diff --git a/.github/workflows/chatbot-finetune-mpt-7b-chat-hpu.yml b/.github/workflows/chatbot-finetune-mpt-7b-chat-hpu.yml
index a04214fc326..5cc9da539cc 100644
--- a/.github/workflows/chatbot-finetune-mpt-7b-chat-hpu.yml
+++ b/.github/workflows/chatbot-finetune-mpt-7b-chat-hpu.yml
@@ -32,13 +32,13 @@ jobs:
         run: |
           cid=$(docker ps -q --filter "name=chatbotfinetune-hpu-s0")
           if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid; fi
-          docker run -tid --runtime=habana -v /mnt/DP_disk1/huggingface/cache/:/root/.cache/huggingface/hub -v .:/root/chatbot -e http_proxy="${{ env.HTTP_PROXY_CONTAINER_RUN }}" -e https_proxy="${{ env.HTTPS_PROXY_CONTAINER_RUN }}" --name="chatbotfinetune-hpu-s0" --hostname="chatbotfinetune-container-mpi-s0" chatbotfinetune-hpu:latest
+          docker run -tid --runtime=habana -v /mnt/DP_disk1/huggingface/cache/:/root/.cache/huggingface/hub -e http_proxy="${{ env.HTTP_PROXY_CONTAINER_RUN }}" -e https_proxy="${{ env.HTTPS_PROXY_CONTAINER_RUN }}" --name="chatbotfinetune-hpu-s0" --hostname="chatbotfinetune-container-mpi-s0" chatbotfinetune-hpu:latest
 
       - name: Run Finetuning
         run: |
-          cmd="python3 /root/chatbot/workflows/chatbot/fine_tuning/instruction_tuning_pipeline/finetune_clm.py \
+          cmd="python3 /intel-extension-for-transformers/workflows/chatbot/fine_tuning/instruction_tuning_pipeline/finetune_clm.py \
             --model_name_or_path mosaicml/mpt-7b-chat \
-            --train_file /root/chatbot/.github/workflows/sample_data/alpaca_data_sample_45.json \
+            --train_file /intel-extension-for-transformers/.github/workflows/sample_data/alpaca_data_sample_45.json \
             --bf16 True \
             --output_dir ./mpt_peft_finetuned_model \
             --num_train_epochs 3 \
diff --git a/.github/workflows/chatbot-finetune-mpt-7b-chat.yml b/.github/workflows/chatbot-finetune-mpt-7b-chat.yml
index c237fed80a0..6cd400c09e2 100644
--- a/.github/workflows/chatbot-finetune-mpt-7b-chat.yml
+++ b/.github/workflows/chatbot-finetune-mpt-7b-chat.yml
@@ -32,7 +32,7 @@ jobs:
         run: |
           cid=$(docker ps -q --filter "name=chatbotfinetune-mpi-s0")
           if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid; fi
-          numactl --cpunodebind=0 -- docker run -tid -v /mnt/DP_disk1/huggingface/cache/:/root/.cache/huggingface/hub -v .:/root/chatbot -e http_proxy="${{ env.HTTP_PROXY_CONTAINER_RUN }}" -e https_proxy="${{ env.HTTPS_PROXY_CONTAINER_RUN }}" --name="chatbotfinetune-mpi-s0" --hostname="chatbotfinetune-container-mpi-s0" chatbotfinetune-mpi:latest
+          numactl --cpunodebind=0 -- docker run -tid -v /mnt/DP_disk1/huggingface/cache/:/root/.cache/huggingface/hub -e http_proxy="${{ env.HTTP_PROXY_CONTAINER_RUN }}" -e https_proxy="${{ env.HTTPS_PROXY_CONTAINER_RUN }}" --name="chatbotfinetune-mpi-s0" --hostname="chatbotfinetune-container-mpi-s0" chatbotfinetune-mpi:latest
           master=$(docker inspect -f "{{range.NetworkSettings.Networks}}{{.IPAddress}}{{end}}" "chatbotfinetune-mpi-s0")
           echo "master_node=$master" >> $GITHUB_OUTPUT
 
@@ -41,16 +41,16 @@ jobs:
         run: |
           cid=$(docker ps -q --filter "name=chatbotfinetune-mpi-s1")
           if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid; fi
-          numactl --cpunodebind=1 -- docker run -tid -v /mnt/DP_disk1/huggingface/cache/:/root/.cache/huggingface/hub -v .:/root/chatbot -e http_proxy="${{ env.HTTP_PROXY_CONTAINER_RUN }}" -e https_proxy="${{ env.HTTPS_PROXY_CONTAINER_RUN }}" --name="chatbotfinetune-mpi-s1" --hostname="chatbotfinetune-container-mpi-s1" chatbotfinetune-mpi:latest
+          numactl --cpunodebind=1 -- docker run -tid -v /mnt/DP_disk1/huggingface/cache/:/root/.cache/huggingface/hub -e http_proxy="${{ env.HTTP_PROXY_CONTAINER_RUN }}" -e https_proxy="${{ env.HTTPS_PROXY_CONTAINER_RUN }}" --name="chatbotfinetune-mpi-s1" --hostname="chatbotfinetune-container-mpi-s1" chatbotfinetune-mpi:latest
           slave=$(docker inspect -f "{{range.NetworkSettings.Networks}}{{.IPAddress}}{{end}}" "chatbotfinetune-mpi-s1")
           echo "slave_node=$slave" >> $GITHUB_OUTPUT
 
       - name: Run Finetuning
         run: |
           sh .github/workflows/script/chatbot/prepare_ft_mpt-7b-chat_mpi.sh ${{ steps.master_container.outputs.master_node }} ${{ steps.slave_container.outputs.slave_node }}
-          docker exec "chatbotfinetune-mpi-s0" bash -c "cd /root/chatbot && source activate && conda activate neuralchat && pip uninstall intel-extension-for-transformers -y && python setup.py install"
-          docker exec "chatbotfinetune-mpi-s1" bash -c "cd /root/chatbot && source activate && conda activate neuralchat && pip uninstall intel-extension-for-transformers -y && python setup.py install"
-          docker exec "chatbotfinetune-mpi-s0" bash -c "cd /root/chatbot; source ./bash_setup.sh; mpirun -f ./hosts2 -n 2 -ppn 1 -genv OMP_NUM_THREADS=48 sh .github/workflows/script/chatbot/start_ft_mpt-7b-chat_mpi.sh"
+          docker exec "chatbotfinetune-mpi-s0" bash -c "cd /intel-extension-for-transformers && source activate && conda activate neuralchat && pip uninstall intel-extension-for-transformers -y && python setup.py install"
+          docker exec "chatbotfinetune-mpi-s1" bash -c "cd /intel-extension-for-transformers && source activate && conda activate neuralchat && pip uninstall intel-extension-for-transformers -y && python setup.py install"
+          docker exec "chatbotfinetune-mpi-s0" bash -c "cd /intel-extension-for-transformers; source ./bash_setup.sh; mpirun -f ./hosts2 -n 2 -ppn 1 -genv OMP_NUM_THREADS=48 sh .github/workflows/script/chatbot/start_ft_mpt-7b-chat_mpi.sh"
 
       - name: Print Logs and Check Finetuning Status
         if: success() || failure()
diff --git a/.github/workflows/chatbot-inference-llama-2-7b-chat-hf.yml b/.github/workflows/chatbot-inference-llama-2-7b-chat-hf.yml
index 21819521632..149fc7c4484 100644
--- a/.github/workflows/chatbot-inference-llama-2-7b-chat-hf.yml
+++ b/.github/workflows/chatbot-inference-llama-2-7b-chat-hf.yml
@@ -28,11 +28,11 @@ jobs:
         run: |
           cid=$(docker ps -q --filter "name=chatbotinfer-gha")
           if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid; fi
-          docker run -tid -v /home/sdp/.cache/huggingface/hub:/root/.cache/huggingface/hub -v .:/root/chatbot -e http_proxy="${{ env.HTTP_PROXY_CONTAINER_RUN }}" -e https_proxy="${{ env.HTTPS_PROXY_CONTAINER_RUN }}" --name="chatbotinfer-gha" --hostname="chatbotinfer-gha-container" chatbotinfer-gha:latest
+          docker run -tid -v /home/sdp/.cache/huggingface/hub:/root/.cache/huggingface/hub -e http_proxy="${{ env.HTTP_PROXY_CONTAINER_RUN }}" -e https_proxy="${{ env.HTTPS_PROXY_CONTAINER_RUN }}" --name="chatbotinfer-gha" --hostname="chatbotinfer-gha-container" chatbotinfer-gha:latest
 
       - name: Run Inference Test
         run: |
-          docker exec "chatbotinfer-gha" bash -c "cd /root/chatbot && source activate && conda activate neuralchat;\
+          docker exec "chatbotinfer-gha" bash -c "cd /intel-extension-for-transformers && source activate && conda activate neuralchat;\
                  git config --global --add safe.directory '*' && \
                  git submodule update --init --recursive && \
                  pip uninstall intel-extension-for-transformers -y; \
@@ -45,7 +45,7 @@ jobs:
         if: always()
         run: |
           cid=$(docker ps -q --filter "name=chatbotinfer-gha")
-          if [[ ! -z "$cid" ]]; then docker exec "chatbotinfer-gha" bash -c "rm -rf /root/chatbot/* && rm -rf /root/chatbot/.* || echo Clean" && docker stop $cid && docker rm $cid; fi
+          if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid; fi
 
       - name: Test Summary
         run: echo "Inference completed successfully"
diff --git a/.github/workflows/chatbot-inference-llama-2-7b_70b-chat-hf-hpu.yml b/.github/workflows/chatbot-inference-llama-2-7b_70b-chat-hf-hpu.yml
index dee3b6ff49d..6cd4b966013 100644
--- a/.github/workflows/chatbot-inference-llama-2-7b_70b-chat-hf-hpu.yml
+++ b/.github/workflows/chatbot-inference-llama-2-7b_70b-chat-hf-hpu.yml
@@ -29,15 +29,15 @@ jobs:
         run: |
           cid=$(docker ps -q --filter "name=chatbotinfer-hpu")
           if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid; fi
-          docker run -tid --runtime=habana -v /mnt/DP_disk1/huggingface/cache/:/root/.cache/huggingface/hub -v .:/root/chatbot -e http_proxy="${{ env.HTTP_PROXY_CONTAINER_RUN }}" -e https_proxy="${{ env.HTTPS_PROXY_CONTAINER_RUN }}" --name="chatbotinfer-hpu" --hostname="chatbotinfer-hpu-container" chatbotinfer-hpu:latest
+          docker run -tid --runtime=habana -v /mnt/DP_disk1/huggingface/cache/:/root/.cache/huggingface/hub -e http_proxy="${{ env.HTTP_PROXY_CONTAINER_RUN }}" -e https_proxy="${{ env.HTTPS_PROXY_CONTAINER_RUN }}" --name="chatbotinfer-hpu" --hostname="chatbotinfer-hpu-container" chatbotinfer-hpu:latest
 
       - name: Run Inference Test without DeepSpeed
         run: |
-          docker exec "chatbotinfer-hpu" bash -c "cd /root/chatbot; python workflows/chatbot/inference/generate.py --base_model_path \"meta-llama/Llama-2-7b-chat-hf\" --hf_access_token \"${{ env.HF_ACCESS_TOKEN }}\" --habana --use_hpu_graphs --instructions \"Transform the following sentence into one that shows contrast. The tree is rotten.\" "
+          docker exec "chatbotinfer-hpu" bash -c "cd /intel-extension-for-transformers; python workflows/chatbot/inference/generate.py --base_model_path \"meta-llama/Llama-2-7b-chat-hf\" --hf_access_token \"${{ env.HF_ACCESS_TOKEN }}\" --habana --use_hpu_graphs --instructions \"Transform the following sentence into one that shows contrast. The tree is rotten.\" "
 
       - name: Run Inference Test with DeepSpeed
         run: |
-          docker exec "chatbotinfer-hpu" bash -c "cd /root/chatbot; export HABANA_VISIBLE_MODULES=\"0,1\"; python workflows/chatbot/utils/gaudi_spawn.py --use_deepspeed --world_size 2 workflows/chatbot/inference/generate.py --base_model_path \"meta-llama/Llama-2-7b-chat-hf\" --hf_access_token \"${{ env.HF_ACCESS_TOKEN }}\" --habana --use_hpu_graphs --use_kv_cache --task chat --instructions \"Transform the following sentence into one that shows contrast. The tree is rotten.\" "
+          docker exec "chatbotinfer-hpu" bash -c "cd /intel-extension-for-transformers; export HABANA_VISIBLE_MODULES=\"0,1\"; python workflows/chatbot/utils/gaudi_spawn.py --use_deepspeed --world_size 2 workflows/chatbot/inference/generate.py --base_model_path \"meta-llama/Llama-2-7b-chat-hf\" --hf_access_token \"${{ env.HF_ACCESS_TOKEN }}\" --habana --use_hpu_graphs --use_kv_cache --task chat --instructions \"Transform the following sentence into one that shows contrast. The tree is rotten.\" "
 
       - name: Stop Container
         if: success() || failure()
diff --git a/.github/workflows/chatbot-inference-mpt-7b-chat-hpu.yml b/.github/workflows/chatbot-inference-mpt-7b-chat-hpu.yml
index 2e185a7c478..407084adc36 100644
--- a/.github/workflows/chatbot-inference-mpt-7b-chat-hpu.yml
+++ b/.github/workflows/chatbot-inference-mpt-7b-chat-hpu.yml
@@ -30,11 +30,11 @@ jobs:
         run: |
           cid=$(docker ps -q --filter "name=chatbotinfer-hpu")
           if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid; fi
-          docker run -tid --runtime=habana -v /mnt/DP_disk1/huggingface/cache/:/root/.cache/huggingface/hub -v .:/root/chatbot -e http_proxy="${{ env.HTTP_PROXY_CONTAINER_RUN }}" -e https_proxy="${{ env.HTTPS_PROXY_CONTAINER_RUN }}" --name="chatbotinfer-hpu" --hostname="chatbotinfer-hpu-container" chatbotinfer-hpu:latest
+          docker run -tid --runtime=habana -v /mnt/DP_disk1/huggingface/cache/:/root/.cache/huggingface/hub -e http_proxy="${{ env.HTTP_PROXY_CONTAINER_RUN }}" -e https_proxy="${{ env.HTTPS_PROXY_CONTAINER_RUN }}" --name="chatbotinfer-hpu" --hostname="chatbotinfer-hpu-container" chatbotinfer-hpu:latest
 
       - name: Run Inference Test
         run: |
-          docker exec "chatbotinfer-hpu" bash -c "cd /root/chatbot; python workflows/chatbot/inference/generate.py --base_model_path \"mosaicml/mpt-7b-chat\" --habana --use_hpu_graphs --instructions \"Transform the following sentence into one that shows contrast. The tree is rotten.\" "
+          docker exec "chatbotinfer-hpu" bash -c "cd /intel-extension-for-transformers; python workflows/chatbot/inference/generate.py --base_model_path \"mosaicml/mpt-7b-chat\" --habana --use_hpu_graphs --instructions \"Transform the following sentence into one that shows contrast. The tree is rotten.\" "
 
       - name: Stop Container
         if: success() || failure()
diff --git a/.github/workflows/chatbot-inference-mpt-7b-chat.yml b/.github/workflows/chatbot-inference-mpt-7b-chat.yml
index 5180f57794d..633fd3dd0c9 100644
--- a/.github/workflows/chatbot-inference-mpt-7b-chat.yml
+++ b/.github/workflows/chatbot-inference-mpt-7b-chat.yml
@@ -29,11 +29,11 @@ jobs:
         run: |
           cid=$(docker ps -q --filter "name=chatbotinfer-gha")
           if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid; fi
-          docker run -tid -v /home/sdp/.cache/huggingface/hub:/root/.cache/huggingface/hub -v .:/root/chatbot -e http_proxy="${{ env.HTTP_PROXY_CONTAINER_RUN }}" -e https_proxy="${{ env.HTTPS_PROXY_CONTAINER_RUN }}" --name="chatbotinfer-gha" --hostname="chatbotinfer-gha-container" chatbotinfer-gha:latest
+          docker run -tid -v /home/sdp/.cache/huggingface/hub:/root/.cache/huggingface/hub -e http_proxy="${{ env.HTTP_PROXY_CONTAINER_RUN }}" -e https_proxy="${{ env.HTTPS_PROXY_CONTAINER_RUN }}" --name="chatbotinfer-gha" --hostname="chatbotinfer-gha-container" chatbotinfer-gha:latest
 
       - name: Run Inference Test
         run: |
-          docker exec "chatbotinfer-gha" bash -c "cd /root/chatbot && source activate && conda activate neuralchat; \
+          docker exec "chatbotinfer-gha" bash -c "cd /intel-extension-for-transformers && source activate && conda activate neuralchat; \
                  git config --global --add safe.directory '*' && \
                  git submodule update --init --recursive && \
                  pip uninstall intel-extension-for-transformers -y; \
@@ -46,7 +46,7 @@ jobs:
         if: always()
         run: |
           cid=$(docker ps -q --filter "name=chatbotinfer-gha")
-          if [[ ! -z "$cid" ]]; then docker exec "chatbotinfer-gha" bash -c "rm -rf /root/chatbot/* && rm -rf /root/chatbot/.* || echo Clean" && docker stop $cid && docker rm $cid; fi
+          if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid; fi
 
       - name: Test Summary
         run: echo "Inference completed successfully"
diff --git a/.github/workflows/script/chatbot/hpu_check/run_check.sh b/.github/workflows/script/chatbot/hpu_check/run_check.sh
index 0eeda395150..95f8ebaba7b 100644
--- a/.github/workflows/script/chatbot/hpu_check/run_check.sh
+++ b/.github/workflows/script/chatbot/hpu_check/run_check.sh
@@ -18,6 +18,5 @@ cid=$(docker ps -q --filter "name=$cont_name")
 if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid; fi
 
 # run checks
-script_dir=$(dirname "$0")
-docker run --rm --runtime=habana -v $script_dir:/root/chatbot --name="$cont_name" --hostname="chatbot-hpu-check-container" "$image_name" bash -c "python /root/chatbot/to_hpu.py"
+docker run --rm --runtime=habana --name="$cont_name" --hostname="chatbot-hpu-check-container" "$image_name" bash -c "python /intel-extension-for-transformers/.github/workflows/script/chatbot/hpu_check/to_hpu.py"
 
diff --git a/.github/workflows/script/chatbot/hpu_check/to_hpu.py b/.github/workflows/script/chatbot/hpu_check/to_hpu.py
index e559f69f5a7..ee7d2218c9b 100644
--- a/.github/workflows/script/chatbot/hpu_check/to_hpu.py
+++ b/.github/workflows/script/chatbot/hpu_check/to_hpu.py
@@ -1,5 +1,4 @@
 import torch
-from optimum.habana.transformers.modeling_utils import adapt_transformers_to_gaudi
 
 ly = torch.nn.Linear(2, 4)
 ly.to("hpu")
diff --git a/.github/workflows/script/chatbot/prepare_ft_mpt-7b-chat_mpi.sh b/.github/workflows/script/chatbot/prepare_ft_mpt-7b-chat_mpi.sh
index d01e29ecae6..b5c862c29d1 100644
--- a/.github/workflows/script/chatbot/prepare_ft_mpt-7b-chat_mpi.sh
+++ b/.github/workflows/script/chatbot/prepare_ft_mpt-7b-chat_mpi.sh
@@ -8,7 +8,7 @@ export I_MPI_HYDRA_IFACE=eth0
 EOF
 )"
 # for launching mpirun from yaml
-docker exec "chatbotfinetune-mpi-s0" bash -c "cd /root/chatbot; echo \"source activate && conda activate neuralchat\" > bash_setup.sh; echo export MASTER_ADDR=$master_node >> bash_setup.sh"
+docker exec "chatbotfinetune-mpi-s0" bash -c "cd /intel-extension-for-transformers; echo \"source activate && conda activate neuralchat\" > bash_setup.sh; echo export MASTER_ADDR=$master_node >> bash_setup.sh"
 # for ssh setup mpi and oneccl properly
 docker exec "chatbotfinetune-mpi-s0" bash -c "echo \"$prepare_script\" >> ~/.bashrc; echo export MASTER_ADDR=$master_node >> ~/.bashrc"
 
diff --git a/.github/workflows/script/chatbot/start_ft_mpt-7b-chat_mpi.sh b/.github/workflows/script/chatbot/start_ft_mpt-7b-chat_mpi.sh
index 37edbc5f3a3..ec899e42036 100644
--- a/.github/workflows/script/chatbot/start_ft_mpt-7b-chat_mpi.sh
+++ b/.github/workflows/script/chatbot/start_ft_mpt-7b-chat_mpi.sh
@@ -1,4 +1,4 @@
-cd /root/chatbot
+cd /intel-extension-for-transformers
 hname=$(hostname -s)
 python3 workflows/chatbot/fine_tuning/instruction_tuning_pipeline/finetune_clm.py \
     --model_name_or_path mosaicml/mpt-7b-chat \