nvidia
/

llama-nemotron-embed-vl-1b-v2

Feature Extraction

llama_nemotron_vl

visual document retrieval

page image embedding

semantic search

question-answering retrieval

Model card Files Files and versions

Resources

View closed (1)

Add convenience options to processor methods

#3 opened about 1 month ago by

nvidia-oliver-holworthy

Use default attention implementation with option to override

#2 opened about 1 month ago by

nvidia-oliver-holworthy