# Text Feature Extraction

This is an intermediate version of a multilingual Mixture of Experts (MoE) text embedding model, obtained through multi-stage contrastive training

A Turkish BERT model pre-trained by Trendyol, suitable for various natural language understanding tasks.

Snowflake Arctic Embed M is a sentence transformer model focused on sentence similarity tasks, capable of efficiently extracting text features and calculating similarity between sentences.

This is a multilingual embedding model based on LaBSE, supporting Russian and Moksha languages, fine-tuned on the myv_ru_2022 dataset.

STAR is a supervised contrastive pretraining transformer model for social media writing style understanding.

This is a BERT-based Japanese SimCSE model, specifically designed for extracting high-quality sentence embeddings from Japanese sentences.

A general-purpose Chinese sentence embedding model for calculating sentence similarity and semantic search tasks.

envibert is a bilingual model based on the RoBERTa architecture, supporting Vietnamese and English processing, optimized for production environments.

BERT is a pre-trained language model based on the Transformer architecture, trained on English corpus through masked language modeling and next sentence prediction tasks.

A Chinese RoBERTa model pretrained on CLUECorpusSmall, with 8 layers and 512 hidden units, suitable for various Chinese NLP tasks.

DistilBERT is a lightweight distilled version of BERT, retaining 97% of BERT's performance while being 40% smaller in size.

A Transformer model pre-trained on English corpus using self-supervised learning similar to ELECTRA, trained by predicting replaced tokens.

gaBERT is a BERT-based monolingual Irish language model trained on 7.9 million Irish sentences, suitable for fine-tuning downstream tasks in Irish.