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
- Use quadratic-memory semi-hard triplet mining
- Cached losses (GradCache) trigger one DDP all-reduce per mini-batch per column instead of one per step
- Group tied scores when evaluating paraphrase mining
- Prune invalid positive pairs before forming batch-all triplets
- Compute CoSENT ranking loss with linear-memory suffix reductions
- Count tied top matches as correct in TranslationEvaluator
- Return zero ranking loss when no label pairs are ordered
- Keep Euclidean similarity gradients finite at zero distance
- Accept a string main_score_function in NanoBEIREvaluator
- docs: Document shared input formats across model archetypes
- Docs
- Python not yet supported