# Legal Text Similarity

A legal domain embedding model optimized based on the ModernBERT architecture, supporting multi-dimensional feature extraction and sentence similarity calculation

An optimized sentence transformer model based on nomic-embed-text-v2-moe, specializing in sentence similarity calculation and feature extraction for Russian legal texts

Sentence embedding model based on ModernBERT-base for sentence similarity and feature extraction tasks

A sentence embedding model based on Nomic Embed Text v2 MoE, specializing in sentence similarity and feature extraction tasks

This is a fine-tuned sentence transformer model derived from Alibaba-NLP/gte-multilingual-base, specifically optimized for semantic similarity tasks in legal and administrative texts, with support for multilingual processing.

A model specifically designed for calculating similarity in legal texts, suitable for scenarios like building vector databases.