# Image-text matching

Vision-language model fine-tuned based on CLIP-ViT-B/32, suitable for image-text matching tasks

MEXMA-SigLIP2 is a high-performance CLIP model combining the MEXMA multilingual text encoder and SigLIP2 image encoder, supporting 80 languages.

This is a small CLIP model for debugging purposes, based on the ViT architecture with randomly initialized weights.

A CLIP model fine-tuned based on BeichenZhang/LongCLIP-L, supporting long-text input (248 tokens) with performance enhanced by Geometric parameterization (GmP) technology

A CLIP model based on ResNet101 architecture, supporting zero-shot image classification tasks.

Zero-shot image classification model based on ResNet50 architecture and CLIP technology