diff --git a/intel_extension_for_transformers/neural_chat/docker/Dockerfile b/intel_extension_for_transformers/neural_chat/docker/Dockerfile
index 5329f56a22a..fed3fce8351 100644
--- a/intel_extension_for_transformers/neural_chat/docker/Dockerfile
+++ b/intel_extension_for_transformers/neural_chat/docker/Dockerfile
@@ -144,3 +144,49 @@ RUN cd /intel-extension-for-transformers/intel_extension_for_transformers/neural
 
 WORKDIR /intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/
 
+## NVIDIA GPU environment
+FROM nvidia/cuda:12.2.2-runtime-ubuntu22.04 as nvgpu
+
+ARG ITREX_VER=main
+ARG PYTHON_VERSION=3.9
+ARG REPO=https://github.com/intel/intel-extension-for-transformers.git
+
+# See http://bugs.python.org/issue19846
+ENV LANG C.UTF-8
+
+# Install system dependencies
+SHELL ["/bin/bash", "--login", "-c"]
+RUN apt-get update \
+    && apt-get install -y build-essential \
+    && apt-get install -y wget numactl git \
+    && apt-get install -y openssh-server \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+# Download ITREX code
+RUN git clone --single-branch --branch=${ITREX_VER} ${REPO} intel-extension-for-transformers
+
+# Install miniconda
+ENV CONDA_DIR /opt/conda
+RUN wget --quiet https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda.sh && \
+    /bin/bash ~/miniconda.sh -b -p /opt/conda
+
+# Put conda in path so we can use conda activate
+SHELL ["/bin/bash", "--login", "-c"]
+ENV PATH=$CONDA_DIR/bin:$PATH
+RUN conda init bash && \
+    unset -f conda && \
+    export PATH=$CONDA_DIR/bin/:${PATH} && \
+    conda config --add channels intel && \
+    conda create -yn neuralchat python=${PYTHON_VERSION} && \
+    echo "conda activate neuralchat" >> ~/.bashrc && \
+    echo "export PYTHONPATH=/intel-extension-for-transformers" >> ~/.bashrc && \
+    source ~/.bashrc
+
+RUN source activate && conda activate neuralchat && cd /intel-extension-for-transformers && \
+    pip install -r ./intel_extension_for_transformers/neural_chat/examples/instruction_tuning/requirements.txt && \
+    pip install -r ./intel_extension_for_transformers/neural_chat/requirements.txt
+
+WORKDIR /intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/
+
+CMD ["/usr/sbin/sshd", "-D"]
\ No newline at end of file
diff --git a/intel_extension_for_transformers/neural_chat/docker/finetuning/README.md b/intel_extension_for_transformers/neural_chat/docker/finetuning/README.md
index 3197ef4a8bf..2b61061d651 100644
--- a/intel_extension_for_transformers/neural_chat/docker/finetuning/README.md
+++ b/intel_extension_for_transformers/neural_chat/docker/finetuning/README.md
@@ -60,6 +60,20 @@ If you don't need to set proxy settings:
 docker build --build-arg UBUNTU_VER=22.04 -f /path/to/workspace/intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/docker/finetuning/Dockerfile -t chatbot_finetune . --target hpu
 ```
 
+### On Nvidia GPU Environment
+
+If you need to set proxy settings:
+
+```bash
+docker build --network=host --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f /path/to/workspace/intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/docker/Dockerfile -t chatbot_finetune . --target nvgpu
+```
+
+If you don't need to set proxy settings:
+
+```bash
+docker build -f /path/to/workspace/intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/docker/Dockerfile -t chatbot_finetune . --target nvgpu
+```
+
 ## 5. Create Docker Container
 Before creating your docker container, make sure the model has been downloaded to local. 
 
@@ -72,6 +86,10 @@ docker run -it --disable-content-trust --privileged --name="chatbot" --hostname=
 ```bash
 docker run -it --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e https_proxy -e http_proxy -e HTTPS_PROXY -e HTTP_PROXY -e no_proxy -e NO_PROXY -v /dev/shm:/dev/shm  -v /absolute/path/to/flan-t5-xl:/flan -v /absolute/path/to/alpaca_data.json:/dataset/alpaca_data.json --cap-add=sys_nice --net=host --ipc=host chatbot_finetuning:latest 
 ```
+### On Nvidia GPU Environment
+```bash
+docker run --gpus all -it --disable-content-trust --privileged --name="chatbot" --hostname="chatbot-container" --network=host -e https_proxy -e http_proxy -e HTTPS_PROXY -e HTTP_PROXY -e no_proxy -e NO_PROXY -v /dev/shm:/dev/shm -v /absolute/path/to/flan-t5-xl:/flan -v /absolute/path/to/alpaca_data.json:/dataset/alpaca_data.json "chatbot_finetune"
+```
 
 # Finetune