Phi-4-multimodal-instruct
Aħħar reviżjoni:
Sovranità u ospitar
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
Phi-4-multimodal-instruct huwa mudell 5.6B li jaċċetta test, immaġini u diskors f'checkpoint wieħed, b'kuntest ta' 128K-token u l-liċenzja MIT. Il-karta tal-mudell tirrapporta 55.1 fuq MMMU, 93.2 fuq DocVQA u 62.4 fuq MathVista, u telenka l-lingwi appoġġjati separatament għal kull modalità ta' input. Hija għażla kompatta għal pipelines ta' dokumenti u diskors li kieku jkollhom bżonn żewġ mudelli.
Speċifikazzjonijiet
- Fornitur
- Microsoft (US)
- Tieqa tal-kuntest
- 131k
- Parametri
- 5.57B
- Modalitajiet
- text, vision, audio
- Liċenzja
- mit · licence
- Piżijiet miftuħa
- yes
- Data tar-rilaxx
- 24 Fra 2025
- Kompiti
- Viżjoni, Sommarizzazzjoni, Appoġġ multilingwi, Spiża baxxa
Lingwi
Qawwi: en, de, fr, es, it, pt
Adekwat: nl, pl, sv, da, fi, cs, ru, uk, ar, zh, ja, ko, hi, tr
Qawwi
- en
- de
- fr
- es
- it
- pt
Adekwat
- nl
- pl
- sv
- da
- fi
- cs
- ru
- uk
- ar
- zh
- ja
- ko
- hi
- 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
- 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
Limiti
- modality-specific quality is below dedicated single-modality models
- English-centric training data
- no evaluation has been run by LLM EU
Mistoqsijiet frequenti
Is Phi-4-multimodal-instruct 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 Phi-4-multimodal-instruct released?
Phi-4-multimodal-instruct 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 Phi-4-multimodal-instruct, and what context window does it have?
Phi-4-multimodal-instruct is recorded at 5.57B (safetensors total 5,574,460,384) (source: https://huggingface.co/api/models/microsoft/Phi-4-multimodal-instruct), with a context window of 131072 tokens (source: https://huggingface.co/microsoft/Phi-4-multimodal-instruct).