diff --git a/PaddleNLP/README.md b/PaddleNLP/README.md
index 660ac9a7030951082943442d6080c7073871a873..e3ce07f8e097cb947b4913c4851bccd646e63928 100644
--- a/PaddleNLP/README.md
+++ b/PaddleNLP/README.md
@@ -99,6 +99,15 @@ For more pretrained model selection, please refer to [Pretrained-Models](./docs/
 
 Please refer to our official AI Studio account for more interactive tutorials: [PaddleNLP on AI Studio](https://aistudio.baidu.com/aistudio/personalcenter/thirdview/574995)
 
+* [paddlenlp.seq2vec是什么? 瞧瞧它怎么完成情感分析教程](https://aistudio.baidu.com/aistudio/projectdetail/1294333) shows how to use lstm to do sentiment analysis.
+
+* [使用PaddleNLP语义预训练模型ERNIE优化情感分析教程](https://aistudio.baidu.com/aistudio/projectdetail/1283423) shows how to exploit the pretrained ERNIE to make sentiment analysis better.
+
+* [基于Bi-GRU+CRF的快递单信息抽取](https://aistudio.baidu.com/aistudio/projectdetail/1317771) shows how to make use of bigru and crf to do information extraction.
+
+* [使用PaddleNLP预训练模型ERNIE优化快递单信息抽取](https://aistudio.baidu.com/aistudio/projectdetail/1329361) shows how to exploit the pretrained ERNIE to do information extraction better.
+
+
 ## Community
 
 * SIG for Pretrained Model Contribution
diff --git a/PaddleNLP/README_en.md b/PaddleNLP/README_en.md
index 576597d40833a21e366a4aa2df782d9d7539b7b7..66d6ea65e2efbeb0c5c3435a64aca13ecc61a9a1 100644
--- a/PaddleNLP/README_en.md
+++ b/PaddleNLP/README_en.md
@@ -87,10 +87,22 @@ For more pretrained model selection, please refer to [PretrainedModels](./paddle
 * [Metrics API](./docs/embeddings.md)
 * [Models API](./docs/models.md)
 
+
+
+
 ## Tutorials
 
 Please refer to our official AI Studio account for more interactive tutorials: [PaddleNLP on AI Studio](https://aistudio.baidu.com/aistudio/personalcenter/thirdview/574995)
 
+* [paddlenlp.seq2vec是什么? 瞧瞧它怎么完成情感分析教程](https://aistudio.baidu.com/aistudio/projectdetail/1294333) shows how to use lstm to do sentiment analysis.
+
+* [使用PaddleNLP语义预训练模型ERNIE优化情感分析教程](https://aistudio.baidu.com/aistudio/projectdetail/1283423) shows how to exploit the pretrained ERNIE to make sentiment analysis better.
+
+* [基于Bi-GRU+CRF的快递单信息抽取](https://aistudio.baidu.com/aistudio/projectdetail/1317771) shows how to make use of bigru and crf to do information extraction.
+
+* [使用PaddleNLP预训练模型ERNIE优化快递单信息抽取](https://aistudio.baidu.com/aistudio/projectdetail/1329361) shows how to exploit the pretrained ERNIE to do information extraction better.
+
+
 ## Community
 
 * SIG for Pretrained Model Contribution
diff --git a/PaddleNLP/examples/text_classification/README.md b/PaddleNLP/examples/text_classification/README.md
index f12face79a5bde8f14c163cf5c769c7783cb42e9..0eb6c93d4ed829e2525a64ccb51a0e5c25649e9e 100644
--- a/PaddleNLP/examples/text_classification/README.md
+++ b/PaddleNLP/examples/text_classification/README.md
@@ -9,3 +9,13 @@
 ## Pretrained Model (PTMs)
 
 [Pretrained Models](./pretrained_models) 展示了如何使用以ERNIE为代表的模型Fine-tune完成文本分类任务。
+
+## 线上体验教程
+
+* [paddlenlp.seq2vec是什么? 瞧瞧它怎么完成情感分析教程](https://aistudio.baidu.com/aistudio/projectdetail/1294333)展示了使用序列模型LSTM完成情感分析任务。
+
+* [使用PaddleNLP语义预训练模型ERNIE优化情感分析教程](https://aistudio.baidu.com/aistudio/projectdetail/1283423)展示了使用ERNIE优化情感分析任务。
+
+* [基于Bi-GRU+CRF的快递单信息抽取](https://aistudio.baidu.com/aistudio/projectdetail/1317771)
+
+* [使用PaddleNLP预训练模型ERNIE优化快递单信息抽取](https://aistudio.baidu.com/aistudio/projectdetail/1329361)
diff --git a/PaddleNLP/examples/text_classification/pretrained_models/README.md b/PaddleNLP/examples/text_classification/pretrained_models/README.md
index 5e060b177d99116afff54afe6926d5a231108b86..658112cbc927cb5aa2ddddd12a201c3915304ad1 100644
--- a/PaddleNLP/examples/text_classification/pretrained_models/README.md
+++ b/PaddleNLP/examples/text_classification/pretrained_models/README.md
@@ -125,3 +125,13 @@ Data: 这个宾馆比较陈旧了，特价的房间也很一般。总体来说
 Data: 怀着十分激动的心情放映，可是看着看着发现，在放映完毕后，出现一集米老鼠的动画片      Label: negative
 Data: 作为老的四星酒店，房间依然很整洁，相当不错。机场接机服务很好，可以在车上办理入住手续，节省时间。      Label: positive
 ```
+
+## 线上体验教程
+
+* [paddlenlp.seq2vec是什么? 瞧瞧它怎么完成情感分析教程](https://aistudio.baidu.com/aistudio/projectdetail/1294333)展示了使用序列模型LSTM完成情感分析任务。
+
+* [使用PaddleNLP语义预训练模型ERNIE优化情感分析教程](https://aistudio.baidu.com/aistudio/projectdetail/1283423)展示了使用ERNIE优化情感分析任务。
+
+* [基于Bi-GRU+CRF的快递单信息抽取](https://aistudio.baidu.com/aistudio/projectdetail/1317771)
+
+* [使用PaddleNLP预训练模型ERNIE优化快递单信息抽取](https://aistudio.baidu.com/aistudio/projectdetail/1329361)
diff --git a/PaddleNLP/examples/text_classification/rnn/README.md b/PaddleNLP/examples/text_classification/rnn/README.md
index 9dfcd59c7fbe187b222ab3bb2713a282576eaae0..d41980d6d804219c5b2a5f4c2a89b25afbd64549 100644
--- a/PaddleNLP/examples/text_classification/rnn/README.md
+++ b/PaddleNLP/examples/text_classification/rnn/README.md
@@ -161,3 +161,13 @@ Data: 这个宾馆比较陈旧了，特价的房间也很一般。总体来说
 Data: 怀着十分激动的心情放映，可是看着看着发现，在放映完毕后，出现一集米老鼠的动画片      Lable: negative
 Data: 作为老的四星酒店，房间依然很整洁，相当不错。机场接机服务很好，可以在车上办理入住手续，节省时间。      Lable: positive
 ```
+
+## 线上体验教程
+
+* [paddlenlp.seq2vec是什么? 瞧瞧它怎么完成情感分析教程](https://aistudio.baidu.com/aistudio/projectdetail/1294333)展示了使用序列模型LSTM完成情感分析任务。
+
+* [使用PaddleNLP语义预训练模型ERNIE优化情感分析教程](https://aistudio.baidu.com/aistudio/projectdetail/1283423)展示了使用ERNIE优化情感分析任务。
+
+* [基于Bi-GRU+CRF的快递单信息抽取](https://aistudio.baidu.com/aistudio/projectdetail/1317771)
+
+* [使用PaddleNLP预训练模型ERNIE优化快递单信息抽取](https://aistudio.baidu.com/aistudio/projectdetail/1329361)
diff --git a/PaddleNLP/examples/text_matching/sentence_transformers/predict.py b/PaddleNLP/examples/text_matching/sentence_transformers/predict.py
index dfd50b7623b5dc7e58bf0fc2fd2deb9b9fc8697b..b72ab2d13060ec5ad3d629e6cb7641d41d148e5f 100644
--- a/PaddleNLP/examples/text_matching/sentence_transformers/predict.py
+++ b/PaddleNLP/examples/text_matching/sentence_transformers/predict.py
@@ -91,7 +91,6 @@ def convert_example(example,
         title_segment_ids(obj: `list[int]`): List of title sequence pair mask.
         label(obj:`numpy.array`, data type of int64, optional): The input label if not is_test.
     """
-    print(example)
     query, title = example[0], example[1]
 
     query_encoded_inputs = tokenizer.encode(
@@ -193,7 +192,7 @@ if __name__ == "__main__":
     args.model_type = args.model_type.lower()
     model_class, tokenizer_class = MODEL_CLASSES[args.model_type]
 
-    if args.model_name == 'ernie_tiny':
+    if args.model_name == 'ernie-tiny':
         # ErnieTinyTokenizer is special for ernie_tiny pretained model.
         tokenizer = ppnlp.transformers.ErnieTinyTokenizer.from_pretrained(
             args.model_name)
diff --git a/PaddleNLP/paddlenlp/__init__.py b/PaddleNLP/paddlenlp/__init__.py
index e94c4e3b961b6090e0eaf944b782b5fe6d53a5a3..98b2546fa63bb05fff519bb81a8bfb4a87b60b09 100644
--- a/PaddleNLP/paddlenlp/__init__.py
+++ b/PaddleNLP/paddlenlp/__init__.py
@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = '2.0.0a8'
+__version__ = '2.0.0a9'
 
 from . import data
 from . import datasets