SparseEncoder

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.

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.

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.