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 supported13 Subscribers
Add a CodeTriage badge to sentence-transformers
Help out
- Issues
- reducing `encode_multi_process` GPU memory usage
- Giving hard_negative a higher weight when calculating loss
- how to keep `encode_multi_process` output on the GPU
- MultipleNegativesSymmetricRankingLoss (potential optimization opportunity)
- Sentence Transformers / datasets dependency.
- Dask vs multiprocessing
- Inference speed difference when using sentence-transformers (python) and candle (rust)
- Cross Encoders do not free GPU memory after execution
- encode Function Returns NaN Embeddings for Some Tokens When Called on All Vocabulary
- [`fix`] Quantization of token embeddings
- Docs
- Python not yet supported