Sentence Transformers
Project record
Maintained by Hugging Face13
Sentence Transformers is a Python framework for using and training embedding and reranker models. It computes dense embeddings with Sentence Transformer models, scores text pairs with Cross-Encoder (reranker) models, and also supports sparse encoders and multi-vector models for ColBERT-style late-interaction retrieval, with pretrained models published on Hugging Face. Version 6.1.0 was released on September 18, 2026.14
- Repository: Repository (external site: github.com)
- Documentation: Documentation (SBERT.net) (external site: sbert.net)
- License: LICENSE (Apache-2.0) (external site: github.com)
- Website: Package on PyPI (external site: pypi.org)
- Release notes: Releases (external site: github.com)
Availability and license
Overall availability
Source is public on GitHub, and the package is published on PyPI and conda-forge.16
Availability is separate from permission: read the license before using or redistributing.
Component reuse rights
- weights
- Unknown — no complete fact-level rights review
- code
- Reviewed qualifying license recorded — check scope and conditions
- data
- Unknown — no complete fact-level rights review
- documentation
- Unknown — no complete fact-level rights review
No complete system-rights review is recorded for this release.
Public materials checklist
| Item | Status | Notes and evidence |
|---|---|---|
| Source codeIs the source code publicly readable? | Public | Public on GitHub, with example applications in the repository.1 |
| DocumentationIs user documentation published? | Public | SBERT.net has a quickstart, installation guide, training overviews for each model type, and a package reference.16 |
| InstallationAre installation instructions or packages publicly available? | Public | Installable with pip, uv, or conda-forge, or from source; optional extras add image, audio, video, training, ONNX, and OpenVINO support. Requires Python 3.10 or later, PyTorch 2.2 or later, and Transformers v5 or later.65 |
| Supported platformsAre supported operating systems or hardware documented? | Partial | The package metadata lists Python 3.10 to 3.13. For GPU use the documentation defers to PyTorch's installation instructions; no operating system list is given.56 |
| Release statusAre versioned releases published? | Public | Versioned GitHub releases with notes and matching PyPI versions, marked "Production/Stable"; 6.1.0 was released on 2026-09-18.45 |
What it is useful for
Organization context
Provenance and derivatives
U.S. eligibility
Eligible · basis: U.S.-governed project
Two-organization history. The project was originally developed by the UKP Lab at TU Darmstadt in Germany, which the NOTICE file lists as copyright holder for 2019 to 2025. The repository is now in Hugging Face's GitHub organization, the NOTICE file lists Hugging Face, Inc. as copyright holder from 2025, and the README names a Hugging Face maintainer. Hugging Face, Inc. is a Delaware corporation per Hugging Face's terms of service; the catalog's hugging-face record assesses its U.S. headquarters. The catalog treats Hugging Face as the current maintaining entity.137
Sources
This listing is not an endorsement, a safety assessment, or a federal approval.