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
- FT Cross-Encoder model to get certain results (0 or 1) in case of binary classification?
- unable to initialize the model from README.md
- Pre-train SentenceEmbedder using TSDAE from scratch i.e not using existing model like "bert-base-uncased"
- Matryoshka Embeddings Implementation details
- Not able to load models from cache with latest torch version
- Can not load a local model
- backward_loss transpose() meaning in MultipleNegativesSymmetricRankingLoss
- The `util.cos_sim` always uses `Tensor` object and also returns the same when we are working with numpy
- Multitasking Loss
- [BUG]: CrossEncoder.predict() with num_workers > 0 returns constants
- Docs
- Python not yet supported