Improve model card: Add paper, code, and project page links
Browse filesThis PR enhances the model card by adding prominent links to key resources:
* **Paper**: Added an explicit link to the Hugging Face Papers page for "[PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model](https://huggingface.co/papers/2510.14528)".
* **Code**: Included a direct link to the official GitHub repository, "[PaddlePaddle/PaddleOCR GitHub](https://github.com/PaddlePaddle/PaddleOCR)", for easier access to the code.
* **Project Page**: Added a link to the comprehensive PaddleOCR-VL documentation, "[PaddleOCR-VL Documentation](https://www.paddleocr.ai/latest/en/version3.x/algorithm/PaddleOCR-VL/PaddleOCR-VL.html)", which serves as the project's main documentation page.
These additions improve the discoverability and completeness of information for users interested in the model.
README.md
CHANGED
|
@@ -1,4 +1,10 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
pipeline_tag: image-text-to-text
|
| 4 |
tags:
|
|
@@ -11,12 +17,6 @@ tags:
|
|
| 11 |
- table
|
| 12 |
- formula
|
| 13 |
- chart
|
| 14 |
-
base_model: baidu/ERNIE-4.5-0.3B-Paddle
|
| 15 |
-
language:
|
| 16 |
-
- en
|
| 17 |
-
- zh
|
| 18 |
-
- multilingual
|
| 19 |
-
library_name: PaddleOCR
|
| 20 |
---
|
| 21 |
|
| 22 |
<div align="center">
|
|
@@ -28,11 +28,15 @@ PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vi
|
|
| 28 |
|
| 29 |
</h1>
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
[](https://github.com/PaddlePaddle/PaddleOCR)
|
| 32 |
-
[](https://discord.gg/JPmZXDsEEK)
|
| 37 |
[](https://x.com/PaddlePaddle)
|
| 38 |
[](./LICENSE)
|
|
@@ -52,13 +56,13 @@ PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vi
|
|
| 52 |
|
| 53 |
### **Core Features**
|
| 54 |
|
| 55 |
-
1.
|
| 56 |
|
| 57 |
|
| 58 |
-
2.
|
| 59 |
|
| 60 |
|
| 61 |
-
3.
|
| 62 |
|
| 63 |
|
| 64 |
### **Model Architecture**
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: baidu/ERNIE-4.5-0.3B-Paddle
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- zh
|
| 6 |
+
- multilingual
|
| 7 |
+
library_name: PaddleOCR
|
| 8 |
license: apache-2.0
|
| 9 |
pipeline_tag: image-text-to-text
|
| 10 |
tags:
|
|
|
|
| 17 |
- table
|
| 18 |
- formula
|
| 19 |
- chart
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
---
|
| 21 |
|
| 22 |
<div align="center">
|
|
|
|
| 28 |
|
| 29 |
</h1>
|
| 30 |
|
| 31 |
+
**📖 Paper**: [PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model](https://huggingface.co/papers/2510.14528)
|
| 32 |
+
**💻 Code**: [PaddlePaddle/PaddleOCR GitHub](https://github.com/PaddlePaddle/PaddleOCR)
|
| 33 |
+
**🌐 Project Page**: [PaddleOCR-VL Documentation](https://www.paddleocr.ai/latest/en/version3.x/algorithm/PaddleOCR-VL/PaddleOCR-VL.html)
|
| 34 |
+
|
| 35 |
[](https://github.com/PaddlePaddle/PaddleOCR)
|
| 36 |
+
[](https://huggingface.co/PaddlePaddle/PaddleOCR-VL)
|
| 37 |
+
[](https://modelscope.cn/models/PaddlePaddle/PaddleOCR-VL)
|
| 38 |
+
[](https://huggingface.co/spaces/PaddlePaddle/PaddleOCR-VL_Online_Demo)
|
| 39 |
+
[](https://modelscope.cn/studios/PaddlePaddle/PaddleOCR-VL_Online_Demo/summary)
|
| 40 |
[](https://discord.gg/JPmZXDsEEK)
|
| 41 |
[](https://x.com/PaddlePaddle)
|
| 42 |
[](./LICENSE)
|
|
|
|
| 56 |
|
| 57 |
### **Core Features**
|
| 58 |
|
| 59 |
+
1. **Compact yet Powerful VLM Architecture:** We present a novel vision-language model that is specifically designed for resource-efficient inference, achieving outstanding performance in element recognition. By integrating a NaViT-style dynamic high-resolution visual encoder with the lightweight ERNIE-4.5-0.3B language model, we significantly enhance the model’s recognition capabilities and decoding efficiency. This integration maintains high accuracy while reducing computational demands, making it well-suited for efficient and practical document processing applications.
|
| 60 |
|
| 61 |
|
| 62 |
+
2. **SOTA Performance on Document Parsing:** PaddleOCR-VL achieves state-of-the-art performance in both page-level document parsing and element-level recognition. It significantly outperforms existing pipeline-based solutions and exhibiting strong competitiveness against leading vision-language models (VLMs) in document parsing. Moreover, it excels in recognizing complex document elements, such as text, tables, formulas, and charts, making it suitable for a wide range of challenging content types, including handwritten text and historical documents. This makes it highly versatile and suitable for a wide range of document types and scenarios.
|
| 63 |
|
| 64 |
|
| 65 |
+
3. **Multilingual Support:** PaddleOCR-VL Supports 109 languages, covering major global languages, including but not limited to Chinese, English, Japanese, Latin, and Korean, as well as languages with different scripts and structures, such as Russian (Cyrillic script), Arabic, Hindi (Devanagari script), and Thai. This broad language coverage substantially enhances the applicability of our system to multilingual and globalized document processing scenarios.
|
| 66 |
|
| 67 |
|
| 68 |
### **Model Architecture**
|