diff --git a/README_cn.md b/README_cn.md
index b37fa6424c10554a62cb82db1b777e9e00214d38..56f7e0177398d177e5eee5e70dbe59a677d12d97 100644
--- a/README_cn.md
+++ b/README_cn.md
@@ -15,7 +15,7 @@ PaddleDetection模块化地实现了多种主流目标检测算法，提供了
 </div>
 
 ### 产品动态
-- 2021.02.07: 发布release/2.0-beta1版本，PaddleDetection动态图试用版本，详情参考[PaddleDetection动态图](dygraph)。
+- 2021.02.07: 发布release/2.0-rc版本，PaddleDetection动态图试用版本，详情参考[PaddleDetection动态图](dygraph)。
 - 2020.11.20: 发布release/0.5版本,详情请参考[版本更新文档](docs/CHANGELOG.md)。
 - 2020.11.10: 添加实例分割模型[SOLOv2](configs/solov2)，在Tesla V100上达到38.6 FPS, COCO-val数据集上mask ap达到38.8，预测速度提高24%，mAP提高2.4个百分点。
 - 2020.10.30: PP-YOLO支持矩形图像输入，并新增PACT模型量化策略。
diff --git a/dygraph/README.md b/dygraph/README.md
index 329d12b3224eb20cacbf485a2fa852f59f58a56f..7661b032985a882ab54634478a73ec8820283917 100644
--- a/dygraph/README.md
+++ b/dygraph/README.md
@@ -127,12 +127,16 @@ PaddleDetection模块化地实现了多种主流目标检测算法，提供了
 
 ## 文档教程
 
-### 教程
+### 入门教程
 
 - [安装说明](docs/tutorials/INSTALL_cn.md)
 - [快速开始](docs/tutorials/QUICK_START_cn.md)
 - [如何准备数据](docs/tutorials/PrepareDataSet.md)
 - [训练/评估/预测流程](docs/tutorials/GETTING_STARTED_cn.md)
+
+### 进阶教程
+
+- [模型压缩](configs/slim)
 - [推理部署](deploy)
     - [模型导出教程](deploy/EXPORT_MODEL.md)
     - [Python端推理部署](deploy/python)
diff --git a/dygraph/setup.py b/dygraph/setup.py
index 2ecdc8c478e0cd148e84b0f37a84ad4547265767..5c2f365b3cc9e5f1d46411f965c09fbf40ae96a6 100644
--- a/dygraph/setup.py
+++ b/dygraph/setup.py
@@ -35,8 +35,14 @@ def package_model_zoo():
     from ppdet.model_zoo import MODEL_ZOO_FILENAME
     cur_dir = osp.dirname(osp.realpath(__file__))
     cfg_dir = osp.join(cur_dir, "configs")
-    cfgs = glob.glob(osp.join(cfg_dir, '*.yml'))
-    model_names = [osp.splitext(osp.split(cfg)[1])[0] for cfg in cfgs]
+    cfgs = glob.glob(osp.join(cfg_dir, '*/*.yml'))
+
+    valid_cfgs = []
+    for cfg in cfgs:
+        # exclude dataset base config
+        if osp.split(osp.split(cfg)[0])[1] not in ['datasets']:
+            valid_cfgs.append(cfg)
+    model_names = [osp.splitext(osp.split(cfg)[1])[0] for cfg in valid_cfgs]
 
     model_zoo_file = osp.join(cur_dir, 'ppdet', 'model_zoo', MODEL_ZOO_FILENAME)
     with open(model_zoo_file, 'w') as wf:
@@ -64,7 +70,7 @@ if __name__ == "__main__":
         packages=find_packages(exclude=("configs", "tools", "deploy")),
         package_data={'ppdet.model_zoo': package_model_zoo()},
         author='PaddlePaddle',
-        version='2.0-beta',
+        version='2.0-rc',
         install_requires=parse_requirements('./requirements.txt'),
         description='Object detection and instance segmentation toolkit based on PaddlePaddle',
         long_description=readme(),