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
chore: update license to OpenMDW-1.1
Updates the model, configuration, and NVIDIA source-code licensing to OpenMDW-1.1, following llama-nemotron-rerank-1b-v2 PR #16.
Replaces LICENSE with the reference license text, updates model-card metadata and license references, and updates NVIDIA source-file SPDX identifiers. Adds the same CONTRIBUTING.md as the reference PR. Preserves existing copyright notices, Llama attribution, and third-party notices.
Validation: checked all changed files, verified the license matches the reference byte-for-byte, and confirmed Python ASTs are unchanged.
Signed-off-by: Oliver Holworthy 1216955+oliverholworthy@users.noreply.github.com