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
- Include a model identity in the hard negatives embedding cache key
- [fix] Return per-input token embeddings from encode() with Flash Attention input flattening
- [Bug] GradCache replay downcasts FP64 embeddings to FP32 in the surrogate dot product
- [Bug] Keep FP64 in the GradCache replay surrogate
- [`feat`] Add min-max score normalization to DistillKLDivLoss family
- Fix normalize_embeddings crash on a single 1D embedding
- Fix mixed-precision distances in batch triplet losses
- Fix CachedGISTEmbedLoss retokenization for flattened inputs
- Fix blank rows in CrossEncoder and RRF evaluator CSVs on Windows
- Rescore with the CrossEncoder when only min_score is set in mine_hard_negatives
- Docs
- Python not yet supported