Feature Extraction
Transformers
Safetensors
sentence-transformers
English
nvembed
mteb
custom_code
Eval Results (legacy)
Instructions to use nvidia/NV-Embed-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/NV-Embed-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="nvidia/NV-Embed-v2", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/NV-Embed-v2", trust_remote_code=True, dtype="auto") - sentence-transformers
How to use nvidia/NV-Embed-v2 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("nvidia/NV-Embed-v2", 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
Max Length of 32768
#18
by hugginghugging - opened
Thank you for open-sourcing this great model! In the example code, max_length is set to 32768. Is there a reason for setting the max length to this large number? I took a look at the paper and this argument is set to 512 for fair comparison with baselines.
What is the token length for this model?