# Cross-language retrieval

Multilingual E5 large pooled model supporting sentence similarity calculation and feature extraction tasks in multiple languages.

GIST-Embedding-v0 is a sentence embedding model based on sentence-transformers, mainly used for sentence similarity calculation and feature extraction tasks.

A visual retrieval model based on Qwen2-VL-2B-Instruct and ColBERT strategy, capable of generating multi-vector text and image representations

A 7B-parameter sentence embedding model based on the Qwen2 architecture, specializing in sentence similarity tasks with outstanding performance on the MTEB benchmark.

A vectorization tool developed by Sinequa that generates embedding vectors from input paragraphs or queries for sentence similarity calculation and retrieval tasks.

This is a streamlined version of BAAI/bge-reranker-v2-m3, retaining only the English and Russian vocabulary, making the model 1.5 times smaller while still generating identical embedding vectors.

mGTE series multilingual text encoder, supporting 75 languages, with a maximum context length of 8192, based on BERT+RoPE+GLU architecture, excelling in GLUE and XTREME-R benchmarks

A dual encoder based on the Bloomz-560m-dpo-chat model, designed to map articles and queries into the same vector space, supporting cross-language retrieval in French and English.

This is an Indonesian text embedding model based on sentence-transformers, capable of mapping sentences and paragraphs into a 384-dimensional dense vector space, suitable for tasks such as clustering and semantic search.

This is a multilingual sentence embedding model based on sentence-transformers, capable of mapping text to a 1024-dimensional vector space, suitable for semantic search and clustering tasks.

LEALLA is a collection of lightweight language-agnostic sentence embedding models supporting 109 languages, distilled from LaBSE. Suitable for obtaining multilingual sentence embeddings and bilingual text retrieval.

A Spanish-English bilingual model based on sentence-transformers that maps text to a 768-dimensional vector space, suitable for semantic search and clustering tasks

A sentence embedding model supporting English and Italian, used for generating vector representations of sentences.

An English-German cross-lingual cross-encoder model trained on the MS Marco passage ranking task, suitable for passage re-ranking in information retrieval scenarios.

This is a multilingual sentence embedding model based on sentence-transformers, capable of mapping sentences and paragraphs into a 768-dimensional vector space, suitable for tasks such as clustering and semantic search.