ai model report

Is trl-internal-testing/small-Qwen3ForCausalLM safe to load?

LOW risk. 3 of 34 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: provenance at 45.

// the finding

0.0xyz score out of 10LOW

LOWThe repo's commit SHA changed since we first saw it — weights were replaced.

2 more findings on this model.

Author: trl-internal-testing
Task: text-generation
Loader: transformers
Downloads: 546,309
Remote code: not required

// dependencies

7 direct, 4 with findings, 28 reachable

Package	Evidence	Advisories	Worst
transformers	direct, runtime	23	none pinned
torch	direct, inferred	13	none pinned
numpy	direct, install	8	hidden
huggingface-hub	direct, install	0	hidden
safetensors	direct, install	0	hidden
tokenizers	direct, install	0	hidden
annotated-doc	direct, install	0	hidden
anyio	direct, install	0	hidden

Create a free accountto see all 34 dependencies, which versions are pinned, and what to change.

// what changed

MEDIUMrisk level raised (clean to low)2026-09-10

Risk computed 2026-09-22 at 18:44 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.