multimodal LLMfamily
BLIP
Vision-language pre-training that bootstraps captions from noisy web data, with models for image captioning, visual question answering and image-text retrieval.
Levelfamily
Classmultimodal LLM
Parametersnot in the notes
Contextnot in the notes
Released28 Jan 2022
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
Lineage
BLIP image captioning large belongs to this familymultimodal LLM13 Dec 2022469.73MBLIP VQA base belongs to this familymultimodal LLM12 Dec 2022384.67MWhere 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
- Salesforce
- Family
- not in the notes
- Released
- 28 Jan 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
- 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
- BSD 3-Clause 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
DeveloperSalesforcebig tech, USA
Salesforcebig tech, USAModelBLIPSalesforce, multimodal LLM
BLIPSalesforce, multimodal LLMR&D TopicsVisual 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
Sources
- arxiv.org/abs/2201.12086 https://arxiv.org/abs/2201.12086
- github.com/salesforce/BLIP https://github.com/salesforce/BLIP
- github.com/GoogleCloudPlatform/vertex-ai-samples/tree/ma... https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/community/model_garden
- paperswithcode.com/method/blip https://paperswithcode.com/method/blip
- huggingface.co/Salesforce/blip-image-captioning-large https://huggingface.co/Salesforce/blip-image-captioning-large
- huggingface.co/Salesforce/blip-vqa-base https://huggingface.co/Salesforce/blip-vqa-base
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "BLIP", https://aurion.semai.id/models/salesforce-blip/, records of October 2026.