pix2struct-docvqa-base

google/pix2struct-docvqa-base

Visual Question Answering282M parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 29, 2026View on Hugging Face ↗
Downloads 30D
1,678
Total downloads
700.7K
Gained 7D
+204(increase)
0.0%(up) vs baseline
Gained 30D
—
Likes
44
+1 in 7D
Rank · tracked models
#25,522
1157(up 1157 places)this week
Parameters
282M
Last source update
Dec 24, 2023
Momentum
54.2
  • pix2struct-docvqa-base gained 204 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

pix2struct-docvqa-base is a visual question answering model published by google. OpenModelStats has tracked the model since Sep 29, 2026, most recently observing it Oct 6, 2026.

Published
Mar 21, 2023
Last updated
Dec 24, 2023
Library
transformers
License
apache-2.0
Task
Visual Question Answering
Parameters
282,285,696
Spaces
—
Derivative models
—
Velocity 7D/day
29
transformerspytorchsafetensorspix2structimage-text-to-textvisual-question-answeringenfrrodemultilingualarxiv:2210.03347

Similar models

Models similar to pix2struct-docvqa-base
ModelDL 30D
deplotgoogle18.4K
pix2struct-ai2d-basegoogle1,016
TinyDoc-VLM-256Meulogik437
blip-vqa-baseSalesforce552.8K
laya-visionthaitea0
git-base-vqav2microsoft1,244
google/pix2struct-docvqa-base — Downloads, Growth & Stats | OpenModelStats