PTA-1

AskUI/PTA-1

Image Text to Text271M parameterstransformersLicense: mit
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
595
Total downloads
59.3K
Gained 7D
+147(increase)
0.3%(up) vs baseline
Gained 30D
—
Likes
101
+0 in 7D
Rank · tracked models
#38,242
318(down 318 places)this week
Parameters
271M
Last source update
Nov 28, 2024
Momentum
33.3
  • PTA-1 gained 147 downloads during the last seven tracked days.
  • It moved from #3607 to #3638 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

PTA-1 is a image text to text model published by AskUI. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Sep 30, 2026.

Published
Nov 13, 2024
Last updated
Nov 28, 2024
Library
transformers
License
mit
Task
Image Text to Text
Parameters
270,957,657
Spaces
—
Derivative models
—
Velocity 7D/day
21
transformerssafetensorsflorence2image-text-to-textcomputer usecustom_codeenbase_model:microsoft/Florence-2-basebase_model:finetune:microsoft/Florence-2-baselicense:mitendpoints_compatibleregion:us

Publisher

AskUIView publisher statistics →

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

Similar models

Models similar to PTA-1
ModelDL 30D
Florence-2-VQAJP2aipib199.5K
Florence-2-base-PromptGenMiaoshouAI2,449
cv-vlmshixuanleong1,986
Florence-2-SD3-Captionergokaygokay1,147
Florence-2-Fluxgokaygokay845
visualheist-baseshixuanleong606