# Multi-label classification

EmoBench - UA is a model for detecting the sentiment of Ukrainian text, capable of recognizing six basic emotions (joy, anger, fear, disgust, surprise, sadness) and the state of no emotion.

A model fine-tuned on the arxiv-new-datasets dataset based on ModernBERT-base, primarily used for text classification tasks

C/C++ code vulnerability detection model fine-tuned based on ModernBERT-base, with 86% accuracy

A toxicity comment classification model fine-tuned based on roberta-base, used to detect toxic content in comments.

A zero-shot classification model fine-tuned based on the Turkish BERT model, trained on the XNLI Turkish dataset, suitable for Turkish text classification tasks.

A natural language inference model fine-tuned based on ModernBERT-large, specifically designed for zero-shot classification tasks

This is the OpenVINO optimized version of the facebook/bart-large-mnli model for zero-shot text classification tasks.

This model is built based on DistilBERT. After fine-tuning, it can perform multi-label classification on emails and URLs to determine whether they are safe or have potential phishing risks.

A compact zero-shot classification model based on DeBERTa architecture, optimized for long-text natural language inference tasks, converted to ONNX format for web compatibility

Quantized ONNX model based on DeBERTa-v3-base, suitable for zero-shot text classification tasks

An efficient zero-shot classifier trained on synthetic data, suitable for topic classification, sentiment analysis, and reranking tasks in RAG workflows.

GLiClass is an efficient zero-shot classifier inspired by GLiNER, suitable for text classification, sentiment analysis, and reranking tasks in RAG workflows.

An efficient zero-shot classifier trained on synthetic data, suitable for topic classification, sentiment analysis, and reranking tasks in RAG workflows

GLiClass is an efficient zero-shot classifier trained on synthetic data, suitable for text classification, sentiment analysis, and reranking tasks in RAG workflows.

This model is fine-tuned based on Bert-Base-Uncased and is used for the multi-label classification task of predicting protein functions based on protein amino acid sequences.

BERT-based multi-label classification model for financial regulatory domains, optimized for anti-money laundering/counter-terrorism financing regulatory texts

GLiClass is an efficient zero-shot classifier trained on synthetic data, suitable for topic classification, sentiment analysis, and reranking tasks in RAG workflows.

A fine-tuned Russian multi-label emotion classification model based on RuBERT-tiny2, supporting 28 emotion categories recognition

A German zero-shot classification model fine-tuned on DeBERTa-v3-base, suitable for multi-label classification tasks

This is a zero-shot classification model based on Spanish, suitable for multilingual natural language understanding tasks.

A BERT-based zero-shot text classification model trained on the UTCD dataset using explicit training methods

A BERT model specifically designed for zero-shot text classification, achieving zero-shot learning capabilities through implicit training within a binary classification framework

This is a BERT-based zero-shot text classification model, specifically designed for zero-shot classification tasks, trained using the aspect-normalized UTCD dataset.

A fine-tuned Russian text multi-label emotion classification model based on rubert-tiny2, capable of recognizing 9 emotional spectra.

A multi-label classification model fine-tuned from google/vit-base-patch16-224-in21k with an accuracy of 73.7%

AASL is an image classification model based on the Creative Commons license, suitable for visual tasks.

Experimental classification model based on fastText word vectors, supporting zero-shot classification tasks

Image classification model based on Vision Transformer architecture, fine-tuned on an unknown dataset

Flair framework's built-in large English NER model for 4 entity types, utilizing document-level XLM-R embeddings and FLERT technique, achieving an F1 score of 94.36 on the CoNLL-03 dataset.

Flair's standard 4-class NER model for Danish, based on Transformer embeddings and LSTM-CRF architecture

A cross-attention natural language inference model specifically trained for zero-shot and few-shot text classification.

German zero-shot classification model based on gbert-large, fine-tuned with 847,862 machine-translated natural language inference sentence pairs

This model is fine-tuned based on Bert Base Italian on the XTREME UD POS Italian dataset for the POS tagging downstream task.

A multi-label emotion classification model for Russian based on fine-tuned rubert-tiny2, capable of recognizing various emotions such as happiness, sadness, surprise, fear, and anger

A text classification model trained on Russian sensitive topic datasets, capable of identifying 18 types of potentially reputation-damaging inappropriate content

A Turkish zero-shot classification model fine-tuned based on dbmdz/distilbert-base-turkish-cased

A Turkish zero-shot classification model based on the ConvBERT architecture, fine-tuned for natural language inference tasks, suitable for multi-class text classification

A Spanish POS tagging model fine-tuned on the CONLL corpus based on RuPERTa-base

A toxicity detection model for Spanish political tweets fine-tuned based on xlm-roberta-base, capable of identifying toxic and highly toxic content in tweets.