ai model report
Is inclusionAI/Ling-3.1-flash safe to load?
LOW risk. 2 of 86 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
- inclusionAI
- Task
- text-generation
- License
- mit
- Downloads
- 8
- Remote code
- ships Python that runs on load (trust_remote_code)
6 direct, 4 with findings, 82 reachable
| Package | Evidence | Advisories | Worst |
|---|---|---|---|
| transformers | direct, runtime | 24 | none pinned |
| torch | direct, runtime | 12 | none pinned |
Create a free accountto see all 86 dependencies, which versions are pinned, and what to change.
Risk computed 2026-10-16 at 04:46 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.