
vision
BEiT-3
General vision and vision-language foundation model, from the paper "Image as a Foreign Language".
Levelvariant
Classvision
Parametersnot in the notes
Contextnot in the notes
Released22 Aug 2022
Opennessunknown
Runs onnot in the notes
Statusnot in the notes
Lineage
successor
BEiT v2 is the parent (successor)high confidencenotesWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 3 models. Confidence and evidence are the notes' own.
R&D Topics
Identity
- Developer
- Microsoft AI
- Family
- BEiT
- Released
- 22 Aug 2022 sourcesannouncement page
- Weights published
- –
- Record checked
- 12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- image
- Output
- not in the notes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- unknown
- Licence
- not in the notes sources
- Access routes
- not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Industry Use Cases
No industry use case links this model.
Links
Developer
Microsoft AIbig tech, USA
Microsoft AIbig tech, USAModel
BEiT-3Microsoft AI, vision
BEiT-3Microsoft AI, visionR&D TopicsSelf-Supervised Visual Representation LearningContrastive Image-Text Encoders (CLIP and SigLIP Lines)
Use CasesPathology Whole-Slide ImagingHealthcareUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs Itnone recordedDeployments of these use cases; none names this model.
Organisations 1
R&D topics 2
Self-Supervised Visual Representation LearningPretraining image encoders without labels so their features transfer to many vision tasks.produced byContrastive Image-Text Encoders (CLIP and SigLIP Lines)Image and text encoders trained together so that pictures and captions share one embeddin…produced by
Sources
- arxiv.org/abs/2208.10442 https://arxiv.org/abs/2208.10442
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "BEiT-3", https://aurion.semai.id/models/microsoft-beit-3/, records of October 2026.