Update README.md

README.md

@@ -15,7 +15,7 @@ Text classification technology is widely used in various industries such as dial
 However, there are many challenges in industrial-level text classification practices, including diverse tasks, limited data availability and label transfer difficulty. 
 To address these issues, UTC models text classification as a matching task between labels and text, based on the idea of Unified Semantic Matching (USM).
 Thus, it can handle multiple classification tasks with a single model, reducing development and machine costs and achieving good zero/few-shot transfer performance.
-Specifically, UTC won the 1st place on both [ZeroCLUE](https://www.cluebenchmarks.com/zeroclue.html) and [FewCLUE](https://www.cluebenchmarks.com/fewclue.html) benchmarks.
+
 
 
 USM Paper: https://arxiv.org/abs/2301.03282
@@ -23,9 +23,8 @@ USM Paper: https://arxiv.org/abs/2301.03282
 PaddleNLP released UTC model for various text classification tasks which use ERNIE models as the pre-trained language models and were finetuned on a large amount of text classification data.
 
 
-![UTC-diagram]()
+![UTC-diagram](https://user-images.githubusercontent.com/25607475/212268807-66181bcb-d3f9-4086-9d4a-de4d1d0933c2.png)
 
-![UTC-benchmarks]()
 
 ## Available Models
 
@@ -36,7 +35,9 @@ PaddleNLP released UTC model for various text classification tasks which use ERN
 
 ## Performance on Text Dataset
 
-We conducted experiments on the in-house test sets of 
+UTC won the 1st place on both [ZeroCLUE](https://www.cluebenchmarks.com/zeroclue.html) and [FewCLUE](https://www.cluebenchmarks.com/fewclue.html) benchmarks.
+
+![UTC-benchmarks](https://s3.amazonaws.com/moonup/production/uploads/1675418622696-62d7bc8c63583ad7bf1d665a.png)