Update README.md

README.md

@@ -30,7 +30,7 @@ output=model(torch.tensor([tokenizer.encode(texta,textb)]))
 print(torch.nn.functional.softmax(output.logits,dim=-1))
 
 ```
-## Scores on downstream chinese tasks 
+## Scores on downstream chinese tasks（The dev datasets of BUSTM and AFQMC may exist in the train set） 
 |    Model   | BQ    |  BUSTM  | AFQMC    |
 | :--------:    | :-----:  | :----:  | :-----:   | 
 | Erlangshen-Roberta-110M-Similarity | 85.41     |   95.18    | 81.72     |