naver-clova-ix/donut-base
Image-to-Text
•
Updated
•
179k
•
240
Document Models (Pretrained)
Various pretrained models for analyzing documents. These need to be fine-tuned for a task
-
-
google/pix2struct-base
Image-to-Text • 0.3B • Updated • 3.79k • 76 -
google/pix2struct-large
Image-to-Text • 1B • Updated • 854 • 34 -
microsoft/layoutlmv3-base
0.1B • Updated • 526k • 465 -
microsoft/layoutlmv2-base-uncased
Updated • 430k • 66 -
microsoft/layoutxlm-base
Updated • 5.96k • 72 -
microsoft/layoutlmv3-large
Updated • 58.7k • 124 -
nielsr/nougat
Image-to-Text • Updated • 22 • 4 -
microsoft/table-transformer-detection
Object Detection • 28.8M • Updated • 1.81M • 385 -
microsoft/dit-base
Updated • 40.6k • 30 -
microsoft/dit-large
Updated • 175 • 18 -
nbroad/donut-base-ascii
Image-to-Text • Updated • 21 • 7 -
facebook/nougat-base
Image-to-Text • 0.3B • Updated • 5.85k • 180 -
facebook/nougat-small
Image-to-Text • 0.2B • Updated • 3.24k • 30 -
Kosmos-2.5: A Multimodal Literate Model
Paper • 2309.11419 • Published • 55 -
adept/fuyu-8b
Any-to-Any • 9B • Updated • 45.9k • 1.02k -
Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning
Paper • 2312.10160 • Published • 2 -
khhuang/chartve
Image-to-Text • Updated • 65 • 3 -
khhuang/chart-to-table
Image-to-Text • Updated • 121 • 18 -
microsoft/udop-large
Image-Text-to-Text • 0.7B • Updated • 7.36k • 120