diff --git a/models/nlp/language_model/roberta/ixrt/README.md b/models/nlp/language_model/roberta/ixrt/README.md
index 5ba6e8880b088b23bc9d8b4205291309951f0624..0588c797f1f8bf147fe5d37607cf34c2821e7f6d 100644
--- a/models/nlp/language_model/roberta/ixrt/README.md
+++ b/models/nlp/language_model/roberta/ixrt/README.md
@@ -9,6 +9,10 @@ Language model pretraining has led to significant performance gains but careful
 ### Install
 
 ```bash
+export PROJ_ROOT=/PATH/TO/DEEPSPARKINFERENCE
+export MODEL_PATH=${PROJ_ROOT}/models/nlp/language_model/roberta/ixrt
+cd ${MODEL_PATH}
+
 pip3 install onnxsim
 pip3 install py-libnuma==1.2
 pip3 install bert
@@ -32,8 +36,7 @@ tar xf open_roberta.tar
 rm -f open_roberta.tar
 
 # get roberta-torch-fp32.json
-git clone -b iluvatar_general_infer https://github.com/yudefu/ByteMLPerf.git
-cp ./ByteMLPerf/byte_infer_perf/general_perf/model_zoo/roberta-torch-fp32.json ./
+wget https://raw.githubusercontent.com/bytedance/ByteMLPerf/main/byte_infer_perf/general_perf/model_zoo/roberta-torch-fp32.json
 
 # export onnx
 python3 export_onnx.py --model_path open_roberta/roberta-base-squad.pt --output_path open_roberta/roberta-torch-fp32.onnx
@@ -63,7 +66,8 @@ If you want to evaluate the accuracy of this model, please visit the website: <h
 For detailed steps regarding this model, please refer to this document: <https://github.com/yudefu/ByteMLPerf/blob/iluvatar_general_infer/byte_infer_perf/general_perf/backends/ILUVATAR/README.zh_CN.md> Note: You need to modify the relevant paths in the code to your own correct paths.
 
 ```bash
-# Install requirements
+# Link and install requirements
+ln -s ${PROJ_ROOT}/toolbox/ByteMLPerf ./
 pip3 install -r ./ByteMLPerf/byte_infer_perf/general_perf/requirements.txt
 pip3 install -r ./ByteMLPerf/byte_infer_perf/general_perf/backends/ILUVATAR/requirements.txt
 mv perf_engine.py ./ByteMLPerf/byte_infer_perf/general_perf/core/perf_engine.py
diff --git a/models/nlp/language_model/roformer/ixrt/README.md b/models/nlp/language_model/roformer/ixrt/README.md
index ba1e5975e0d0f6d094f3055aaf708c65dfed9b07..c088cf0f740821d5cc96557dbc53588f4ee5866f 100644
--- a/models/nlp/language_model/roformer/ixrt/README.md
+++ b/models/nlp/language_model/roformer/ixrt/README.md
@@ -26,7 +26,9 @@ Dataset: <https://lf-bytemlperf.17mh.cn/obj/bytemlperf-zoo/open_cail2019.tar>
 
 ```bash
 # Go to path of this model
-cd ${PROJ_ROOT}/models/nlp/language_model/roformer/ixrt
+export PROJ_ROOT=/PATH/TO/DEEPSPARKINFERENCE
+export MODEL_PATH=${PROJ_ROOT}/models/nlp/language_model/roformer/ixrt
+cd ${MODEL_PATH}
 
 # Download the pretrained model and dataset to 'data'
 mkdir -p data/
@@ -69,16 +71,17 @@ If you want to evaluate the accuracy of this model, please visit the website: <h
 For detailed steps regarding this model, please refer to this document: <https://github.com/yudefu/ByteMLPerf/blob/iluvatar_general_infer/byte_infer_perf/general_perf/backends/ILUVATAR/README.zh_CN.md> Note: You need to modify the relevant paths in the code to your own correct paths.
 
 ```bash
-# Clone ByteMLPerf
-git clone -b iluvatar_general_infer https://github.com/yudefu/ByteMLPerf.git
+# link ByteMLPerf and install requirements
+ln -s ${PROJ_ROOT}/toolbox/ByteMLPerf ./
 pip3 install -r ./ByteMLPerf/byte_infer_perf/general_perf/requirements.txt
+
 mv perf_engine.py ./ByteMLPerf/byte_infer_perf/general_perf/core/perf_engine.py
-mkdir -p ./ByteMLPerf/byte_infer_perf/general_perf/model_zoo/popular/
 
 # Comment Line102 in compile_backend_iluvatar.py
 sed -i '102s/build_engine/# build_engine/' ./ByteMLPerf/byte_infer_perf/general_perf/backends/ILUVATAR/compile_backend_iluvatar.py
 
 # Move open_roformer
+mkdir -p ./ByteMLPerf/byte_infer_perf/general_perf/model_zoo/popular/
 mv ./data/open_roformer ./ByteMLPerf/byte_infer_perf/general_perf/model_zoo/popular/
 
 # Setup open_cail2019 dataset
diff --git a/models/recommendation/widedeep/ixrt/README.md b/models/recommendation/widedeep/ixrt/README.md
index fb01a4d49378ff076dd712ca225bb352262d1f80..350a6da35f97da01cb2c82932c93dac64360f3cc 100644
--- a/models/recommendation/widedeep/ixrt/README.md
+++ b/models/recommendation/widedeep/ixrt/README.md
@@ -23,7 +23,9 @@ Dataset: <https://lf-bytemlperf.17mh.cn/obj/bytemlperf-zoo/eval.csv>
 
 ```bash
 # Go to path of this model
-cd ${PROJ_ROOT}/models/recommendationwidedeep/ixrt
+export PROJ_ROOT=/PATH/TO/DEEPSPARKINFERENCE
+export MODEL_PATH=${PROJ_ROOT}/models/recommendation/widedeep/ixrt
+cd ${MODEL_PATH}
 
 # export onnx
 python3 export_onnx.py --model_path open_wide_deep_saved_model --output_path open_wide_deep_saved_model/widedeep.onnx
@@ -55,8 +57,8 @@ If you want to evaluate the accuracy of this model, please visit the website: <h
 For detailed steps regarding this model, please refer to this document: <https://github.com/yudefu/ByteMLPerf/blob/iluvatar_general_infer/byte_infer_perf/general_perf/backends/ILUVATAR/README.zh_CN.md> Note: You need to modify the relevant paths in the code to your own correct paths.
 
 ```bash
-# Clone ByteMLPerf
-git clone -b iluvatar_general_infer https://github.com/yudefu/ByteMLPerf.git
+# link and install ByteMLPerf requirements
+ln -s ${PROJ_ROOT}/toolbox/ByteMLPerf ./
 pip3 install -r ./ByteMLPerf/byte_infer_perf/general_perf/requirements.txt
 mv perf_engine.py ./ByteMLPerf/byte_infer_perf/general_perf/core/perf_engine.py