PS3 Lang 4K SigLIP2

--- license: cc-by-nc-sa-4.0 language: - en base_model: - google/siglip2-so400m-patch14-384 pipeline_tag: image-feature-extraction --- ## Description: <br> PS3_Lang-4K-SigLIP2 is a vision encoder that extracts visual features from images of up to 4K resolution. This model is for research and development only. ### License/Terms of Use: <br> Governing Terms: [CC-BY-NC-SA-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en). Additional Information: [Apache License 2.0](https://choosealicense.com/licenses/apache-2.0/) for [Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct). ### Deployment Geography: Global ### Use Case: <br> The model is used for extracting visual features from high-resolution images. ### Release Date: <br> Huggingface [07/26/2025] via [https://huggingface.co/nvidia/PS3_Lang-4K-SigLIP2] <br> ## Reference(s): The model is from the paper [Scaling Vision Pre-Training to 4K Resolution](https://arxiv.org/abs/2503.19903). Useful links: [](https://nvlabs.github.io/PS3/) [](https://arxiv.org/abs/2503.19903) [](https://huggingface.co/spaces/bfshi/VILA-HD-demo) [](https://huggingface.co/collections/nvidia/ps3-scaling-vision-pre-training-to-4k-resolution-682d0535b61c07afd45242e9) [](https://huggingface.co/collections/nvidia/ps3-scaling-vision-pre-training-to-4k-resolution-682d0535b61c07afd45242e9) [](https://github.com/NVlabs/PS3) ## Model Architecture: **Architecture Type:** Neural Network **Network Architecture:** Vision Transformer designed for high-resolution images This model was developed based on [SigLIP2](https://huggingface.co/google/siglip2-so400m-patch14-384). Please see training designs in the paper...

Source context: 79 downloads · 1 likes · Pipeline image-feature-extraction · Repo nvidia/PS3_Lang-4K-SigLIP2