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 scalar quantization arithmetic for float16 embeddings
- Exclude unretrieved positives from observed RRF ranking metrics
- Compute large-batch orthogonal regularization with the feature Gram matrix
- Preserve ranking-loss gradients with weighted log-sigmoid
- Compare CSR reconstructions with the raw input when normalize=True
- Drop two docstring entries for parameters that do not exist
- Pass args.seed to the per-dataset batch samplers
- [`fix`] Apply default_prompt_name in encode_query when there is no query prompt
- Keep the CSR 4k latents off the dead-latent mask
- Schedule the regularizer weights of every SpladeLoss
- Docs
- Python not yet supported