Update README.md
Browse files
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.
|