# High-Precision Classification

A vision-language encoder model fine-tuned based on SigLIP2 for detecting whether images are fake or real

A multilingual sentiment analysis model based on XLM-RoBERTa, supporting AutoTrain for text classification tasks.

A Vision Transformer-based binary classification model specifically designed for detecting deepfake images, with an accuracy rate of 99.2%

An image classification model fine-tuned based on SigLIP2, used to detect whether an image is real or AI-generated

This model is fine-tuned on 120,000 images (60,000 AI-generated and 60,000 human images) specifically designed to detect high-quality AI-generated images.

A fashion image classification model fine-tuned based on the SigLIP2 architecture, specifically designed for the Fashion-MNIST dataset

A lightweight classifier for determining whether indoor real estate images belong to a bathroom, bedroom, dining room, kitchen, or living room

Llama 3.2 11B Vision Instruct is a multimodal model combining vision and language, supporting image-to-text tasks.

Lightweight BERT model fine-tuned specifically for URL classification tasks, capable of categorizing URLs as benign, phishing, malware, or defacement

An AI-generated text detection model developed by Desklib, designed to distinguish between human-written and AI-generated English texts, achieving leading performance in the RAID benchmark.

Multilingual E5 large instruction model supporting text embedding and classification tasks in multiple languages

A fine-tuned model based on Vision Transformer (ViT) architecture for classifying chest X-rays, trained on the CheXpert dataset.

A video analysis model fine-tuned based on MCG-NJU/videomae-base, specializing in anomaly behavior detection tasks

BERT-based phishing email/webpage classification model achieving 87.3% accuracy on validation set

Multilingual E5 large instruction model, supporting multiple languages and tasks including classification, retrieval, clustering, etc.

Multilingual E5 large instruction model supporting text embedding and classification tasks in multiple languages

A RoBERTa Large fine-tuned model for detecting AI-generated content

Multilingual E5 Large is a multilingual sentence transformer model focused on sentence similarity and feature extraction tasks, supporting multiple languages.

This is a transformers-based model focused on the field of electronic components and scientific components.

This is a model designed to extract relations from privacy policy texts, supporting the identification of data collection, storage, and transmission-related information.

This is a sentiment analysis model fine-tuned based on FinancialBERT, specifically designed to analyze the sentiment tendencies (bearish, bullish, neutral) of financial news tweets.

This model is fine-tuned based on EEVE-Korean-Instruct-10.8B-v1.0, designed to evaluate whether the retrieved context in RAG (Retrieval-Augmented Generation) is correct for a given question, answering with 'yes' or 'no'.

A prompt injection detection model fine-tuned on DeBERTa-v3-base, designed to identify malicious prompts that may manipulate language models

A stress classification model fine-tuned based on roberta-base, used to identify stress-related content in employee reviews.

A voice command recognition model based on the HuBERT architecture, optimized for keyword spotting tasks

A DeBERTa-v3 fine-tuned model for prompt injection detection, designed to identify malicious prompt inputs

A lightweight intent classification model based on DistilBERT, efficiently recognizing user text intents

An image classification model based on Vision Transformer architecture, specifically designed to detect AI-generated fake images

An NSFW image classification model based on the ViT architecture, pre-trained on ImageNet-21k via supervised learning and fine-tuned on 80,000 images to distinguish between normal and NSFW content.

This is an image classification model built with PyTorch and HuggingPics, specifically designed for detecting defects in solar panels.

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on a blurry image dataset, designed to distinguish between blurry and clear images.

ToxicityModel is a fine-tuned model based on RoBERTa, designed to assess the toxicity level of English sentences.

An audio digit recognition model fine-tuned based on data2vec-audio-base-960h, excelling on digit-mask augmented datasets

An image classification model based on YOLOv8, specifically designed to identify 12 common weeds and crops.

EVA02 base version visual representation model, pre-trained on ImageNet-22k through masked image modeling, suitable for image classification and feature extraction tasks.

A model based on the swin-tiny-patch4-window7-224 architecture, designed to distinguish between real images and AI-generated images.

This is a vision model based on the Beit architecture, specifically fine-tuned for product image classification tasks.

This is an astronomical photography object classification model trained via AutoTrain, capable of accurately identifying different celestial objects in astrophotography.

An image classification model fine-tuned on the image folder dataset based on microsoft/beit-base-patch16-224-pt22k-ft22k

This is a multi-class flower image classification model trained using AutoTrain, achieving an outstanding accuracy of 99% on the validation set.