diff --git a/intel_extension_for_transformers/neural_chat/docker/Dockerfile b/intel_extension_for_transformers/neural_chat/docker/Dockerfile
index b09a20ce3ef..09ab00f65dc 100644
--- a/intel_extension_for_transformers/neural_chat/docker/Dockerfile
+++ b/intel_extension_for_transformers/neural_chat/docker/Dockerfile
@@ -70,13 +70,13 @@ RUN if [ -f /torch-2.0.1+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-l
 RUN if [ -f /torchaudio-2.0.2+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-linux_x86_64.whl ]; then source activate && conda activate neuralchat && pip install /torchaudio-2.0.2+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-linux_x86_64.whl; fi
 RUN if [ -f /torchvision-0.15.2+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-linux_x86_64.whl ]; then source activate && conda activate neuralchat && pip install /torchvision-0.15.2+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-linux_x86_64.whl; fi
 
-RUN source activate && conda activate neuralchat && pip install oneccl_bind_pt -f https://developer.intel.com/ipex-whl-stable-cpu && \
+RUN source activate && conda activate neuralchat && pip install oneccl_bind_pt==2.0.0 -f https://developer.intel.com/ipex-whl-stable-cpu && \
     cd /intel-extension-for-transformers && pip install -r requirements.txt && pip install -v . && \
     cd ./intel_extension_for_transformers/neural_chat/examples/instruction_tuning && pip install -r requirements.txt && \
     cd /intel-extension-for-transformers/intel_extension_for_transformers/neural_chat && pip install -r requirements_cpu.txt && \
-    conda install astunparse ninja pyyaml mkl mkl-include setuptools cmake cffi typing_extensions future six requests dataclasses -y && \
+    conda install astunparse ninja pyyaml mkl mkl-include setuptools cmake cffi future six requests dataclasses -y && \
     conda install jemalloc gperftools -c conda-forge -y && \
-    pip install datasets accelerate SentencePiece evaluate nltk rouge_score protobuf==3.20.1 tokenizers einops peft
+    pip install typing_extensions datasets accelerate SentencePiece evaluate nltk rouge_score protobuf==3.20.1 tokenizers einops peft
 
 # Enable passwordless ssh for mpirun
 RUN mkdir /var/run/sshd
diff --git a/intel_extension_for_transformers/neural_chat/docker/finetuning/Dockerfile b/intel_extension_for_transformers/neural_chat/docker/finetuning/Dockerfile
index cdfd8f571d2..bd33a2f9fd3 100644
--- a/intel_extension_for_transformers/neural_chat/docker/finetuning/Dockerfile
+++ b/intel_extension_for_transformers/neural_chat/docker/finetuning/Dockerfile
@@ -63,7 +63,7 @@ RUN conda init bash && \
     echo "conda activate chatbot-finetuning" >> ~/.bashrc && \
     source ~/.bashrc
 
-RUN source activate && conda activate chatbot-finetuning && pip install oneccl_bind_pt -f https://developer.intel.com/ipex-whl-stable-cpu && \
+RUN source activate && conda activate chatbot-finetuning && pip install oneccl_bind_pt==2.0.0 -f https://developer.intel.com/ipex-whl-stable-cpu && \
     pip install datasets torch accelerate SentencePiece evaluate nltk rouge_score protobuf==3.20.1 tokenizers einops && \
     git clone https://github.com/huggingface/peft.git && cd peft && python setup.py install && \
     cd /itrex && pip install -v . && \
diff --git a/intel_extension_for_transformers/neural_chat/docs/notebooks/multi_node_finetuning_on_spr.ipynb b/intel_extension_for_transformers/neural_chat/docs/notebooks/multi_node_finetuning_on_spr.ipynb
index 5e8f43e14bb..788f9145d89 100644
--- a/intel_extension_for_transformers/neural_chat/docs/notebooks/multi_node_finetuning_on_spr.ipynb
+++ b/intel_extension_for_transformers/neural_chat/docs/notebooks/multi_node_finetuning_on_spr.ipynb
@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -13,6 +14,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -21,7 +23,7 @@
     "```bash\n",
     "pip install -r requirements.txt\n",
     "# To use ccl as the distributed backend in distributed training on CPU requires to install below requirement.\n",
-    "python -m pip install oneccl_bind_pt==1.13 -f https://developer.intel.com/ipex-whl-stable-cpu\n",
+    "python -m pip install oneccl_bind_pt==2.0.0 -f https://developer.intel.com/ipex-whl-stable-cpu\n",
     "```\n",
     "\n",
     "Then, follow the [hugginface guide](https://huggingface.co/docs/transformers/perf_train_cpu_many) to install Intel® oneCCL Bindings for PyTorch, IPEX\n",
@@ -42,6 +44,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -56,6 +59,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
diff --git a/intel_extension_for_transformers/neural_chat/examples/instruction_tuning/README.md b/intel_extension_for_transformers/neural_chat/examples/instruction_tuning/README.md
index 66b02ca31bd..d25f15b1a38 100644
--- a/intel_extension_for_transformers/neural_chat/examples/instruction_tuning/README.md
+++ b/intel_extension_for_transformers/neural_chat/examples/instruction_tuning/README.md
@@ -18,7 +18,7 @@ Recommend python 3.9 or higher version.
 ```shell
 pip install -r requirements.txt
 # To use ccl as the distributed backend in distributed training on CPU requires to install below requirement.
-python -m pip install oneccl_bind_pt==1.13 -f https://developer.intel.com/ipex-whl-stable-cpu
+python -m pip install oneccl_bind_pt==2.0.0 -f https://developer.intel.com/ipex-whl-stable-cpu
 ```
 
 ## 2. Prepare the Model
diff --git a/workflows/chatbot/fine_tuning/README.md b/workflows/chatbot/fine_tuning/README.md
index a2c6e39bfcd..6bd52568499 100644
--- a/workflows/chatbot/fine_tuning/README.md
+++ b/workflows/chatbot/fine_tuning/README.md
@@ -18,7 +18,7 @@ Recommend python 3.9 or higher version.
 ```shell
 pip install -r requirements.txt
 # To use ccl as the distributed backend in distributed training on CPU requires to install below requirement.
-python -m pip install oneccl_bind_pt -f https://developer.intel.com/ipex-whl-stable-cpu
+python -m pip install oneccl_bind_pt==2.0.0 -f https://developer.intel.com/ipex-whl-stable-cpu
 ```
 
 ## 2. Prepare the Model