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 supported16 Subscribers
Add a CodeTriage badge to sentence-transformers
Help out
- Issues
- Inner Product Metric Produces Negative Distances for Similar Embeddings with Quantized Int8 Data
- Fix #3185: Support `convert_to_numpy` for `output_value="token_embeddings"`
- `convert_to_numpy=True` not working with `output_value="token_embeddings"`; returns `torch.Tensor` type
- modernBERT doesn't support Denoising Auto Encoder loss
- Question to MultipleNegativesRankingLoss and cosine similarity
- Deepspeed + CachedMNRL: Gradient computed twice for this partition. Multiple gradient reduction is currently not supported
- load_best_model fails with multi gpu and lora training
- finetuning modernbert
- fully support float16 and bfloat16 for embeddings (or at least float16)
- Dataset Format for MNRL Loss with Multiple Negatives
- Docs
- Python not yet supported