# videomae-base-finetuned-kinetics: Open-Weight Model Source: https://savrn.com/models/videomae-base-finetuned-kinetics Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve videomae-base-finetuned-kinetics (87M 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 | 0.2 GB | 0.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.0 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 25, 2026. [videomae-base-finetuned-kinetics on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/videomae-base-finetuned-kinetics/gpus) ## SAVRN's Notes on videomae-base-finetuned-kinetics VideoMAE classifies short video clips into the 400 action classes of Kinetics, from playing guitar to riding a bike. Nanjing University's group pretrained it with masked autoencoding for 1,600 epochs, then fine-tuned it. It has 87M parameters. The license is CC-BY-NC-4.0, which rules out commercial use. For research and prototypes it is a clean baseline; for a product, look for permissively licensed video models or fine-tune your own. SAVRN Research, 2026-09-18 ## Model Card 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… Excerpt from the card by Multimedia Computing Group-Nanjing University, licensed cc-by-nc-4.0. ## Configuration Architecture VideoMAEForVideoClassification Layers 12 Hidden size 768 Feed-forward size 3,072 Attention heads 12 Stored precision float32 Model type videomae ## Identity and Version Repository MCG-NJU/videomae-base-finetuned-kinetics Publisher Multimedia Computing Group-Nanjing University Task Video classification Modality Video Library transformers Parameters 87M parameters Languages Not stated by the source Revision 488eb9a0565f257b32866000305c8178965eb9f6 First published 2022-07-08 Last updated 2024-03-29 ## Files and Weights 6 files, 692.4 MB in total. The weights are 2 files totalling 692.4 MB in bin, safetensors. Weights2 files · 692.4 MB Configuration2 files · 23.1 KB Documentation1 file · 3.6 KB Repository1 file · 1.2 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 346.2 MB | 065cfde56f97 | | pytorch_model.bin | Weights | 346.2 MB | f8462908e843 | | config.json | Configuration | 22.9 KB | — | | preprocessor_config.json | Configuration | 271 B | — | | README.md | Documentation | 3.6 KB | — | | .gitattributes | Repository | 1.2 KB | — | ## License and Download License cc-by-nc-4.0 Access Open weights, no gate Download size 692.4 MB [Download from Multimedia Computing Group-Nanjing University](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) Released by Multimedia Computing Group-Nanjing University through its official repository on Hugging Face. [Read the license](https://creativecommons.org/licenses/by-nc/4.0/). ## Built From - Described by [arXiv:2111.06377](https://savrn.com/papers/masked-autoencoders-are-scalable-vision-learners) - Described by [arXiv:2203.12602](https://savrn.com/papers/videomae-masked-autoencoders-are-data-efficient-learners-for-self-supervised-video-pre-tra) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 692.4 MB | | 16-bit | 0.2 GB | | 8-bit | 0.1 GB | | 4-bit | 0.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Built on This Model - Derived from[videomae-base-finetuned-kinetics-violence-nonviolence-tuned](https://savrn.com/models/videomae-base-finetuned-kinetics-violence-nonviolence-tuned) - Derived from[vi-sign-language-videomae-base](https://savrn.com/models/vi-sign-language-videomae-base) ## Questions About videomae-base-finetuned-kinetics ### How much GPU memory does videomae-base-finetuned-kinetics need? About 0.2 GB at 16-bit and 0.1 GB at 4-bit: the weights (87M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run videomae-base-finetuned-kinetics 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 videomae-base-finetuned-kinetics commercially? Not without separate permission. videomae-base-finetuned-kinetics 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 Model · Video classification ### [vi-sign-language-videomae-base](https://savrn.com/models/vi-sign-language-videomae-base) [Star Duong](https://savrn.com/model-publishers/star092304) This repository houses a fine-tuned VideoMAE (Base) model optimized for multi-class Vietnamese Sign Language Recognition (VSLR). The model architecture adapts self-supervised video representations to accurately classify short video clips of sign gestures into distinct Vietnamese text labels. The model processes short video sequences by partitioning them into spatiotemporal patches, mapping sequential gestures (such as "Ăn", "Bệnh viện", "Xin lỗi") to their corresponding semantic classes. The training routine was monitored closely across key evaluation metrics to prevent overfitting while maximizing classification accuracy on the validation split. The plot below illustrates the progression… Open weights mit 86M parameters transformers [View model](https://savrn.com/models/vi-sign-language-videomae-base) Model · Video classification ### [videomae-base-finetuned-ucf101-subset](https://savrn.com/models/videomae-base-finetuned-ucf101-subset) [Hon Nguyen](https://savrn.com/model-publishers/tihon-nth) This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown 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 - trainingsteps: 370 - Transformers 5.16.1 - Pytorch 2.14.0+cu126 - Datasets 5.0.1 - Tokenizers 0.23.2 Open weights cc-by-nc-4.0 86M parameters transformers [View model](https://savrn.com/models/videomae-base-finetuned-ucf101-subset) Model · Video classification ### [finetuned-ucf101-subset](https://savrn.com/models/finetuned-ucf101-subset) [Hon Nguyen](https://savrn.com/model-publishers/tihon-nth) This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown 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 - trainingsteps: 370 - Transformers 5.16.1 - Pytorch 2.11.0+cu128 - Datasets 5.0.1 - Tokenizers 0.23.1 Open weights cc-by-nc-4.0 86M parameters transformers [View model](https://savrn.com/models/finetuned-ucf101-subset) Model · Video classification ### [videomae-violence-detector](https://savrn.com/models/videomae-violence-detector) [Oleg Radzhabov](https://savrn.com/model-publishers/happygook) This model is a fine-tuned version of MCG-NJU/videomae-base for binary violence classification (violent / non-violent). It builds on Nikeytas/videomae-crime-detector-production-v1, which was itself fine-tuned from videomae-base on a subset of UCF Crime. Starting from that checkpoint, this model was further fine-tuned on the Bus Violence Dataset to close the domain gap to public-transport surveillance footage. - UCF Crime (jinmang2/ucfcrime) — inherited from the base checkpoint - Bus Violence Dataset (Zenodo) — real moving-bus footage, binary violent / non-violent labels, used for domain-specific fine-tuning Evaluated on a held-out Bus Violence Dataset test split (n = 280). The base… Open weights mit 86M parameters [View model](https://savrn.com/models/videomae-violence-detector) Model · Video classification ### [videomae-base-finetuned-kinetics-violence-nonviolence-tuned](https://savrn.com/models/videomae-base-finetuned-kinetics-violence-nonviolence-tuned) [Limon Alfredo](https://savrn.com/model-publishers/cliffer1) This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 16 - evalbatchsize: 16 - lrschedulertype: linear - lrschedulerwarmupratio: 0.1 - trainingsteps: 348 - Transformers 4.49.0 - Pytorch 2.6.0+cu126 - Datasets 3.3.2 - Tokenizers 0.21.0 Open weights cc-by-nc-4.0 86M parameters transformers [View model](https://savrn.com/models/videomae-base-finetuned-kinetics-violence-nonviolence-tuned) Model · Video classification ### [VideoMAEv2-Base](https://savrn.com/models/videomaev2-base) [OpenGVLab](https://savrn.com/model-publishers/opengvlab) VideoMAEv2-Base 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 Open weights cc-by-nc-4.0 86M parameters [View model](https://savrn.com/models/videomaev2-base) ## Multimedia Computing Group-Nanjing University [All models and datasets](https://savrn.com/model-publishers/mcg-nju) ## Versions - [488eb9a0565f](https://savrn.com/models/videomae-base-finetuned-kinetics/versions/488eb9a0565f) · current 2026-09-18 ## Explore More - [All video classification models](https://savrn.com/models/tasks/video-classification) - [All models under cc-by-nc-4.0](https://savrn.com/models/licenses/cc-by-nc-4-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-20. - [Hugging Face record](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) - [How the hub is built](https://savrn.com/model-hub/methodology)