9d..9e13d373 100644
--- a/python/llm/example/CPU/Speculative-Decoding/baichuan2/README.md
+++ b/python/llm/example/CPU/Speculative-Decoding/baichuan2/README.md
@@ -73,7 +73,7 @@ python -m pip install oneccl_bind_pt==2.2.0 --extra-index-url https://pytorch-ex
 # if there is any installation problem for oneccl_binding, you can also find suitable index url at "https://pytorch-extension.intel.com/release-whl/stable/cpu/cn/" or "https://developer.intel.com/ipex-whl-stable-cpu" according to your environment.
 
 # Install other dependencies
-pip install -r requirements.txt
+python -m pip install transformers==4.36.2 transformers-stream-generator
 ```
 
 #### 4.2 Run Baichuan2 Models with IPEX
diff --git a/python/llm/example/CPU/Speculative-Decoding/baichuan2/requirements.txt b/python/llm/example/CPU/Speculative-Decoding/baichuan2/requirements.txt
deleted file mode 100644
index 11ab0b5e..00000000
--- a/python/llm/example/CPU/Speculative-Decoding/baichuan2/requirements.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-transformers==4.36.2
-transformers-stream-generator
diff --git a/python/llm/example/CPU/Speculative-Decoding/vicuna/requirements.txt b/python/llm/example/CPU/Speculative-Decoding/vicuna/requirements.txt
deleted file mode 100644
index 11ab0b5e..00000000
--- a/python/llm/example/CPU/Speculative-Decoding/vicuna/requirements.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-transformers==4.36.2
-transformers-stream-generator