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
- Weighted mean pooling changes with left padding
- Count weightedmean positions from the first non-padding token
- StaticEmbedding ignores model2vec `mapping`/`weights` tensors, so e.g. `minishlab/potion-code-16M` produces wrong embeddings
- Apply model2vec token mapping and weights when loading StaticEmbedding
- Normalize Matryoshka teacher targets like the student embeddings
- Fix encode_document to ignore empty prompt and use default prompt name
- Fix uint64 precision loss in resolve_ids
- Similarity utilities reject dense tensor lists returned by encode
- Fix similarity scoring of dense tensor lists
- [`fix`] Respect `verbose=False` for the average-positives message in `mine_hard_negatives`
- Docs
- Python not yet supported