Feature Extraction
sentence-transformers
PyTorch
Safetensors
Transformers
multilingual
llama_bidirec
text
text-embeddings
retrieval
semantic-search
custom_code
text-embeddings-inference
Instructions to use nvidia/llama-nemotron-embed-1b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use nvidia/llama-nemotron-embed-1b-v2 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("nvidia/llama-nemotron-embed-1b-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] - Transformers
How to use nvidia/llama-nemotron-embed-1b-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="nvidia/llama-nemotron-embed-1b-v2", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/llama-nemotron-embed-1b-v2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add rope_theta to rope_scaling for transformers 5.4+ compatibility
#19
by oliverholworthy - opened
transformers==5.4.0 validates that rope_theta is present inside rope_scaling before the migration from the top-level field runs, causing a KeyError when loading the config without trust_remote_code=True. Adds rope_theta inside rope_scaling while keeping the top-level value for backwards compatibility with transformers v4.
oliverholworthy changed pull request title from Update rope params to Add rope_theta to rope_scaling for transformers 5.4+ compatibility
oliverholworthy changed pull request status to open
oliverholworthy changed pull request status to merged