llama-nemotron-embed-vl-1b-v2
nvidia/llama-nemotron-embed-vl-1b-v2
- kind
- original
- quant
- bf16 (16-bit)
- family
- llama
- modality
- sentence-similarity
- root model
- nvidia/llama-nemotron-embed-vl-1b-v2
- provider
- nvidia
- license
- other
- language
- multilingual
- context
- —
- library
- sentence-transformers
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 101,225
- likes
- 95
- created
- —
- last modified
- 2026-07-07T11:13:28+00:00 (2026)
- huggingface
- https://huggingface.co/nvidia/llama-nemotron-embed-vl-1b-v2
- tags
- sentence-transformerssafetensorsllama_nemotron_vlfeature-extractionretrievalvisual document retrievalvlm embeddingpage image embeddingtext embeddingsemantic searchquestion-answering retrievalragtransformerssentence-similaritycustom_codemultilingualarxiv:2501.14818license:otherendpoints_compatibleregion:us
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.