sentence-transformers
https://github.com/ukplab/sentence-transformers
Python
Sentence Embeddings with BERT & XLNet
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported15 Subscribers
Add a CodeTriage badge to sentence-transformers
Help out
- Issues
- [fix] Return per-input token embeddings from encode() with Flash Attention input flattening
- [`feat`] Add min-max score normalization to DistillKLDivLoss family
- Inputs are silently truncated at `max_seq_length` with no way for the caller to detect it
- [Feature Request] Jev-style structured judgments for CrossEncoder — working implementation in KaLM-Jev
- No constructor-based way to set query_length/document_length on `MultiVectorEncoder`
- Problems in training multi-modal models with large batch sizes
- Loading a LoRA CrossEncoder checkpoint does not restore a trained `modules_to_save` classification head
- Backend ignores root level ONNX files, and cannot detect full model exports
- Let a module declare an extra output type (e.g. multi-vector + sparse from one model)
- Docs: deployment guidance for cold starts and offline model loading (scale-to-zero, local_files_only, warmup)
- Docs
- Python not yet supported