diff --git a/python/llm/example/CPU/PyTorch-Models/Model/llava/README.md b/python/llm/example/CPU/PyTorch-Models/Model/llava/README.md
index aa44bf44e44..51894e20656 100644
--- a/python/llm/example/CPU/PyTorch-Models/Model/llava/README.md
+++ b/python/llm/example/CPU/PyTorch-Models/Model/llava/README.md
@@ -20,13 +20,11 @@ conda activate llm
 
 # install the latest ipex-llm nightly build with 'all' option
 pip install --pre --upgrade ipex-llm[all] --extra-index-url https://download.pytorch.org/whl/cpu
-pip install einops # install dependencies required by llava
-pip install transformers==4.36.2
-
 git clone https://github.com/haotian-liu/LLaVA.git # clone the llava libary
-cp generate.py ./LLaVA/ # copy our example to the LLaVA folder
 cd LLaVA # change the working directory to the LLaVA folder
 git checkout tags/v1.2.0 -b 1.2.0 # Get the branch which is compatible with transformers 4.36
+pip install -e . # Install llava
+cd ..
 ```
 
 On Windows:
@@ -36,13 +34,12 @@ conda create -n llm python=3.11
 conda activate llm
 
 pip install --pre --upgrade ipex-llm[all]
-pip install einops
-pip install transformers==4.36.2
 
 git clone https://github.com/haotian-liu/LLaVA.git
-copy generate.py .\LLaVA\
 cd LLaVA
 git checkout tags/v1.2.0 -b 1.2.0
+pip install -e .
+cd ..
 ```
 
 ### 2. Run
diff --git a/python/llm/example/CPU/PyTorch-Models/Model/llava/generate.py b/python/llm/example/CPU/PyTorch-Models/Model/llava/generate.py
index 780ba963ba6..1ce930dee7c 100644
--- a/python/llm/example/CPU/PyTorch-Models/Model/llava/generate.py
+++ b/python/llm/example/CPU/PyTorch-Models/Model/llava/generate.py
@@ -291,7 +291,8 @@ def get_stopping_criteria(conv, tokenizer, input_ids):
     # Load model
     tokenizer, model, image_processor, _ = load_pretrained_model(model_path=model_path,
                                                                  model_base=None,
-                                                                 model_name=model_name)
+                                                                 model_name=model_name,
+                                                                 device_map=None)
 
     # With only one line to enable IPEX-LLM optimization on model
     model = optimize_model(model)