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] Restore checkpoints into compiled models
- fix: make saved weight files as readable as other saved files
- Skip softmax over single-label CrossEncoder scores
- Support probability targets in SoftmaxLoss
- Fix dense FP16 embedding normalization
- Fix encoder-mask reuse in uncached multi-vector losses
- [Feature Request] Optional probability-target validation for SoftmaxLoss
- fix(gradcache): preserve fp64 precision in the backward hook's surrogate dot product
- Follow only duplicate pairs in the paraphrase mining transitive closure
- [fix] Use the auto-detected device in StaticEmbedding.from_distillation
- Docs
- Python not yet supported