#3535th of 37 in ML frameworks and libraries
sentence-transformers
Python library for computing, training and reranking with text embedding models
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 19.2k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Sentence Transformers is a Python library that computes dense embeddings, sparse (SPLADE-style) embeddings, ColBERT-style multi-vector embeddings and Cross-Encoder reranker scores through one API. It loads models from the 15,000+ on the Hugging Face Hub and includes trainers and loss functions for fine-tuning on your own data.
Who it is for: Python developers building semantic search or fine-tuning embedders
Strengths
- Four model types (dense, sparse, multi-vector, cross-encoder) behind one consistent encode/similarity/rank API
- Loads 15,000+ pretrained models from the Hugging Face Hub, including MTEB leaderboard models
- Built-in training with 20+ embedding losses and evaluation during training
- Optional extras for image, audio, video, ONNX and OpenVINO
Weaknesses
- Library only: no HTTP server, UI or vector store included
- Requires Python 3.10+, PyTorch 2.2+ and transformers v5.0+
- Model weights download from the Hugging Face Hub; gated models need login
- README states no RAM or GPU requirements
What it needs
- GPU optional
- Needs PyTorch 2.2+, transformers 5.0+, Hugging Face Hub
- Models: Sentence Transformer, Cross-Encoder, Sparse Encoder, Multi-Vector Encoder, BERT
Also in ML frameworks and libraries
See all 37| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 95 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd for deep learning | 94 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 90 out of 100 |
| #4 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 87 out of 100 |
| #5 | pytorch-image-modelsPyTorch library of image models, pretrained weights and reference training scripts | 86 out of 100 |