Instructions to use nvidia/NV-Embed-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use nvidia/NV-Embed-v1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("nvidia/NV-Embed-v1", trust_remote_code=True) sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Finetuning guidelines
#21
by mali404 - opened
Hello there,
I am currently researching on whether a retriever model performance increases for specific domain if I finetune it on data particular to that domain. Can you share any finetuning guidelines or better any scripts that I could use in my experiments?
Thanks
Hi, could you find any scripts for pretraining / finetuning this model