# Large-scale Visual Representation

A vision Transformer model based on SigLIP, focusing on image feature extraction with original attention pooling mechanism.

A vision Transformer model based on the CLIP architecture, specifically designed for image feature extraction, released by the LAION organization.

ConvNeXt Base image encoder based on the CLIP framework, trained on the LAION-2B dataset, supports image feature extraction

CLIP image encoder based on ConvNeXt architecture, trained by LAION, suitable for multimodal vision-language tasks

CLIP model based on the ResNet50x64 architecture from the OpenCLIP library, supporting zero-shot image classification tasks.