# Long text encoding

A Hungarian sentence embedding model fine-tuned based on ModernBERT, used for semantic similarity calculation and text feature extraction

This is a sentence transformer fine-tuned from the modernbert-embed-base model for generating sentence embeddings and calculating semantic similarity.

A Korean-optimized sentence embedding model based on BAAI/bge-m3, supporting 1024-dimensional vector representation, suitable for tasks like semantic similarity calculation

A long-context bi-encoder based on MosaicML's pre-trained BERT with 1024 sequence length, for sentence and paragraph embeddings

A long-context bi-encoder based on MosaicML's pre-trained BERT with 1024 sequence length, designed for generating 768-dimensional dense vector representations of sentences and paragraphs