naver-clova-ix/donut-base
Image-to-Text
ā¢
Updated
ā¢
29.9k
ā¢
247
Document Models (Pretrained)
Various pretrained models for analyzing documents. These need to be fine-tuned for a task
-
-
google/pix2struct-base
Image-to-Text ā¢ 0.3B ā¢ Updated ā¢ 4.63k ā¢ 76 -
google/pix2struct-large
Image-to-Text ā¢ 1B ā¢ Updated ā¢ 664 ā¢ 34 -
microsoft/layoutlmv3-base
0.1B ā¢ Updated ā¢ 933k ā¢ 472 -
microsoft/layoutlmv2-base-uncased
Updated ā¢ 515k ā¢ 66 -
microsoft/layoutxlm-base
Updated ā¢ 6.56k ā¢ 73 -
microsoft/layoutlmv3-large
Updated ā¢ 62.9k ā¢ 124 -
nielsr/nougat
Image-to-Text ā¢ Updated ā¢ 4 ā¢ 4 -
microsoft/table-transformer-detection
Object Detection ā¢ 28.8M ā¢ Updated ā¢ 1.48M ā¢ 392 -
microsoft/dit-base
Updated ā¢ 37k ā¢ 30 -
microsoft/dit-large
Updated ā¢ 115 ā¢ 18 -
nbroad/donut-base-ascii
Image-to-Text ā¢ Updated ā¢ 7 -
facebook/nougat-base
Image-to-Text ā¢ 0.3B ā¢ Updated ā¢ 15.7k ā¢ 184 -
facebook/nougat-small
Image-to-Text ā¢ 0.2B ā¢ Updated ā¢ 2.67k ā¢ 30 -
Kosmos-2.5: A Multimodal Literate Model
Paper ā¢ 2309.11419 ā¢ Published ā¢ 55 -
adept/fuyu-8b
Image-to-Text ā¢ 9B ā¢ Updated ā¢ 35.6k ā¢ 1.02k -
Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning
Paper ā¢ 2312.10160 ā¢ Published ā¢ 2 -
khhuang/chartve
Image-to-Text ā¢ Updated ā¢ 57 ā¢ 3 -
khhuang/chart-to-table
Image-to-Text ā¢ Updated ā¢ 82 ā¢ 18 -
microsoft/udop-large
Image-Text-to-Text ā¢ 0.7B ā¢ Updated ā¢ 16.7k ā¢ 121