sentence-transformers
AI & LLMsState-of-the-Art Text Embeddings
Release History
v5.2.0Breaking2 fixes6 featuresVersion 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 featuresSentence‑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 featuresVersion 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 featuresVersion 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 featuresSentence-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 featuresVersion 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 featuresVersion 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 featuresVersion 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 featureVersion 3.4.1 adds native Model2Vec support to SentenceTransformer and fixes several documentation and network‑request bugs.
v3.4.0Breaking10 fixes5 featuresVersion 3.4.0 fixes a major memory‑leak issue, adds compatibility between cached losses and MatryoshkaLoss, introduces several new features, and resolves numerous bugs.