OpenHubAI
Back to browse
Embeddingsapache-2.0
sentence-transformers/all-MiniLM-L6-v2
SEsentence-transformers
In plain English

Good for making your own site search or FAQ matching work by meaning instead of exact keywords. Not a chatbot on its own and needs your own documents to be useful.

A compact 22 million parameter sentence embedding model from the Sentence-Transformers project, widely used as a fast default for semantic search and clustering.

Required documentation

Complete
Intended use

Intended for turning short passages into embeddings for semantic search, clustering, or FAQ matching. Not intended for text generation.

Training data provenance

Trained by the Sentence-Transformers project on a mixture of publicly available sentence pair datasets, documented in the project's own model card.

Licence & terms

Apache-2.0.

MRMaya Rehanirep 4.8Production1110a24
7h ago
Accuracy4.4
Fine-tune4.6
Documentation4.3
Speed4.9
TNTomasz Nowakrep 4.5Production1110a24
7h ago
Accuracy4.5
Fine-tune4.4
Documentation4.1
Speed5.0
PSPriya Shahrep 4.6Prototype1110a24
7h ago
Accuracy4.3
Fine-tune4.5
Documentation4.2
Speed4.8

Discussion0

Posting as a signed-in userSign in to post

No questions yet. Be the first to ask one.

Structured rating
4.5

from 3 reviews of 1110a24

Only 3 reviews on 1110a24 so far. Earlier versions carry more, but they are not this build.
Accuracy4.4
Fine-tune4.5
Documentation4.2
Speed4.9
Run it now
ollama run sentence-transformers/all-MiniLM-L6-v2
Will it fit?
BuildFileVRAM
F1691 MB0.4 GB

Set a hardware profile in the browse sidebar to see which builds fit.

Inference providers

No hosted providers listed yet.

No cloud required. Run it with

No confirmed local runners yet, try the Run it now commands above.

Model tree
Base modelnreimers/MiniLM-L6-H384-uncased
Adapters0
Finetunes0
Quantizations1
Merges0
At a glance
Parameters
Licenceapache-2.0
Downloads254.0M
Reviews3
Docs completenessComplete