Mudelli

multilingual-e5-large

Microsoft

Katalgu biss Piżijiet miftuħa

Aħħar reviżjoni:

Sovranità u ospitar

Katalgu biss

Dan il-mudell huwa kkatalgat għal referenza. Għadu mhux ospitat fuq LLM EU, u l-ebda endpoint tal-ewwel parti ma jservih hawn. It-talbiet lejh imorru direttament għand il-fornitur, taħt it-termini tal-fornitur stess.

Sommarju

multilingual-e5-large huwa mudell ta' embedding ta' test ibbażat fuq XLM-RoBERTa b'560M parametru, ippubblikat taħt il-liċenzja MIT u li jkopri madwar 100 lingwa. Il-karta tal-mudell tuża tul massimu ta' sekwenza ta' 512 token, li huwa l-limitu effettiv kemm għall-indiċjar kif ukoll għall-mistoqsijiet. M'għandux prefiss ta' istruzzjoni għall-mistoqsijiet, għalhekk id-dokumenti u l-mistoqsijiet iridu jiġu inkorporati bl-istess mod.

Speċifikazzjonijiet

Fornitur
Microsoft (US)
Tieqa tal-kuntest
512
Parametri
0.56B
Modalitajiet
embedding
Liċenzja
mit · licence
Piżijiet miftuħa
yes
Data tar-rilaxx
30 Ġun 2023
Kompiti
Irkupru (RAG), Appoġġ multilingwi, Dejta sensittiva, Spiża baxxa

Lingwi

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

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

Qawwi

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

Adekwat

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

Mhux verifikat: il-fornitur ma ddokumentax din id-dikjarazzjoni. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

Meta tużah

Saħħiet

  • MIT licence and roughly 100 languages declared
  • runs on CPU for small indexes
  • long-established baseline with community tooling

Limiti

  • 512-token input limit
  • no instruction-aware query encoding
  • no retrieval benchmark has been run by LLM EU

Mistoqsijiet frequenti

Is multilingual-e5-large served on LLM EU?

It has no endpoint in the catalogue, so it is catalogue only — not hosted on LLM EU yet, with no region and no retention to report. A card whose status is "listed" is a catalogue entry, not a running deployment.

Under what licence is multilingual-e5-large released?

multilingual-e5-large is recorded under mit. The recorded licence text is https://opensource.org/license/mit. The weights are downloadable (open_weights is true). LLM EU republishes the licence id and the link and gives no legal advice; the licence text governs.

How large is multilingual-e5-large, and what context window does it have?

multilingual-e5-large is recorded at 560M (safetensors total 559,890,946) (source: https://huggingface.co/api/models/intfloat/multilingual-e5-large), with a context window of 512 tokens (source: https://huggingface.co/intfloat/multilingual-e5-large).