# vi-sign-language-videomae-base by Star Duong: Open Model Source: https://savrn.com/models/vi-sign-language-videomae-base Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve vi-sign-language-videomae-base (86M 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 23, 2026. [vi-sign-language-videomae-base on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/vi-sign-language-videomae-base/gpus) ## Model Card By Star Duong, published under mit, revision 9759fc78b5d6. ### Vietnamese Sign Language Recognition (VSLR) Model 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. ### Model Description - Base Architecture: [MCG-NJU/videomae-base-finetuned-kinetics](https://savrn.com/models/videomae-base-finetuned-kinetics) (Video Masked Autoencoders) - Dataset utilized: [star092304/ViSignLanguage-Video](https://huggingface.co/datasets/star092304/ViSignLanguage-Video) - Task: Multi-class Video Classification (Spatiotemporal Feature Extraction) - Target Language: Vietnamese Sign Language (VNSL) 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. ### Training & Evaluation Visualizations The training routine was monitored closely across key evaluation metrics to prevent overfitting while maximizing classification accuracy on the validation split. #### 1. Training and Validation Metrics The plot below illustrates the progression of accuracy, precision, recall, and F1-score across successive training epochs. #### 2. Loss Curves [Read the full model card (402 words)](https://savrn.com/models/vi-sign-language-videomae-base/card) ## Configuration Architecture VideoMAEForVideoClassification Layers 12 Hidden size 768 Feed-forward size 3,072 Attention heads 12 Model type videomae ## Identity and Version Repository star092304/vi-sign-language-videomae-base Publisher Star Duong Task Video classification Modality Video Library transformers Parameters 86M parameters Languages vi Revision 9759fc78b5d69625317bb658b4104040f9427fa3 First published 2026-05-31 Last updated 2026-05-31 ## Files and Weights 14 files, 1.0 GB in total. The weights are 3 files totalling 1.0 GB in pth, safetensors. Weights3 files · 1.0 GB Configuration2 files · 6.3 KB Documentation1 file · 4.9 KB Other7 files · 282.1 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | classifier_sequential.pth | Weights | 345.3 MB | 139dcb459071 | | model.safetensors | Weights | 345.2 MB | c845a9922dc1 | | videomae_best_model.pth | Weights | 345.3 MB | 050f2154d641 | | config.json | Configuration | 5.9 KB | — | | preprocessor_config.json | Configuration | 415 B | — | | README.md | Documentation | 4.9 KB | — | | inference/inference_for_colab.ipynb | Other | 30.0 KB | — | | label_mapping.pkl | Other | 1.3 KB | d57950c25dcf | | src/pipeline_VideoMAE.ipynb | Other | 82.0 KB | — | | test/cv_submission.csv | Other | 60.4 KB | — | | test/public_test.csv | Other | 34.4 KB | — | | training_plots/loss.png | Other | 32.9 KB | — | | training_plots/metrics.png | Other | 41.1 KB | — | | .gitattributes | Repository | 1.5 KB | — | ## License and Download License mit Access Open weights, no gate Download size 1.0 GB [Download from Star Duong](https://huggingface.co/star092304/vi-sign-language-videomae-base) Released by Star Duong through its official repository on Hugging Face. [Read the license](https://opensource.org/license/mit). ## Built From - Derived from [MCG-NJU/videomae-base-finetuned-kinetics](https://savrn.com/models/videomae-base-finetuned-kinetics) - Trained on (disclosed) star092304/ViSignLanguage-Video ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 1.0 GB | | 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. ## Questions About vi-sign-language-videomae-base ### How much GPU memory does vi-sign-language-videomae-base need? About 0.2 GB at 16-bit and 0.1 GB at 4-bit: the weights (86M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run vi-sign-language-videomae-base 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 vi-sign-language-videomae-base commercially? Yes. vi-sign-language-videomae-base is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included. ## Similar Models 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) Model · Video classification ### [videomae-base-finetuned-kinetics](https://savrn.com/models/videomae-base-finetuned-kinetics) [Multimedia Computing Group-Nanjing University](https://savrn.com/model-publishers/mcg-nju) 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… Open weights cc-by-nc-4.0 87M parameters transformers [View model](https://savrn.com/models/videomae-base-finetuned-kinetics) ## Star Duong [All models and datasets](https://savrn.com/model-publishers/star092304) ## Versions - [9759fc78b5d6](https://savrn.com/models/vi-sign-language-videomae-base/versions/9759fc78b5d6) · current 2026-09-18 ## Explore More - [All video classification models](https://savrn.com/models/tasks/video-classification) - [All models under mit](https://savrn.com/models/licenses/mit) - [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 2026-10-21. - [Hugging Face record](https://huggingface.co/star092304/vi-sign-language-videomae-base) - [How the hub is built](https://savrn.com/model-hub/methodology)