# BERT architecture

GoBERT is a model specifically designed for general gene function prediction. It can effectively capture the relationships between Gene Ontology (GO) functions by leveraging gene ontology graph information.

A machine-generated text detection model based on the ModernBERT-base architecture, designed to prevent language model collapse

A large Russian morpheme segmentation model based on Transformer architecture, capable of classifying each character of Russian words into one of 25 morpheme categories

A transformers classification model trained based on the BERTForSequenceClassification framework, specifically designed for network and device log mining tasks

CuBERT is a context embedding model based on Python code, specifically designed for source code analysis tasks.

Thai sentiment analysis model fine-tuned from WangchanBERTa, achieving 74.15% accuracy on the evaluation set

State-of-the-art BERT language model suite for Modern Hebrew

This is a base BERT model for Turkish language, case-insensitive, primarily used for fill-mask tasks.

A zero-shot text classification model based on BERT architecture, trained for binary classification on the UTCD dataset using an explicit training strategy

LatinBERT is a Latin language pre-trained model based on BERT architecture

This model is a fine-tuned version of BanglaBERT on the Bengali SQuAD dataset for question answering tasks

Russian QA model trained on sberbank-ai/ruBert-base, suitable for reading comprehension tasks

This model provides POS tagging functionality for ancient Chinese, with training data covering four historical periods of Chinese language development.

BERT model pre-trained on UD_Russian for Russian POS tagging and dependency parsing

This is a model based on sentence-transformers that can map sentences and paragraphs to a 384-dimensional dense vector space, suitable for tasks such as sentence similarity calculation and semantic search.

A sentiment analysis model based on DeepPavlov/rubert-base-cased-conversational architecture, trained on the RuSentiment dataset, capable of identifying neutral, positive, and negative emotions in Russian text.

PERT is a BERT-based pre-trained language model designed for English text processing tasks.

An encoder-decoder model based on the BERT architecture, specifically designed for English-to-German machine translation tasks.

DanBERT is a Danish pre-trained model based on the BERT-Base architecture, trained on over 2 million Danish sentences.

TILDE is a model based on the BERT architecture, mainly used for text retrieval and language modeling tasks.

Basic Sentence BERT model for Japanese, fine-tuned based on BERT model, used for sentence similarity calculation

A sentiment analysis model based on DeepPavlov/rubert-base-cased-conversational architecture, trained on the RuReviews dataset for sentiment classification of Russian product reviews.

SportsBERT is a BERT model specialized in the sports domain, trained on a corpus of sports news, suitable for sports-related natural language processing tasks.

A specialized tool for sentence segmentation in Classical Chinese, developed based on BERT architecture

FlauBERT is a French BERT model trained on a large-scale French corpus, developed by the French National Center for Scientific Research.

Slovak named entity recognition model fine-tuned on FERNET-CC_sk, supporting recognition of three entity types: locations, persons, and organizations

This is a Korean sentence embedding model based on sentence-transformers, capable of mapping sentences and paragraphs into a 768-dimensional dense vector space.

Traditional Chinese BERT model developed by Academia Sinica CKIP Lab, supporting natural language processing tasks

A chemical domain BERT model trained based on TSDAE (Transformer-based Sequential Denoising Auto-Encoder), focusing on sentence similarity tasks

This is a sentence embedding model based on sentence-transformers, which can map text to a 256-dimensional vector space and is suitable for semantic search and clustering tasks.

IndoBERT is the state - of - the - art Indonesian language model based on the BERT model, trained through masked language modeling and next - sentence prediction objectives.

KoBERT is a Korean pre-trained language model based on the BERT architecture, suitable for various Korean natural language processing tasks.

Korean BERT base model trained on a 70GB Korean text dataset, using 42,000 lowercase subword units.

Provides Traditional Chinese transformers models and natural language processing tools

A Persian Q&A model based on BERT architecture, specifically designed for Persian question-answering tasks.

Russian toxicity text classifier based on rubert-base-cased-conversational model

BERT model pre-trained on Thai Wikipedia text for POS tagging and dependency parsing

A Danish BERT model developed by Certainly (formerly BotXO), supporting case-insensitive Danish text processing.

Russian news headline generation model based on RuBERT, specifically optimized for Telegram content

BERT model pre-trained on Chinese Wikipedia texts for POS tagging and dependency parsing.