embedding
jina-embeddings-v3
jina-embeddings-v3 is a multilingual multi-task text embedding model with task-specific LoRA adapters and 8192-token input.
Levelmodel
Classembedding
Parameters572.31M
Context8,192
Released5 Sep 2024
Opennessopen weights restricted
Runs onnot in the notes
Statusnot in the notes
Identity
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
- other Jina-XLM-RoBERTa encoder with RoPE and 5 task LoRA adapters; Matryoshka dimensions 32 to 1024
- Total parameters
- 572.31M sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- Hugging Face API Safetensors count
- Context length
- 8,192 tokens
- Input
- text
- 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
- open weights restricted
- Licence
- Creative Commons Attribution-NonCommercial 4.0 sources
- Access routes
- API, cloud marketplace, 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
- listed by developer
- Regional languages
- Javanese, Sundanese
- Jakarta hosting
- unknown
- Languages
- Foundation supports 100 languages; tuning focused on 30 including Indonesian, Thai and Vietnamese
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.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperJina AIcompany, Germany
Jina AIcompany, GermanyModeljina-embeddings-v3Jina AI, embedding
jina-embeddings-v3Jina AI, embeddingUse 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.
Organisations 1
Sources
- huggingface.co/jinaai/jina-embeddings-v3 https://huggingface.co/jinaai/jina-embeddings-v3
- huggingface.co/api/models/jinaai/jina-embeddings-v3 https://huggingface.co/api/models/jinaai/jina-embeddings-v3
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Jina-Embeddings-v3", https://aurion.semai.id/models/jina-ai-jina-embeddings-v3/, records of October 2026.