Change8

sentence-transformers

AI & LLMs

State-of-the-Art Text Embeddings

Latest: v5.2.010 releases5 breaking changesView on GitHub →

Release History

v5.2.0Breaking2 fixes6 features
Dec 11, 2025

Version 5.2.0 adds multiprocessing to CrossEncoder, multilingual NanoBEIR support, similarity scores in hard‑negative mining, and updates for Transformers 5 while deprecating Python 3.9 and the old `n-tuple-scores` format.

v5.1.29 fixes8 features
Oct 22, 2025

Sentence‑Transformers 5.1.2 adds improved saving for StaticEmbedding and Dense modules, introduces Intel XPU as the default device, enhances loss compatibility, and adds Python 3.13 support while fixing several training and loading bugs.

v5.1.1Breaking8 fixes3 features
Sep 22, 2025

Version 5.1.1 adds explicit validation of unused kwargs in `encode`, introduces FLOPS metrics for SparseEncoder evaluators, supports Knowledgeable Passage Retriever models, and includes several bug fixes around batch size handling, multi‑GPU processing, and evaluator output paths.

v5.1.01 fix6 features
Aug 6, 2025

Version 5.1.0 adds ONNX and OpenVINO backends for SparseEncoder, a new n‑tuple‑scores format for hard‑negative mining, multi‑GPU gathering, TrackIO support, and updated documentation.

v5.0.01 fix8 features
Jul 1, 2025

Sentence-Transformers 5.0.0 adds SparseEncoder support, new encode_query/document methods, multiprocessing encoding, a Router module, custom learning rates, and composite loss logging, while remaining backwards compatible.

v4.1.01 fix5 features
Apr 15, 2025

Version 4.1.0 adds ONNX and OpenVINO backends for CrossEncoder, a new `backend` argument, and utilities for model optimization, while remaining backward compatible.

v4.0.2Breaking7 fixes4 features
Apr 3, 2025

Version 4.0.2 introduces safer max-length handling for CrossEncoder models and improves distributed training device placement, while fixing typing, FSDP, and documentation issues.

v4.0.1Breaking17 features
Mar 26, 2025

Version 4.0.1 introduces a complete overhaul of the CrossEncoder training pipeline with a new `CrossEncoderTrainer`, dataset‑based inputs, multi‑GPU and bf16 support, and many training‑related enhancements, while keeping inference unchanged.

v3.4.16 fixes1 feature
Jan 29, 2025

Version 3.4.1 adds native Model2Vec support to SentenceTransformer and fixes several documentation and network‑request bugs.

v3.4.0Breaking10 fixes5 features
Jan 23, 2025

Version 3.4.0 fixes a major memory‑leak issue, adds compatibility between cached losses and MatryoshkaLoss, introduces several new features, and resolves numerous bugs.