# Lightweight vision model

Vintern-3B-beta is a multilingual foundation model that supports English, Vietnamese, and Chinese, and is mainly used for image-text to text conversion tasks.

AIM-v2 is an efficient image encoder implemented based on the timm library, suitable for various computer vision tasks.

YOLOS is an object detection model based on Vision Transformer (ViT), trained with DETR loss, and performs excellently on the COCO dataset.

A tiny model based on Swin Transformer architecture, specifically fine-tuned for CIFAR-10 image classification tasks

Lightweight image classification model based on DeiT-tiny architecture, achieving 98.56% validation accuracy after fine-tuning on a custom image dataset

This is a multi-category image classification model trained via AutoTrain, demonstrating outstanding performance on the validation set with an accuracy of 90.9%.

This is a multi-class image classification model trained via AutoTrain, specifically designed for weather classification tasks.

Fine-tuned model based on Swin Transformer architecture for AI-generated content detection tasks

A three-class image classification model trained with AutoTrain, achieving 95% accuracy on the validation set

A vision model based on the Swin Transformer Tiny architecture, fine-tuned on an unknown dataset for image classification tasks

Fine-tuned model based on Swin Transformer Tiny architecture for image classification tasks

An image classification model based on the Swin Transformer Tiny architecture, fine-tuned on a custom image dataset for 130 epochs, with an accuracy of 90.23%.

This is a binary classification model trained using AutoTrain, specifically designed to distinguish between images of cats and dogs.

ViT-tiny model converted from timm codebase, suitable for image classification tasks

ViT-Tiny model converted from the timm repository, suitable for image classification tasks, with usage consistent with the ViT-base model

An image classification model based on the Vision Transformer architecture, specifically designed to distinguish between images of Chihuahuas and cookies