# Multilingual Embeddings

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

CrisisTransformers is a series of pre-trained language models and sentence encoders for crisis-related social media texts, based on the RoBERTa architecture, trained on a 15-billion-token crisis event dataset.

XLM-mlm-ende-1024 is an English-German Transformer model pre-trained with the Masked Language Modeling (MLM) objective, using language embeddings to specify the inference language.

An English-Romanian Transformer model pretrained with masked language modeling objective, using language embeddings to specify inference language

XLM-mlm-enfr-1024 is a Transformer model pre-trained on English-French masked language modeling objectives, supporting cross-lingual tasks.