LLM EU
Menüü

EuroLLM-22B-Instruct (2512)

EuroLLM (utter-project) · Pakkujad EU

Ei ole majutatud — mock-taustarakendus Avatud kaalud Euroopa pakkuja

Suveräänsus ja majutamine

Ei ole majutatud — mock-taustarakendus

Selles juurutuses ei ole LLM EU-s majutatud: taotlustele vastab sisseehitatud mock-taustarakendus regioonis dev-mock. Ühtegi kaalu ei käitata.

Kokkuvõte

EuroLLM-22B-Instruct (2512) is the largest released EuroLLM model, covering the same European language set as the 9B version. The model card states that long-context data sources were upsampled in training to extend the context window to 32k tokens. It is published under Apache-2.0 and is the reference checkpoint for the project’s post-training recipe.

Tehnilised andmed

Pakkuja
EuroLLM (utter-project) (PT)
Konteksti aken
33k
Parameetrid
22.64B
Modaalsused
text
Litsents
apache-2.0 · licence
Avatud kaalud
yes
Avaldamiskuupäev
05. dets 2025
Ülesanded
translation, multilingual-support, summarization, reasoning

Keeled

Tugev: en, de, es, fr, it, pt, pl, nl, sv, cs, el, ro, fi, da, uk

Piisav: hu, bg, sk, sl, lt, lv, et, hr, ga, mt, ca, tr, ar, zh, ja, ko, ru, hi

Keeled

Tugev

  • en
  • de
  • es
  • fr
  • it
  • pt
  • pl
  • nl
  • sv
  • cs
  • el
  • ro
  • fi
  • da
  • uk

Piisav

  • hu
  • bg
  • sk
  • sl
  • lt
  • lv
  • et
  • hr
  • ga
  • mt
  • ca
  • tr
  • ar
  • zh
  • ja
  • ko
  • ru
  • hi

Verifitseerimata: pakkuja ei ole seda väidet dokumenteerinud. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

Millal kasutada

Tugevused

  • largest openly licensed model trained specifically for EU languages
  • Apache-2.0 licence
  • reference checkpoint for the project post-training recipe

Piirangud

  • no benchmark table is published on the model card
  • 32k-token context window
  • no evaluation has been run by LLM EU