ai model report
Is nvidia/NV-Embed-v2 safe to load?
LOW risk. 5 of 96 tracked dependencies carry advisories. Driven by No version-matched advisories and no malicious packages..
not scoredno advisory applies to a version this model pinsLOW
MEDIUMconfig.json declares `auto_map` — from_pretrained(trust_remote_code=True) executes Python shipped in this repo.
2 more findings on this model.
- Author
- nvidia
- Task
- feature-extraction
- Loader
- transformers
- License
- cc-by-nc-4.0
- Downloads
- 86,014
- Remote code
- ships Python that runs on load (trust_remote_code)
14 direct, 10 with findings, 87 reachable
| Package | Evidence | Advisories | Worst |
|---|---|---|---|
| transformers | direct, runtime | 24 | none pinned |
| torch | direct, runtime | 12 | none pinned |
Create a free accountto see all 96 dependencies, which versions are pinned, and what to change.
Risk computed 2026-10-07 at 17:51 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.