diff --git a/doc/doc_ch/algorithm_det_drrg.md b/doc/doc_ch/algorithm_det_drrg.md
index b3d533b28005e86d8363e90c9c3815539a45d9fc..d89a16ae68b7024238a3982a342ef39764da9d16 100644
--- a/doc/doc_ch/algorithm_det_drrg.md
+++ b/doc/doc_ch/algorithm_det_drrg.md
@@ -23,7 +23,7 @@
 
 | 模型  |骨干网络|配置文件|precision|recall|Hmean|下载链接|
 |-----| --- | --- | --- | --- | --- | --- |
-| DRRG | ResNet50_vd | [configs/det/det_r50_drrg_ctw.yml](../../configs/det/det_r50_drrg_ctw.yml)| 89.92%|80.91%|85.18%|[训练模型](drrg_model)|
+| DRRG | ResNet50_vd | [configs/det/det_r50_drrg_ctw.yml](../../configs/det/det_r50_drrg_ctw.yml)| 89.92%|80.91%|85.18%|[训练模型](https://paddleocr.bj.bcebos.com/contribution/det_r50_drrg_ctw.tar)|
 
 <a name="2"></a>
 ## 2. 环境配置
diff --git a/doc/doc_ch/algorithm_overview.md b/doc/doc_ch/algorithm_overview.md
index 202c4a79e02920e110ed2b3b1abde9ceed704be3..2dfece9da6b3bad7ca9b9ff8dd95cbb20a9f2a87 100755
--- a/doc/doc_ch/algorithm_overview.md
+++ b/doc/doc_ch/algorithm_overview.md
@@ -55,7 +55,7 @@ PaddleOCR将**持续新增**支持OCR领域前沿算法与模型，**欢迎广
 |模型|骨干网络|precision|recall|Hmean|下载链接|
 | --- | --- | --- | --- | --- | --- |  
 |FCE|ResNet50_dcn|88.39%|82.18%|85.27%|[训练模型](https://paddleocr.bj.bcebos.com/contribution/det_r50_dcn_fce_ctw_v2.0_train.tar)|
-|DRRG|ResNet50_vd|89.92%|80.91%|85.18%|[训练模型](drrg_model)|
+|DRRG|ResNet50_vd|89.92%|80.91%|85.18%|[训练模型](https://paddleocr.bj.bcebos.com/contribution/det_r50_drrg_ctw.tar)|
 
 **说明：** SAST模型训练额外加入了icdar2013、icdar2017、COCO-Text、ArT等公开数据集进行调优。PaddleOCR用到的经过整理格式的英文公开数据集下载：
 * [百度云地址](https://pan.baidu.com/s/12cPnZcVuV1zn5DOd4mqjVw) (提取码: 2bpi)
diff --git a/doc/doc_en/algorithm_det_drrg_en.md b/doc/doc_en/algorithm_det_drrg_en.md
index 837f5c2008f46ff33f9538c09348b3b29cdb5043..2bb7b5703dab89526345e3dcbbb55d6c90ed1c0c 100644
--- a/doc/doc_en/algorithm_det_drrg_en.md
+++ b/doc/doc_en/algorithm_det_drrg_en.md
@@ -25,7 +25,7 @@ On the CTW1500 dataset, the text detection result is as follows:
 
 |Model|Backbone|Configuration|Precision|Recall|Hmean|Download|
 | --- | --- | --- | --- | --- | --- | --- |
-| DRRG | ResNet50_vd | [configs/det/det_r50_drrg_ctw.yml](../../configs/det/det_r50_drrg_ctw.yml)| 89.92%|80.91%|85.18%|[trained model](drrg_model)|
+| DRRG | ResNet50_vd | [configs/det/det_r50_drrg_ctw.yml](../../configs/det/det_r50_drrg_ctw.yml)| 89.92%|80.91%|85.18%|[trained model](https://paddleocr.bj.bcebos.com/contribution/det_r50_drrg_ctw.tar)|
 
 <a name="2"></a>
 ## 2. Environment
diff --git a/doc/doc_en/algorithm_overview_en.md b/doc/doc_en/algorithm_overview_en.md
index 175dcd7a9d1ff615deaf74ab75ed08f0a799fac9..bbab2638418c32f871d73356f6fff17f9b98f685 100755
--- a/doc/doc_en/algorithm_overview_en.md
+++ b/doc/doc_en/algorithm_overview_en.md
@@ -53,7 +53,7 @@ On CTW1500 dataset, the text detection result is as follows:
 |Model|Backbone|Precision|Recall|Hmean| Download link|
 | --- | --- | --- | --- | --- |---|  
 |FCE|ResNet50_dcn|88.39%|82.18%|85.27%| [trained model](https://paddleocr.bj.bcebos.com/contribution/det_r50_dcn_fce_ctw_v2.0_train.tar) |
-|DRRG|ResNet50_vd|89.92%|80.91%|85.18%|[trained model](drrg_model)|
+|DRRG|ResNet50_vd|89.92%|80.91%|85.18%|[trained model](https://paddleocr.bj.bcebos.com/contribution/det_r50_drrg_ctw.tar)|
 
 **Note：** Additional data, like icdar2013, icdar2017, COCO-Text, ArT, was added to the model training of SAST. Download English public dataset in organized format used by PaddleOCR from:
 * [Baidu Drive](https://pan.baidu.com/s/12cPnZcVuV1zn5DOd4mqjVw) (download code: 2bpi).