cv-vlm

shixuanleong/cv-vlm

Image Text to Text271M parametersLicense: mit
Tracked by OpenModelStats since September 1, 2026View on Hugging Face ↗
Downloads 30D
1,986
Total downloads
10.8K
Gained 7D
+74(increase)
0.8%(up) vs baseline
Gained 30D
—
Likes
0
+0 in 7D
Rank · tracked models
#21,905
92(down 92 places)this week
Parameters
271M
Last source update
Oct 27, 2025
Momentum
31.2
  • cv-vlm gained 74 downloads during the last seven tracked days.
  • It moved from #2046 to #2062 among tracked Image Text to Text models this week.

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

cv-vlm is a image text to text model published by shixuanleong. OpenModelStats has tracked the model since Sep 1, 2026, most recently observing it Sep 28, 2026.

Published
Oct 27, 2025
Last updated
Oct 27, 2025
Library
—
License
mit
Task
Image Text to Text
Parameters
270,957,657
Spaces
—
Derivative models
—
Velocity 7D/day
11
pytorchsafetensorsflorence2visionocrsegmentationimage-text-to-textcustom_codelicense:mitregion:us

Similar models

Models similar to cv-vlm
ModelDL 30D
Florence-2-VQAJP2aipib183.5K
Florence-2-base-PromptGenMiaoshouAI2,362
Florence-2-SD3-Captionergokaygokay1,175
Florence-2-Fluxgokaygokay856
visualheist-baseshixuanleong606
PTA-1AskUI597
shixuanleong/cv-vlm — Downloads, Growth & Stats | OpenModelStats