# Multi-label Classification

A voice quality classification model based on Whisper Large v3, used to analyze features such as pitch, timbre, volume, clarity, and rhythm of speech.

PPACE is an 8-billion-parameter large language model specifically designed for automatic classification of biomedical funding project abstracts, supporting the World Health Organization's research priority classification.

BERT-based multilingual sentiment classification model supporting text sentiment analysis in 6 languages

This model is a fine-tuned version of nlpaueb/legal-bert-base-uncased on the InLegalNER dataset, specifically designed for named entity recognition tasks in Indian legal texts.

A text classification model fine-tuned based on ModernBERT-large, designed to detect and classify various types of bias in text.

A fashion object detection model fine-tuned based on YOLOS-tiny, specifically designed to detect 7 categories of fashion items such as bags, bottoms, dresses, etc. Trained on the ModaNet and Fashionpedia datasets, achieving an mAP of 0.697.

FRIDA is a multi-task evaluation model that supports various natural language processing tasks, including classification, clustering, and re-ranking.

This model is based on the DistilBERT architecture, specifically designed for multi-label classification tasks to determine whether emails and URLs are safe or pose phishing risks.

CRNN audio event detection model pre-trained on AudioSet and fine-tuned on AudioSet-strong

PromptGuard is a text classification model designed to detect and protect against LLM prompt attacks, capable of identifying malicious prompt injections and jailbreak attempts.

This model is based on the BERT architecture, specifically designed to identify the MITRE ATT&CK tactic framework categories for cybersecurity texts, supporting multi-label classification.

This is a French zero-shot classification model based on transformers.js, suitable for multi-class text classification tasks without fine-tuning.

GLiNER is a bidirectional Transformer-based general named entity recognition model, specifically optimized for Italian.

This is a fine-tuned text classification model based on BERT-base-uncased, specifically designed to identify crime types from crime descriptions, covering 34 classification labels.

An image tag classification model based on the SwinV2 architecture for automatically identifying content and features in images

SegFormer model fine-tuned on the ATR dataset, primarily used for clothing segmentation and also applicable to human body segmentation

This model is a fine-tuned version based on Facebook's ConvNeXtV2 architecture, specifically trained for multi-label classification tasks on Pixiv ranking images

A cybersecurity entity recognition model fine-tuned on the CyNER dataset based on CYBERT, used to identify named entities related to cyber threats.

A Russian named entity recognition model fine-tuned on microsoft/mdeberta-v3-base, supporting single-token multi-label output

English text classification model based on Deberta-v3 architecture for identifying offensive content

PopBERT is a German political speech populism detection model developed based on the deepset/gbert-large model, specifically designed for analyzing political speeches in the German Bundestag.

This model is a fine-tuned text classification model based on a French pre-trained model, designed to classify French texts according to the United Nations Sustainable Development Goals (SDGs).

This is a fine-tuned BERT-based language model for classifying NLP-related research papers according to concepts in the NLP taxonomy. It is a multi-label classifier capable of predicting concepts at all levels of the NLP taxonomy.

A Russian multi-label emotion classification model fine-tuned on ruBert-base, trained on the ru_goemotions dataset, supporting 9 emotion categories

A CLIP model fine-tuned on Danbooru2021 dataset, specialized for anime image tag classification

An audio classification model based on the audio spectrum transformer architecture, distilled from the original AST AudioSet model, suitable for audio classification tasks.

A BPMN process information extraction model fine-tuned based on bert-base-cased, used to extract key elements such as executors and tasks from textual process descriptions

A biomedical domain intent recognition model fine-tuned based on bert-base-chinese

A fine-tuned Vision Transformer model based on google/vit-base-patch16-384, suitable for image classification tasks

BERT model fine-tuned based on roberta-large-ner-english for protagonist identification tasks

A Vietnamese sentiment analysis model fine-tuned based on PhoBERT-base, used to classify the sentiment tendency of Vietnamese texts (positive/negative/neutral)

A Turkish sentiment analysis model based on Distilbert, fine-tuned on a Turkish-translated sentiment dataset

A music genre encoder fine-tuned based on BERT-mini, capable of embedding music genres into a 256-dimensional space with an accuracy rate exceeding 98%.

This model is a fine-tuned version of Seznam/small-e-czech on the WikiANN dataset for Czech named entity recognition tasks.

This is an Indonesian language tagging classification model, suitable for tagging classification tasks in natural language processing.

A speech intent classification model fine-tuned on the SUPERB intent classification task, based on the Hubert-Base-LS960 pre-trained model

An Indonesian emotion classifier trained on the Indo-roberta model, fine-tuned on the IndoNLU EmoT dataset for sentiment analysis tasks.

A manuscript image classification model fine-tuned based on Google's ViT model, achieving an F1 score of 0.5996 on the evaluation set

A specialized language representation model for the legal domain fine-tuned on a large-scale legal corpus (4.6 GB)

DistilBERT-based sentiment classification model for Tamil-English mixed text, fine-tuned on the tamilmixsentiment dataset