Task
Image To Text
P
PaddlePaddle/PP-DocBee2-3B
Image To Text·PaddlePaddle· 175
The PaddleOCR team has developed PP-DocBee2-3B, a multimodal large model that significantly enhances Chinese document understanding. Building upon the original PP-DocBee, this new iteration introduces an improved data optimization scheme that boosts data quality. PP-DocBee2 achieves superior performance in Chinese document understanding tasks by leveraging a relatively small dataset of 470,000 syn
# pull & run locally
pip install mlforge-sdk && mlforge pull PaddlePaddle/PP-DocBee2-3B
pip install mlforge-sdk && mlforge pull PaddlePaddle/PP-DocBee2-3B
Model details
Provider
PaddlePaddle
Framework
PaddleOCR
Size
7.6 GB
License
apache-2.0
Downloads
175
Updated
2025-08-27
About PaddlePaddle/PP-DocBee2-3B
The PaddleOCR team has developed PP-DocBee2-3B, a multimodal large model that significantly enhances Chinese document understanding. Building upon the original PP-DocBee, this new iteration introduces an improved data optimization scheme that boosts data quality. PP-DocBee2 achieves superior performance in Chinese document understanding tasks by leveraging a relatively small dataset of 470,000 synthetic data points, generated through a proprietary data synthesis strategy. Internally, PP-DocBee2 demonstrates an impressive 11.4% improvement over its predecessor, PP-DocBee, in Chinese business scenario metrics. Furthermore, it outperforms other popular open-source and closed-source models of comparable scale in key accuracy metrics. The key accuracy metrics are as follow: