Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
-
PaddlePaddle/PaddleOCR-VL-1.5
Image-Text-to-Text β’ Updated β’ 17.7k β’ 410 -
PaddleOCR-VL-1.5 Online Demo
π»62PaddleOCR-VL-1.5_Online_Demo
-
PaddlePaddle/PP-DocLayoutV3
Image Segmentation β’ Updated β’ 10.4k β’ 44 -
PaddlePaddle/PP-DocLayoutV3_safetensors
Object Detection β’ Updated β’ 39.5k β’ 14