This collection contains models which convert text or multimodal documents to markdown format for various downstream tasks.
-
rednote-hilab/dots.ocr
Image-Text-to-Text β’ 3B β’ Updated β’ 181k β’ 1.3k -
numind/NuMarkdown-8B-Thinking
Image-to-Text β’ Updated β’ 121k β’ 452 -
zai-org/GLM-4.5V
Image-Text-to-Text β’ 108B β’ Updated β’ 61.8k β’ β’ 718 -
microsoft/kosmos-2.5
Image-Text-to-Text β’ Updated β’ 86.2k β’ 270