nvidia
/

NV-Embed-v2

Feature Extraction

sentence-transformers

Model card Files Files and versions Community

Resources

View closed (11)

Matryoshka Embedding in v2?

#25 opened 32 minutes ago by

Normalising embeddings

#24 opened about 8 hours ago by

Update configuration_nvembed.py (transformers + sentence-transformers) and infinity usage

#23 opened 3 days ago by

Thank you very much for your contribution. Could you please release the fine tuned code?

#22 opened 3 days ago by

What's the difference between v1 and v2?

#21 opened 9 days ago by

How the 7 negative samples are selected? Top7 below 0.95*postive_doc_score?

#20 opened 23 days ago by

Model Loading Problem

#19 opened 26 days ago by

Max Length of 32768

#18 opened about 1 month ago by

Is this model aligned/censored?

#17 opened about 1 month ago by

Is this multilingual and has this been tested on non-English only benchmarks?

#16 opened about 1 month ago by

Customized fine-tuning by users

#13 opened about 2 months ago by

fwj

Upload to Ollama

#12 opened about 2 months ago by

Does this work with vLLM?

#9 opened 2 months ago by

About Plans to Release Training Code

#5 opened 3 months ago by