embedding
all-MiniLM-L6-v2
Sentence-transformers model that maps sentences and paragraphs to 384-dimension vectors for clustering and semantic search.
Levelmodel
Classembedding
Parameters22.7M
Context256
Releasednot in the notes
Opennessopen weights permissive
Runs onCPU server, laptop
Statusactive
Lineage
quantize
all-MiniLM-L6-v2 (Xenova, Transformers.js ONNX) is a child (quantize)high confidenceHugging Face base_modelall-MiniLM-L6-v2 (Xenova, Transformers.js ONNX) belongs to this modelembedding2 May 2023Where 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, 2 models. Confidence and evidence are the notes' own.
Identity
- Developer
- Sentence Transformers
- Family
- not in the notes
- Released
- – sources
- Weights published
- –
- Record checked
- 11 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 MiniLM-L6-H384 (BERT type) fine-tuned with a contrastive objective on about 1.17B sentence pairs; 384-dimension embeddings
- Total parameters
- 22.7M sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- 256 tokens
- Input
- text
- 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
- Apache License 2.0 sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- CPU server, laptop
- 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
DeveloperSentence Transformersopen community
Sentence Transformersopen communityModelall-MiniLM-L6-v2Sentence Transformers, embedding
all-MiniLM-L6-v2Sentence Transformers, 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/sentence-transformers/all-MiniLM-L6-v2 https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "All-MiniLM-L6-v2", https://aurion.semai.id/models/sentence-transformers-all-minilm-l6-v2/, records of October 2026.