# Multilingual Sentence Similarity

GTE Multilingual Base is a multilingual sentence embedding model supporting over 50 languages, suitable for tasks like sentence similarity calculation.

This is a multilingual model supporting embeddings for Hindi (Devanagari), English, and Romanized Hindi text, with special support for Romanized Hindi and cross-lingual alignment.

This is a sentence embedding model based on sentence-transformers, capable of converting Italian and English sentences into 768-dimensional vector representations, suitable for tasks such as sentence similarity calculation and semantic search.

This model is trained using the Cross-Encoder class from SentenceTransformers to predict the semantic similarity score between two sentences.

This is an IndicSBERT model trained on STS datasets of ten major Indian languages, suitable for English and multiple Indian languages with cross-lingual capabilities.

This is a model trained based on the MuRIL model (google/muril-base-cased), optimized for NLI datasets of ten major Indian languages. This single model supports multiple Indian languages and has cross-language capabilities.

This is a sentence similarity model based on sentence-transformers, specifically optimized for sentences related to immigration requirements and claims.

SGPT-125M is a sentence transformer model based on weighted mean and fine-tuned with Natural Language Inference (NLI), designed for sentence similarity calculation and feature extraction.