try to fix pic in readme

README.md

@@ -29,6 +29,7 @@ This T5-Large model, is the first pretrained generative question answering model
 ## Performance
   
  CMRC 2018 dev (Original span prediction task, we cast it as a generative QA task)
+
  CMRC 2018的测试集上的效果（原始任务是一个起始和结束预测问题，这里作为一个生成回答的问题）
   
    | model | F1 | EM | Contain Answer Rate| RougeL | BLEU-4 |
@@ -44,10 +45,12 @@ This T5-Large model, is the first pretrained generative question answering model
 
 ## Cases
 
-![avatar][cases_t5_cmrc.png]
+![avatar][https://huggingface.co/IDEA-CCNL/Randeng-T5-784M-QA-Chinese/tree/main/cases_t5_cmrc.png]
 
 *pred* in picture are generated results,*target* indicates groud truth.
 
+If the picture fails to display, you can find the picture in Files and versions. 
+
 ## Usage
 ```python
 import numpy as np
@@ -77,6 +80,7 @@ tokenizer.batch_decode(pred_ids, skip_special_tokens=True, clean_up_tokenization
 # Citation
 
 You can also cite our [website](https://github.com/IDEA-CCNL/Fengshenbang-LM/):
+
 欢迎引用我们的[网站](https://github.com/IDEA-CCNL/Fengshenbang-LM/):
 ```text
 @misc{Fengshenbang-LM,