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
- Add opt-in synchronized per-dataset training batches
- Reduce TranslationEvaluator memory with blockwise scoring
- [fix] Keep adapters trainable when loading a saved PEFT/LoRA model
- Support variable-length hard negatives in CrossEncoder ranking losses
- Reduce CPU XTR training-scorer memory with streaming token top-k
- [feat] Add an evaluator for exporting sentence embeddings
- [fix] Restore loss-owned weights when resuming from a checkpoint
- Docs: deployment guidance for cold starts and offline model loading
- Discussion: Native OpenTelemetry Instrumentation for Sentence Transformers
- Explain batch sizes for cached contrastive losses
- Docs
- Python not yet supported