DocDjinn: Controllable Synthetic Document Generation with VLMs and Handwriting Diffusion Paper • 2602.21824 • Published Feb 25
deepseek-community/deepseek-vl-7b-chat Image-Text-to-Text • 7B • Updated Jul 26, 2025 • 2.14k • 1
deepseek-community/deepseek-vl-1.3b-chat Image-Text-to-Text • 2B • Updated Jul 26, 2025 • 2.26k • 2
Leveraging Distillation Techniques for Document Understanding: A Case Study with FLAN-T5 Paper • 2409.11282 • Published Sep 17, 2024
Deepseek-VL Collection DeepSeek-VL: Towards Real-World Vision-Language Understanding • 5 items • Updated Jun 14, 2025