Model page

Qwen/Qwen3Guard-Gen-4B warn

The chat template differs from its base model, which changes behavior. Plus 1 minor note.

Could not load this model from the Hugging Face API (private, gated, or nonexistent). Findings below are from our archive.

Scan coverageStatic battery2026-08-21Weights battery2026-08-21Behavioral batterynot rundetails
BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-21
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-21151,936-token embedding scanned · 128 undertrained · lineage consistent
Behavioral batteryLive-inference differentialsnot run

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

Findings

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

medium Chat template differs from claimed parent

The chat template does not match Qwen/Qwen3-4B's. Template drift silently changes model behavior even when weights are identical — 37% of drifted derivatives in our census left it undisclosed. Diff the templates before deploying.

How to fixingot patch

Restore the parent's chat template in `tokenizer_config.json` — a pure metadata fix.

  1. Run `ingot patch <owner/model>` — the patch manifest carries the parent's template and applies it to a local copy's `tokenizer_config.json`.
  2. Or fix by hand: copy the `chat_template` value from the parent repo's `tokenizer_config.json` into this model's, and pin your serving stack to that file.
  3. If the drift was intentional (the author retrained on a new template), confirm that in the model card before "fixing" it — restoring the parent template on retrained weights changes behavior too.

low Undertrained tokens in vocabulary (non-ASCII tail)

Embedding-norm scan flagged 128 undertrained tokens (norm < 0.3× the vocabulary median), but 0 decode to plain-ASCII strings, so exposure in English-language pipelines is limited. Behavioral confirmation requires the behavioral battery.

How to fixruntime guardweight-level

Keep the affected token strings out of the model's input — the scan-derived runtime guard carries this model's exact blocklist.

  1. Fetch this model's guard artifact (`/api/v1/guard/<owner>/<model>`): the confirmed corrupting tokens and the low-norm candidate list, derived from the published scan.
  2. Screen inbound text with it (the `@ingotai/guard` package is a reference implementation) and route flagged records to a different model or human review — verbatim-copy tasks on flagged strings are the failure mode.
  3. The underlying cause is undertrained embeddings in the weights; a true fix is weight-level (continued pretraining on the affected tokens) — that is not a patch, it's a training job.

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.

Fix it

Some findings are metadata-level and patchable — apply the fixes to your local copy (your weights never leave your machine):

npx @ingotai/scan patch Qwen/Qwen3Guard-Gen-4B

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
parameters4411.4M
vocabulary151,936 tokens
licenseapache-2.0
serializationsafetensors
chat templatepresent · sha256:b4230b556815baa1
claimed lineageQwen/Qwen3-4B
lineage verifiedconsistent vs Qwen/Qwen3-4B — embedding-row cosine 1.000
glitch-token surface128 undertrained candidates, 0 plain-ASCII
Full measured fingerprint
architecturesQwen3ForCausalLM
librarytransformers
pipelinetext-generation
repo files13
revision6ec42827da0c
HF snapshot497.0k downloads · 53 likes · updated 2025-11-07 · captured 2026-08-21
embedding tensormodel.embed_tokens.weight · BF16 · 151,936×2560
embedding normsmedian 1.1258 · mean 1.0967
lineage checkconsistent — cosine 1 over 64 sampled rows vs Qwen/Qwen3-4B
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightscomplete2026-08-21 05:0858s1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, lineage-norm-correlation
embedding tensormodel.embed_tokens.weight · BF16 · 151,936×2560
glitch surface128 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-Gen-4B/badge.svg)](https://ingot.tools/models/Qwen/Qwen3Guard-Gen-4B)
Gate it in CI