diff --git a/models/nlp/language_model/albert/ixrt/README.md b/models/nlp/language_model/albert/ixrt/README.md
index 55a22ced7f147d755ac14af7df6982bece54c38a..29e41623354e16bca9be8afb67ff78a2071ae8ff 100644
--- a/models/nlp/language_model/albert/ixrt/README.md
+++ b/models/nlp/language_model/albert/ixrt/README.md
@@ -37,7 +37,7 @@ bash /scripts/prepare_model_and_dataset.sh
 Please correct the paths in the following commands or files.
 ```bash
 tar -xvf open_albert.tar
-wget < https://github.com/bytedance/ByteMLPerf/blob/main/byte_infer_perf/general_perf/model_zoo/albert-torch-fp32.json >
+wget <https://raw.githubusercontent.com/bytedance/ByteMLPerf/main/byte_infer_perf/general_perf/model_zoo/albert-torch-fp32.json >
 python3 torch2onnx.py --model_path albert-base-squad.pt --output_path albert-torch-fp32.onnx
 onnxsim albert-torch-fp32.onnx albert-torch-fp32-sim.onnx
 
@@ -61,38 +61,29 @@ bash scripts/infer_albert_fp16_performance.sh
 
 ### Accuracy
 
-If you want to evaluate the accuracy of this model, please visit the website: < https://github.com/yudefu/ByteMLPerf/tree/iluvatar_general_infer >, which integrates inference and training of many models under this framework, supporting the ILUVATAR backend
+If you want to evaluate the accuracy of this model, please visit here: <toolbox/ByteMLPerf/tree/iluvatar_general_infer>, which integrates inference and training of many models under this framework, supporting the ILUVATAR backend
 
-```bash
-
-git clone https://github.com/yudefu/ByteMLPerf.git -b iluvatar_general_infer
-```
 
-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.
+For detailed steps regarding this model, please refer to this document: <toolbox/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
 
-pip3 install -r https://github.com/yudefu/ByteMLPerf/blob/iluvatar_general_infer/byte_infer_perf/general_perf/requirements.txt
-mv /ixrt/perf_engine.py /ByteMLPerf/byte_infer_perf/general_perf/core/perf_engine.py
+pip3 install -r toolbox/ByteMLPerf/blob/iluvatar_general_infer/byte_infer_perf/general_perf/requirements.txt
+mv /ixrt/perf_engine.py toolbox/ByteMLPerf/byte_infer_perf/general_perf/core/perf_engine.py
 sftp -P 29880 vipzjtd@iftp.iluvatar.com.cn     密码：123..com
 get /upload/3-app/byteperf/madlag.tar
 exit
 tar -zxvf madlag.tar
 
-接着修改代码：ByteMLPerf/byte_infer_perf/general_perf/datasets/open_squad/data_loader.py
+接着修改代码：toolbox/ByteMLPerf/byte_infer_perf/general_perf/datasets/open_squad/data_loader.py
 AutoTokenizer.from_pretrained("madlag/albert-base-v2-squad") => AutoTokenizer.from_pretrained("/Your/Path/madlag/albert-base-v2-squad")
 
-cd /ByteMLPerf/byte_infer_perf/
+cd toolbox/ByteMLPerf/byte_infer_perf/
 mv /general_perf/general_perf/model_zoo/popular/open_albert /general_perf/model_zoo/popular/open_albert
-cd /ByteMLPerf/byte_infer_perf/general_perf
+cd /toolboxByteMLPerf/byte_infer_perf/general_perf
 python3 core/perf_engine.py --hardware_type ILUVATAR --task albert-torch-fp32
 ```
 
-If report ModuleNotFoundError: No module named 'tensorrt_legacy',Please fix:
-<ByteMLPerf/byte_infer_perf/general_perf/backends/ILUVATAR/common.py> "tensorrt_legacy" to "tensorrt"
-<ByteMLPerf/byte_infer_perf/general_perf/backends/ILUVATAR/compile_backend_iluvatar.py> "tensorrt_legacy" to "tensorrt"
-<ByteMLPerf/byte_infer_perf/general_perf/backends/ILUVATAR/runtime_backend_iluvatar.py> "tensorrt_legacy" to "tensorrt"
-
 
 ## Results