gte-multilingual-reranker-base

Alibaba Qwen

Catalogue only Open weights

Sovereignty and hosting

Catalogue only

This model is catalogued for reference. It is not hosted on LLM EU yet, and no first-party endpoint serves it here. Requests to it go to the provider directly, under that provider's own terms.

Summary

gte-multilingual-reranker-base is a cross-encoder reranker for multilingual retrieval, with 305M parameters and support for inputs up to 8192 tokens. It is published under Apache-2.0 and covers 75 languages in its declared language list. In a retrieval pipeline it belongs after a first-stage vector search, not as a standalone embedding model.

Specifications

Provider
Alibaba Qwen (CN)
Context window
8.2k
Parameters
0.31B
Modalities
embedding
License
apache-2.0 · licence
Open weights
yes
Release date
20 Jul 2024
Tasks
rag, multilingual-support, private, cheap

Languages

Strong: en, de, fr, es, it, pt, nl, pl

Adequate: ru, uk, ar, zh, ja, ko, hi, tr, sv, da, fi, cs, ro, el

Languages

Strong

  • en
  • de
  • fr
  • es
  • it
  • pt
  • nl
  • pl

Adequate

  • ru
  • uk
  • ar
  • zh
  • ja
  • ko
  • hi
  • tr
  • sv
  • da
  • fi
  • cs
  • ro
  • el

Not verified: the provider has not documented this claim. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

When to use it

Strengths

  • 8192-token input limit, long for a reranker
  • 75 declared languages including all large EU languages
  • small enough to run next to the embedding model
  • Apache-2.0 licence

Limits

  • a reranker only: it cannot generate text or embeddings for indexing
  • the model card examples truncate inputs at 512 tokens unless configured otherwise
  • no evaluation has been run by LLM EU