SentenceTransformer

This release introduces Multi-Vector Embedding models (ColBERT-style) as a new model type, enhancing retrieval capabilities. It also modernizes dependencies, fixes silent scoring bugs, and improves performance.

This minor release focuses on correctness and robustness, fixing silent scoring bugs related to chat-template truncation and improving stability for hard-negative mining and GIST losses. It also introduces MPS support and restores TSDAE functionality on recent `transformers` versions.

This release introduces the `train-sentence-transformers` Agent Skill and two new training losses, `EmbedDistillLoss` and `ADRMSELoss`, alongside numerous robustness and correctness improvements.

This patch release enhances input handling for numpy string/object arrays in `encode()` and `predict()` and introduces a critical security fix by restricting activation function loading in the `Dense` module.

This release introduces major first-class multimodal support for SentenceTransformer and CrossEncoder, enabling unified processing of text, images, audio, and video. The CrossEncoder architecture has also been fully modularized, enabling support for generative rerankers.

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.

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.

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

This release introduces a preview of the EmbeddingGemma model, a highly efficient 308M parameter multilingual embedding model optimized for on-device RAG and mobile use cases.