Llama Nemotron Rerank VL 1B v2
flagshipNVIDIA Llama Nemotron Rerank VL 1B v2 is a multimodal cross-encoder reranking model that can rank both text and image-containing documents. Built on the Llama architecture with vision capabilities, it scores the relevance of documents (including screenshots, PDFs, and images) against text queries.
The model extends traditional text reranking to visual content, enabling search applications to rank documents with mixed text-and-image content. It handles charts, infographics, scanned documents, and visually rich web pages, providing relevance scores based on both textual and visual content understanding.
Rerank VL 1B v2 is designed for modern search applications where documents increasingly contain visual elements alongside text.
Providers for Llama Nemotron Rerank VL 1B v2
1 routes · sorted by uptimeClosedRouter routes requests to the providers best able to handle your prompt size and parameters, with automatic fallbacks to maximize uptime.
