multimodal LLMfamily
Florence-2
Small sequence-to-sequence vision foundation model that handles captioning, object detection, grounding, segmentation and OCR from text prompts.
Levelfamily
Classmultimodal LLM
Parametersnot in the notes
Contextnot in the notes
Released10 Nov 2023
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
Lineage
Florence-2 base belongs to this familymultimodal LLM15 Jun 2024231.57MFlorence-2 large belongs to this familymultimodal LLM15 Jun 2024776.72MWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.
R&D Topics
Identity
- Developer
- Microsoft AI
- Family
- not in the notes
- Released
- 10 Nov 2023 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
- text, image
- Output
- text
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
- open weights permissive
- Licence
- MIT License sources
- Access routes
- open weights download
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
DeveloperMicrosoft AIbig tech, USA
Microsoft AIbig tech, USAModelFlorence-2Microsoft AI, multimodal LLM
Florence-2Microsoft AI, multimodal LLMR&D TopicsDocument, OCR and Chart UnderstandingOpen-Vocabulary Object Detection and GroundingVisual Instruction Tuning
Use CasesRobot Inspection with Instrument ReadingIndustrialPathology 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.
Models 2
Organisations 1
R&D topics 3
Visual Instruction TuningConnecting a vision encoder to a language model and training it on image-grounded instruc…produced byOpen-Vocabulary Object Detection and GroundingDetectors and segmenters that find objects named in free text, including classes never la…produced byDocument, OCR and Chart UnderstandingVision-language models that read text-rich images such as scanned documents, forms, chart…exemplar
Sources
- arxiv.org/abs/2311.06242 https://arxiv.org/abs/2311.06242
- huggingface.co/api/models?pipeline_tag=image-text-to-text&so... https://huggingface.co/api/models?pipeline_tag=image-text-to-text&sort=downloads&limit=50
- replicate.com/lucataco/florence-2-large https://replicate.com/lucataco/florence-2-large
- huggingface.co/microsoft/Florence-2-base https://huggingface.co/microsoft/Florence-2-base
- huggingface.co/microsoft/Florence-2-large https://huggingface.co/microsoft/Florence-2-large
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Florence-2", https://aurion.semai.id/models/microsoft-florence-2/, records of October 2026.