This model is a fine-tuned version of MCG-NJU/videomae-large on the Deepfake Detection Challenge dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 8 - evalbatchsize: 8 - lrschedulertype: linear - lrschedulerwarmupratio: 0.1 - trainingsteps: 4470 - mixedprecisiontraining: Native AMP - Transformers 4.44.2 - Pytorch 2.5.0+cu121 - Datasets 3.1.0 - Tokenizers 0.19.1
VideoMAEv2-Large model pre-trained for 800 epochs in a self-supervised way on UnlabeldHybrid-1M dataset. It was introduced in the paper [[CVPR23]VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://arxiv.org/abs/2203.12602) by Wang et al.
Parameters304M
Context—
Weights1.2 GB
Licensecc-by-nc-4.0
AccessOpen weights
Monthly Downloads3.4k
Runs On
What it takes to serve VideoMAEv2-Large (304M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.6 GB | 0.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.3 GB | 0.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.2 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
Model Card
VideoMAEv2-Large model pre-trained for 800 epochs in a self-supervised way on UnlabeldHybrid-1M dataset. It was introduced in the paper [[CVPR23]VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://arxiv.org/abs/2203.12602) by Wang et al. and first released in GitHub. You can use the raw model for video feature extraction. Here is how to use this model to extract a video feature
Excerpt from the card by OpenGVLab, licensed cc-by-nc-4.0.
Configuration
- Architecture
- VideoMAEv2_Base
- Model type
- VideoMAEv2_Base
Identity and Version
- Repository
- OpenGVLab/VideoMAEv2-Large
- Publisher
- OpenGVLab
- Task
- Video classification
- Modality
- Video
- Library
- Not stated by the source
- Parameters
- 304M parameters
- Languages
- Not stated by the source
- Revision
- 9981a9c8f77118c421e5228e1b219468a4b0238d
- First published
- 2025-01-14
- Last updated
- 2025-01-14
Files and Weights
7 files, 1.2 GB in total. The weights are 1 file totalling 1.2 GB in safetensors.
Weights1 file · 1.2 GB
Configuration4 files · 18.9 KB
Documentation1 file · 2.1 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.2 GB | c27064402bfe |
| config.json | Configuration | 920 B | — |
| modeling_config.py | Configuration | 517 B | — |
| modeling_videomaev2.py | Configuration | 17.1 KB | — |
| preprocessor_config.json | Configuration | 304 B | — |
| README.md | Documentation | 2.1 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- cc-by-nc-4.0
- Access
- Open weights, no gate
- Download size
- 1.2 GB
Download from OpenGVLab
Released by OpenGVLab through its official repository on Hugging Face. Read the license.
Built From
- Described by arXiv:2203.12602
- Described by arXiv:2303.16727
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.2 GB |
| 16-bit | 0.6 GB |
| 8-bit | 0.3 GB |
| 4-bit | 0.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About VideoMAEv2-Large
How much GPU memory does VideoMAEv2-Large need?
About 0.7 GB at 16-bit and 0.2 GB at 4-bit: the weights (304M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run VideoMAEv2-Large on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use VideoMAEv2-Large commercially?
Not without separate permission. VideoMAEv2-Large is released under Creative Commons Attribution-NonCommercial 4.0. CC BY-NC 4.0 permits sharing and adapting with credit for non-commercial purposes only. Commercial use needs separate permission from the rights holder.
Similar Models
VideoMAE model(large) variant that has been finetuned for multi-label video classification (a video can belong to multiple classes simultaneously) for camera motion classification on internal dataset. The model predicts 18 different camera motion 'arcleft', 'arcright', 'dollyin', 'dollyout', 'panleft', 'panright', 'pedestaldown', 'pedestalup', 'rollleft', 'rollright', 'static', 'tiltdown', 'tiltup', 'truckleft', 'truckright', 'undefined', 'zoomin', 'zoomout' and and 3 shot type classes: 'pov', 'shake', 'track'. Model was trained to associate entire video with camera labels, not frame-level motions(!): [input video] -> label/labels (because multilabel) for all video. So, if this camera…
Model · Video classification
videomae-large-finetuned-kinetics
VideoMAE model pre-trained for 1600 epochs in a self-supervised way and fine-tuned in a supervised way on Kinetics-400. It was introduced in the paper VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training by Tong et al. and first released in this repository. Disclaimer: The team releasing VideoMAE did not write a model card for this model so this model card has been written by the Hugging Face team. VideoMAE is an extension of Masked Autoencoders (MAE) to video. The architecture of the model is very similar to that of a standard Vision Transformer (ViT), with a decoder on top for predicting pixel values for masked patches. Videos are presented to…
A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of VJEPA, resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at scale. The code is released in this repository. To run V-JEPA 2 model, ensure you have installed the latest transformers: V-JEPA 2 is intended to represent any video (and image) to perform video classification, retrieval, or as a video encoder for VLMs. To load a video, sample the number of frames according to the model. For this model, we use 64. To load an image, simply copy the image to the desired number of frames. For more code examples, please refer to the V-JEPA 2…
A HuggingFace-format conversion of Meta AI's V-JEPA 2.1 ViT-L/16 video encoder and predictor, operating at 384x384 resolution. The weights are Meta's, copied without modification. This repository provides the transformers-compatible packaging plus a documented numerical validation against the original implementation. An equivalent community port already exists (Dev-Jahn/vjepa2.1-vitl-fpc64-384). This repository adds an independently reproduced conversion together with the validation results below. Forward outputs match the existing port to all reported digits. The only structural change is that the fused QKV projection of each attention block is split into separate query / key / value…
VideoMAE model pre-trained on Kinetics-400 for 1600 epochs in a self-supervised way. It was introduced in the paper VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training by Tong et al. and first released in this repository. Disclaimer: The team releasing VideoMAE did not write a model card for this model so this model card has been written by the Hugging Face team. VideoMAE is an extension of Masked Autoencoders (MAE) to video. The architecture of the model is very similar to that of a standard Vision Transformer (ViT), with a decoder on top for predicting pixel values for masked patches. Videos are presented to the model as a sequence of…