vit-gpt2-coco-en

ydshieh/vit-gpt2-coco-en

Image to Text239M parameterstransformers
Tracked by OpenModelStats since September 8, 2026View on Hugging Face ↗
Downloads 30D
14.7K
Total downloads
532.2K
Gained 7D
+2,446(increase)
0.5%(up) vs baseline
Gained 30D
—
Likes
39
+0 in 7D
Rank · tracked models
#6,584
24(up 24 places)this week
Parameters
239M
Last source update
Dec 2, 2025
Momentum
55.2
  • vit-gpt2-coco-en gained 2,446 downloads during the last seven tracked days.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

vit-gpt2-coco-en is a image to text model published by ydshieh. OpenModelStats has tracked the model since Sep 8, 2026, most recently observing it 12h ago.

Published
Mar 2, 2022
Last updated
Dec 2, 2025
Library
transformers
License
—
Task
Image to Text
Parameters
239,195,904
Spaces
—
Derivative models
—
Velocity 7D/day
349
transformerspytorchtfjaxtensorboardsafetensorsvision-encoder-decoderimage-text-to-textimage-to-textendpoints_compatibleregion:us

Similar models

Models similar to vit-gpt2-coco-en
ModelDL 30D
nougat-smallfacebook3,604
image-caption-generatorbipin100
ko-trocrddobokki1,596
Falcon-OCRtiiuae5,529
pix2struct-basegoogle22.3K
pix2struct-textcaps-basegoogle3,149
ydshieh/vit-gpt2-coco-en — Downloads, Growth & Stats | OpenModelStats