Florence-2-DocVQA

HuggingFaceM4/Florence-2-DocVQA

Image Text to Text823M parameterstransformers
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
638
Total downloads
50.2K
Gained 7D
+154(increase)
0.3%(up) vs baseline
Gained 30D
—
Likes
65
+0 in 7D
Rank · tracked models
#38,900
369(down 369 places)this week
Parameters
823M
Last source update
Oct 30, 2024
Momentum
34.0
  • Florence-2-DocVQA gained 154 downloads during the last seven tracked days.
  • It moved from #3672 to #3699 among tracked Image Text to Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Florence-2-DocVQA is a image text to text model published by HuggingFaceM4. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 7, 2026.

Published
Jun 21, 2024
Last updated
Oct 30, 2024
Library
transformers
License
—
Task
Image Text to Text
Parameters
822,949,977
Spaces
—
Derivative models
—
Velocity 7D/day
22
transformerssafetensorsflorence2image-text-to-textcustom_codearxiv:1910.09700base_model:microsoft/Florence-2-base-ftbase_model:finetune:microsoft/Florence-2-base-ftendpoints_compatibleregion:us

Publisher

HuggingFaceM4View publisher statistics →

Derived from microsoft/Florence-2-base-ft (reported by the source; parent not yet tracked).

Similar models

Models similar to Florence-2-DocVQA
ModelDL 30D
Florence-2-Flux-Largegokaygokay1,728
TFT-ID-1.0yifeihu104
tibetan-ocrBDRC262.6K
OvisOCR2ATH-MaaS239.4K
Qwen3.5-0.8B-4bitmlx-community6,130
Qwen3.5-0.8B-8bitmlx-community5,268
HuggingFaceM4/Florence-2-DocVQA — Downloads, Growth & Stats | OpenModelStats