git-large-textvqa

microsoft/git-large-textvqa

Visual Question Answering395M parameterstransformersLicense: mit
Tracked by OpenModelStats since October 12, 2026View on Hugging Face ↗
Downloads 30D
138
Total downloads
5,351
Gained 7D
—
Gained 30D
—
Likes
8
Rank · tracked models
—
–this week
Parameters
395M
Last source update
Apr 9, 2024

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-10-12. Charts appear as daily observations accumulate.

Overview

git-large-textvqa is a visual question answering model published by microsoft. OpenModelStats has tracked the model since Oct 12, 2026, most recently observing it 18h ago.

Published
Jan 2, 2023
Last updated
Apr 9, 2024
Library
transformers
License
mit
Task
Visual Question Answering
Parameters
394,857,407
Spaces
—
Derivative models
—
Velocity 7D/day
—
transformerspytorchsafetensorsgitimage-text-to-textvisionvisual-question-answeringenarxiv:2205.14100license:mitregion:us

Similar models

Models similar to git-large-textvqa
ModelDL 30D
git-large-vqav2microsoft699
blip-vqa-baseSalesforce498.3K
TinyDoc-VLM-256Meulogik437
deplotgoogle10.1K
pix2struct-docvqa-basegoogle1,846
pix2struct-ai2d-basegoogle979
microsoft/git-large-textvqa — Downloads, Growth & Stats | OpenModelStats