Phi-4-multimodal-instruct

Microsoft

Catalóg amháin Meáchain oscailte

Ceannasacht agus óstáil

Sa chatalóg amháin

Tá an tsamhail seo catalógaithe le haghaidh tagartha. Níl sí óstáilte ar LLM EU fós, agus ní fhreastalaíonn aon chríochphointe céadpháirtí uirthi anseo. Téann iarratais chuici chuig an soláthraí go díreach, faoi théarmaí an tsoláthraí sin féin.

Achoimre

Phi-4-multimodal-instruct is a 5.6B model that accepts text, images and speech in one checkpoint, with a 128K-token context and the MIT licence. The model card reports 55.1 on MMMU, 93.2 on DocVQA and 62.4 on MathVista, and lists the supported languages separately for each input modality. It is a compact option for document and speech pipelines that would otherwise need two models.

Sonraíochtaí

Soláthraí
Microsoft (US)
Fuinneog chomhthéacs
131k
Paraiméadair
5.57B
Módúlachtaí
text, vision, audio
Ceadúnas
mit · licence
Meáchain oscailte
yes
Dáta scaoilte
24 Feabh 2025
Tascanna
vision, summarization, multilingual-support, cheap

Teangacha

Láidir: en, de, fr, es, it, pt

Leordhóthanach: nl, pl, sv, da, fi, cs, ru, uk, ar, zh, ja, ko, hi, tr

Teangacha

Láidir

  • en
  • de
  • fr
  • es
  • it
  • pt

Leordhóthanach

  • nl
  • pl
  • sv
  • da
  • fi
  • cs
  • ru
  • uk
  • ar
  • zh
  • ja
  • ko
  • hi
  • tr

Gan fíorú: níl an t-éileamh seo doiciméadaithe ag an soláthraí. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

Cathain a úsáidfear é

Láidreachtaí

  • text, image and speech input at 5.6B parameters
  • 128K-token context for document batches
  • MIT licence
  • 23 declared languages including most large EU languages

Teorainneacha

  • modality-specific quality is below dedicated single-modality models
  • English-centric training data
  • no evaluation has been run by LLM EU