embeddingfamily
ColPali
Retrieves document pages directly from their images using a vision language model with late-interaction multi-vector embeddings, skipping OCR.
Levelfamily
Classembedding
Parametersnot in the notes
Contextnot in the notes
Released27 Jun 2024
Opennessunknown
Runs onnot in the notes
Statusactive
Lineage
ColQwen2 v1.0 belongs to this familyembedding3 Nov 2024ColPali v1.2 belongs to this familyembedding26 Aug 2024Where 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
- Illuin Technology
- Family
- not in the notes
- Released
- 27 Jun 2024 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
- unknown
- Licence
- not in the notes 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
- Model card languages: en
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
DeveloperIlluin Technologycompany
Illuin TechnologycompanyModelColPaliIlluin Technology, embedding
ColPaliIlluin Technology, embeddingR&D TopicsRetrieval-Augmented Generation (RAG)Text Embeddings for Semantic SearchVisual Document Retrieval
Use CasesEmbeddings and Retrieval for SEA LanguagesPublic SectorUse 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
Retrieval-Augmented Generation (RAG)Grounding generation in retrieved documents.used byText Embeddings for Semantic SearchTraining encoders that turn text in many languages into vectors so that search, clusterin…produced byVisual Document RetrievalRetrieving document pages by embedding the page images themselves with a vision language…exemplar
Sources
- arxiv.org/abs/2407.01449 https://arxiv.org/abs/2407.01449
- github.com/illuin-tech/colpali https://github.com/illuin-tech/colpali
- huggingface.co/api/models?pipeline_tag=visual-document-retri... https://huggingface.co/api/models?pipeline_tag=visual-document-retrieval&sort=downloads&limit=50
- modelscope.cn/models/AI-ModelScope/colpali https://www.modelscope.cn/models/AI-ModelScope/colpali
- huggingface.co/vidore/colpali-v1.2 https://huggingface.co/vidore/colpali-v1.2
- huggingface.co/vidore/colqwen2-v1.0 https://huggingface.co/vidore/colqwen2-v1.0
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "ColPali", https://aurion.semai.id/models/illuin-colpali/, records of October 2026.