Sentence Similarity
sentence-transformers
Safetensors
Transformers
ministral3
feature-extraction
text
text-embeddings
retrieval
semantic-search
rag
vllm
Instructions to use nvidia/Nemotron-3-Embed-1B-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use nvidia/Nemotron-3-Embed-1B-BF16 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("nvidia/Nemotron-3-Embed-1B-BF16") 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/Nemotron-3-Embed-1B-BF16 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("nvidia/Nemotron-3-Embed-1B-BF16") model = AutoModel.from_pretrained("nvidia/Nemotron-3-Embed-1B-BF16", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Congratulations on the LMEB SOTA! ๐
#3
by Yuki131 - opened
Congratulations to the NVIDIA Nemotron team! ๐
The results merged in https://github.com/embeddings-benchmark/results/pull/617 show outstanding LMEB performance:
- Nemotron-3-Embed-8B-BF16: 64.4, a new overall SOTA.
- Nemotron-3-Embed-1B-BF16: 61.5, a new SOTA at the ~1B scale.
The LMEB leaderboard does not appear to have synchronized the newly merged results yet. Based on the merged scores, the 8B and 1B models should rank first and second overall, respectively, once the leaderboard is updated.
ybabakhin changed discussion status to closed
Glad to see the results are liveโwell deserved! ๐