Task
Image Feature Extraction
L
nvidia/llama-nemotron-embed-1b-v2
Image Feature Extraction·nvidia· 656.8K· 57
sentence-transformers
other
1.2B params
The Llama Nemotron Embedding 1B model is optimized for multilingual and cross-lingual text question-answering retrieval with support for long documents (up to 8192 tokens) and dynamic embedding size (Matryoshka Embeddings). This model was evaluated on 26 languages: English, Arabic, Bengali, Chinese, Czech, Danish, Dutch, Finnish, French, German, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japan
# pull & run locally
pip install mlforge-sdk && mlforge pull nvidia/llama-nemotron-embed-1b-v2
pip install mlforge-sdk && mlforge pull nvidia/llama-nemotron-embed-1b-v2
Model details
Provider
nvidia
Framework
sentence-transformers
Parameters
1.2B
Size
4.6 GB
License
other
Downloads
656.8K
Likes
57
Paper
arXiv:2407.15831
Updated
2026-05-20
About nvidia/llama-nemotron-embed-1b-v2
The Llama Nemotron Embedding 1B model is optimized for multilingual and cross-lingual text question-answering retrieval with support for long documents (up to 8192 tokens) and dynamic embedding size (Matryoshka Embeddings). This model was evaluated on 26 languages: English, Arabic, Bengali, Chinese, Czech, Danish, Dutch, Finnish, French, German, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Norwegian, Persian, Polish, Portuguese, Russian, Spanish, Swedish, Thai, and Turkish.