ViT-L-16-HTxt-Recap-CLIP

UCSC-VLAA/ViT-L-16-HTxt-Recap-CLIP

Zero-Shot Image Classificationopen_clipLicense: cc-by-4.0
Tracked by OpenModelStats since September 10, 2026View on Hugging Face ↗
Downloads 30D
906
Total downloads
367.7K
Gained 7D
+132(increase)
0.0%(up) vs baseline
Gained 30D
—
Likes
18
+0 in 7D
Rank · tracked models
#33,818
26(down 26 places)this week
Parameters
—
Last source update
Jun 24, 2024
Momentum
30.4
  • ViT-L-16-HTxt-Recap-CLIP gained 132 downloads during the last seven tracked days.
  • It moved from #187 to #188 among tracked Zero-Shot Image Classification models this week.

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

ViT-L-16-HTxt-Recap-CLIP is a zero-shot image classification model published by UCSC-VLAA. OpenModelStats has tracked the model since Sep 10, 2026, most recently observing it 5h ago.

Published
Jun 13, 2024
Last updated
Jun 24, 2024
Library
open_clip
License
cc-by-4.0
Task
Zero-Shot Image Classification
Parameters
—
Spaces
0
Derivative models
—
Velocity 7D/day
19
open_clipclipzero-shot-image-classificationdataset:UCSC-VLAA/Recap-DataComp-1Barxiv:2406.08478license:cc-by-4.0region:us

Similar models

UCSC-VLAA/ViT-L-16-HTxt-Recap-CLIP — Downloads, Growth & Stats | OpenModelStats