diff --git a/deploy/slim/README.md b/deploy/slim/README.md
index eed8aa3b21f5af6f0168d77f30c770cb6dbc1857..4e6ab72b9a386d98817fd915ba41aeef03e15187 100644
--- a/deploy/slim/README.md
+++ b/deploy/slim/README.md
@@ -125,7 +125,7 @@ python3.7 -m paddle.distributed.launch \
 在得到在线量化训练、模型剪枝保存的模型后，可以将其导出为inference model，用于预测部署，以模型剪枝为例：
 
 ```bash
-python3.7 tools/export.py \
+python3.7 tools/export_model.py \
     -c ppcls/configs/slim/ResNet50_vd_prune.yaml \
     -o Global.pretrained_model=./output/ResNet50_vd/best_model \
     -o Global.save_inference_dir=./inference
diff --git a/deploy/slim/README_en.md b/deploy/slim/README_en.md
index d7a978f467ae5f8b754606112d5799d43e2c0417..36284762f48773985a83e1ce32fe6f35f072e750 100644
--- a/deploy/slim/README_en.md
+++ b/deploy/slim/README_en.md
@@ -127,7 +127,7 @@ python3.7 -m paddle.distributed.launch \
 After getting the compressed model, we can export it as inference model for predictive deployment. Using pruned model as example:
 
 ```bash
-python3.7 tools/export.py \
+python3.7 tools/export_model.py \
     -c ppcls/configs/slim/ResNet50_vd_prune.yaml \
     -o Global.pretrained_model=./output/ResNet50_vd/best_model
     -o Global.save_inference_dir=./inference
diff --git a/docs/en/advanced_tutorials/model_prune_quantization_en.md b/docs/en/advanced_tutorials/model_prune_quantization_en.md
index 1946cfa5fb1e67c64fc97b5cd35d3f9c66ad9662..f75aa1440b6eb5e7963d21925a859d0f7a82be99 100644
--- a/docs/en/advanced_tutorials/model_prune_quantization_en.md
+++ b/docs/en/advanced_tutorials/model_prune_quantization_en.md
@@ -157,7 +157,7 @@ python3.7 -m paddle.distributed.launch \
 Having obtained the saved model after online quantization training and pruning, it can be exported as an inference model for inference deployment. Here we take model pruning as an example:
 
 ```
-python3.7 tools/export.py \
+python3.7 tools/export_model.py \
     -c ppcls/configs/slim/ResNet50_vd_prune.yaml \
     -o Global.pretrained_model=./output/ResNet50_vd/best_model \
     -o Global.save_inference_dir=./inference
diff --git a/docs/zh_CN/training/advanced/prune_quantization.md b/docs/zh_CN/training/advanced/prune_quantization.md
index 6d2fae5d0eda03d1dca0d23410469d06146c7f39..27921f055ec581dc57626bd082eb980bc330653b 100644
--- a/docs/zh_CN/training/advanced/prune_quantization.md
+++ b/docs/zh_CN/training/advanced/prune_quantization.md
@@ -151,7 +151,7 @@ python3.7 -m paddle.distributed.launch \
 在得到在线量化训练、模型剪枝保存的模型后，可以将其导出为 inference model，用于预测部署，以模型剪枝为例：
 
 ```bash
-python3.7 tools/export.py \
+python3.7 tools/export_model.py \
     -c ppcls/configs/slim/ResNet50_vd_prune.yaml \
     -o Global.pretrained_model=./output/ResNet50_vd/best_model \
     -o Global.save_inference_dir=./inference