ms-eff-gcvit-deepfake-b5-celeb-df-v2
KoreaPeter/ms-eff-gcvit-deepfake-b5-celeb-df-v2
Tracked by OpenModelStats since September 3, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 8,970
- Total downloadsCumulative all-time download counter reported by the source platform.
- 34.7K
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +1,012(increase)
- 3.6%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 2
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #20 among tracked Video Classification models.
- #8,013
- 289(down 289 places)this week
- Parameters
- 52.7M
- Last source update
- Jul 4, 2026
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 59.1
- ms-eff-gcvit-deepfake-b5-celeb-df-v2 gained 1,012 downloads during the last seven tracked days.
- It moved from #19 to #20 among tracked Video Classification models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
ms-eff-gcvit-deepfake-b5-celeb-df-v2 is a video classification model published by KoreaPeter. OpenModelStats has tracked the model since Sep 3, 2026, most recently observing it Oct 3, 2026.
- Published
- Jun 23, 2026
- Last updated
- Jul 4, 2026
- Library
- transformers
- License
- mit
- Task
- Video Classification
- Parameters
- 52,743,453
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 145
transformerssafetensorsms_eff_gcvitimage-classificationPyTorchvisionDeepFake-DetectionDeepGuardtf-efficientnetglobal-context-vision-transformervideo-classificationcustom_code
Publisher
KoreaPeterView publisher statistics →Derived from timm/tf_efficientnet_b5.ns_jft_in1k (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| ms-eff-gcvit-deepfake-b5-ff-plus-plusKoreaPeter | 9,128 |
| ms-eff-gcvit-deepfake-b5-kodfKoreaPeter | 8,851 |
| VideoMAEv2-BaseOpenGVLab | 12K |
| videomae-crime-detector-maxdata-v1Nikeytas | 422 |
| videomae-base-finetuned-ucf101-subsettihon-nth | 554 |
| finetuned-ucf101-subsettihon-nth | 474 |