Model page

Qwen/Qwen3Guard-Stream-4B warn

downloads 906likes 25license apache-2.0arch qwen3params 4025.1Mupdated 2025-11-07

claims base: Qwen/Qwen3-4B · chat template: present · view on Hugging Face ↗

Scan coverage

Ingot runs three batteries against a model. What each one checks →

BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-21
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-21151,936-token embedding scanned · 0 undertrained · lineage consistent
Behavioral batteryLive-inference differentialsn/anot applicable — feature-extraction model has no text-generation surface to probe

Findings

Scanned 2026-08-21 · published from a community scan.

medium Repo ships executable Python (trust_remote_code)

The repository contains custom code files that run in-process when loaded with trust_remote_code=True. Pin the revision hash and review the code before loading.

How to fix

Review and pin the custom code; never float on `main` with trust_remote_code=True.

  1. Read every `.py` file in the repo before first load — this code runs in your process.
  2. Pin the revision: `from_pretrained(model_id, revision="<commit sha>", trust_remote_code=True)` so a later push can't swap the code under you.
  3. Prefer a version of the architecture already in `transformers` if one exists, which removes the remote-code requirement entirely.

info Embedding-norm glitch scan clean

No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (1.125). The glitch-token data-corruption class has no candidate surface in this model.

info Weights consistent with claimed parent Qwen/Qwen3-4B

Mean cosine similarity of 64 sampled token-embedding rows against Qwen/Qwen3-4B is 1.000 — the weights plausibly descend from the declared base (relation: unspecified).

How to fix

Fix or verify the `base_model` declaration so lineage checks can run.

  1. If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
  2. If you don't: identify the true parent (config architecture + weight shapes narrow it fast) and re-scan with that lineage in mind.

Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.

Fingerprint

The durable profile of this model: measured weights-and-metadata facts, rebuilt on every scan and battery run. Updated 2026-08-21.

architectureqwen3 · 36 layers · 2560-dim
parameters4025.1M
vocabulary151,936 tokens
licenseapache-2.0
serializationsafetensors custom code
chat templatepresent · sha256:a55ee1b1660128b7
claimed lineageQwen/Qwen3-4B
lineage verifiedconsistent vs Qwen/Qwen3-4B — embedding-row cosine 1.000
glitch-token surfaceclean no undertrained tokens
Full measured fingerprint
architecturesQwen3ForGuardModel
librarytransformers
pipelinefeature-extraction
repo files14
revision27a8f4e52e66
HF snapshot891 downloads · 25 likes · updated 2025-11-07 · captured 2026-08-21
embedding tensormodel.embed_tokens.weight · BF16 · 151,936×2560
embedding normsmedian 1.1254 · mean 1.0966
lineage checkconsistent — cosine 1 over 64 sampled rows vs Qwen/Qwen3-4B

Battery runs

The run trace behind the findings above: every deep-battery job for this model, with what each run measured or why it failed. Findings are only as good as the runs that produced them.

batterystatusqueueddurationattempts
weightscomplete2026-08-21 05:1351s1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, lineage-norm-correlation
embedding tensormodel.embed_tokens.weight · BF16 · 151,936×2560
glitch surface0 undertrained, 0 plain-ASCII
lineage checkconsistent — cosine 1 over 64 rows vs Qwen/Qwen3-4B

Verdict badge

Ship the verdict in your README — it always shows the latest published analysis:

Ingot verdict: warn

[![Ingot scan](https://ingot.tools/api/v1/models/Qwen/Qwen3Guard-Stream-4B/badge.svg)](https://ingot.tools/models/Qwen/Qwen3Guard-Stream-4B)
Gate it in CI