OpenGVLab/VideoMAEv2-Base download history
OpenGVLab/VideoMAEv2-Base is an 86M-parameter video classification model by OpenGVLab. In the last 30 days it was downloaded 34,763 times (13,499 in the last 7 days), and 278,429 times in total.
It ranks #4,607 on the Hub by monthly downloads and #15 among video classification models.
It has 20 likes.
3 models build on VideoMAEv2-Base: 0 quantized, 3 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 34,800 times in the last 30 days. See the VideoMAEv2-Base galaxy.
Most downloaded derivatives
- ai-forever/kandinsky-video-motion-predictor (finetune), 37 downloads in 30 days
- Conna/AVF-MAE (finetune), 0 downloads in 30 days
- Kiffaz11/Videomae_v2_base-hmdb51-finetuned (finetune), 0 downloads in 30 days
Downloads by month
Downloads in the 30 days up to the end of each month, and the change from the month before.
| Month | Downloads | Change |
|---|---|---|
| Up to 2026-11-18 | 34,763 | +123% |
| October 2026 | 15,580 | +33% |
| September 2026 | 11,673 | -33% |
| August 2026 | 17,416 | -31% |
| July 2026 | 25,174 | +80% |
| June 2026 | 13,992 | -18% |
| May 2026 | 17,125 | +6% |
| April 2026 | 16,188 | +11% |
| March 2026 | 14,616 | +14% |
| February 2026 | 12,870 | +107% |
| January 2026 | 6,209 | -57% |
| December 2025 | 14,414 | +62% |
Its busiest 30 days so far ended on 2026-11-18, with 34,763 downloads.
Open OpenGVLab/VideoMAEv2-Base on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.