I tested the DeepSeek-OCR model on the vLLM framework as the usage guide indicated. And, with the prompt <image>\n<|grounding|>Convert the document to markdown., I asked the model to convert any image ...
Green Materials and Processes R&D Group, Korea Institute of Industrial Technology, Ulsan 44413, Republic of Korea Department of Chemical and Biomolecular Engineering, Yonsei University, 50 Yonsei-ro, ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results