yuhangzang commited on
Commit
6d287df
·
verified ·
1 Parent(s): 23c8441

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -25,6 +25,10 @@ curation pipeline to ensure the quality of the questions and answers used for th
25
  By employing CapRL training framework, initializing with the Qwen2.5-VL-3B model, and using a carefully
26
  filtered 75K QA dataset as the training set, we obtained a highly capable captioner, CapRL-3B.
27
 
 
 
 
 
28
  ## Key Features
29
  * **Remarkable visual understanding for Chart, Infographics and Document**: CapRL-3B achieves perception accuracy and visual information coverage comparable to Qwen2.5-VL-72B.
30
  * **Well-organized output**: The outputs of CapRL-3B are relatively well-structured, making them clear and easy to understand.
 
25
  By employing CapRL training framework, initializing with the Qwen2.5-VL-3B model, and using a carefully
26
  filtered 75K QA dataset as the training set, we obtained a highly capable captioner, CapRL-3B.
27
 
28
+ <p align="center">
29
+ <img src="https://Cooperx521@github.com/InternLM/CapRL/blob/main/assets/teaser.png" width="80%"/>
30
+ <p>
31
+
32
  ## Key Features
33
  * **Remarkable visual understanding for Chart, Infographics and Document**: CapRL-3B achieves perception accuracy and visual information coverage comparable to Qwen2.5-VL-72B.
34
  * **Well-organized output**: The outputs of CapRL-3B are relatively well-structured, making them clear and easy to understand.