ai model report

Is CMSManhattan/JiRackUltra_1b safe to load?

CLEAN risk. 4 of 107 tracked dependencies carry advisories. Driven by No version-matched advisories and no malicious packages..

View on HuggingFace

// posture

fig. 01 — posture on eight axes, 100 is clean. Weakest: load safety at 60.

// the finding

not scoredno advisory applies to a version this model pinsCLEAN

LOWShips both safetensors and 1 pickle-format file(s); a consumer passing use_safetensors=False takes the pickle path.

1 more finding on this model.

Author: CMSManhattan
Task: text-generation
License: mit
Downloads: 307,357
Remote code: not required

// dependencies

20 direct, 17 with findings, 100 reachable

Package	Evidence	Advisories	Worst
transformers	direct, runtime	23	none pinned
torch	direct, runtime	13	none pinned
requests	direct, install	8	hidden
tqdm	direct, install	2	hidden
datasets	direct, install	0	hidden
huggingface-hub	direct, install	0	hidden
safetensors	direct, install	0	hidden
annotated-doc	direct, install	0	hidden

Create a free accountto see all 107 dependencies, which versions are pinned, and what to change.

Risk computed 2026-09-24 at 13:54 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.