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`] similarity functions crashing or overflowing on quantized (int8/uint8/binary) embeddings
- [fix] Keep paraphrase mining top_k per sentence across corpus chunks
- [docs] Fix dead MTEB 'adding a model' link
- [fix] Keep top_k per sentence across corpus chunks in paraphrase mining
- Evaluate the main similarity function in TripletEvaluator
- Fix encode(precision=...) and quantize_embeddings crashing on bfloat16 embeddings
- encode_document() never uses a "passage" or "corpus" prompt
- Add opt-in lazy preprocessing for cached multimodal training
- Fix WordEmbeddings crash with HF tokenizers on transformers v5
- Stop the multi-process pool when hard negative mining fails
- Docs
- Python not yet supported