mergekit-community/Qwen3-7B-Instruct warn
No license declared — no usage rights by default; glitch tokens that can silently corrupt ordinary input. Plus 1 minor note.
claims base: Qwen/Qwen2.5-Coder-7B-Instruct, Qwen/Qwen2.5-7B-Instruct, Qwen/Qwen2.5-Math-7B-Instruct · chat template: present · view on Hugging Face ↗
Scan coverageStatic battery2026-08-27Weights battery2026-08-21Behavioral batterycompletedetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-27 |
| Weights battery | Weights forensics: no GPU, no download | complete 2026-08-21152,064-token embedding scanned · 8983 undertrained · lineage inconclusive |
| Behavioral battery | Live-inference differentials | completefull differential battery (curated) |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-27 · published from a community scan.
medium No license declared
The model card declares no license. You have no usage rights by default — treat as all-rights-reserved until the owner clarifies.
How to fix
Get a license from the owner or pick a licensed alternative — this is a legal gap, not a technical one.
- With no declared license you have no usage rights by default; treat the weights as all-rights-reserved.
- Open an issue or discussion on the repo asking the owner to declare a license, or use the licensed upstream/parent model instead.
medium Undertrained (glitch) token surface in vocabulary
Embedding-norm scan flagged 8983 undertrained tokens (norm < 0.3× the vocabulary median of 0.965), including 189 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "PostalCodesNL", "(stypy", "<unk>", "$PostalCodesNL", "TokenNameIdentifier", "Cumhurba", "wannonce", "NdrFc". In models where this class was tested behaviorally, such tokens silently rewrote user input into confident, schema-valid, wrong output. These are candidates from the weights alone; 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.
- 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.
- 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.
- 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.
low Lineage vs claimed parent Qwen/Qwen2.5-Coder-7B-Instruct inconclusive
Mean embedding-row cosine similarity to the declared base is 0.634 — below the 0.8 typical of true derivatives but not low enough to call mislabeled. Heavy continued pretraining or vocabulary surgery can look like this; verify provenance before relying on the parent's safety or licensing posture.
How to fix
Fix or verify the `base_model` declaration so lineage checks can run.
- If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
- If you don't: identify the true parent (config architecture + weight shapes narrow it fast) and re-scan with that lineage in mind.
info Glitch-token echo probe clean
The model repeated 0/16 low-norm candidate tokens verbatim (controls 0/8). No behavioral glitch-token differential at this threshold.
Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.
Check every checkpoint before it ships
Use the web app, API, CLI, or CI gate to scan candidate checkpoints and catch model drift before deployment. Public-model scans publish to the open database; paid plans add the volume needed for continuous checks.
Fingerprint
The durable profile of this model: measured weights-and-metadata facts, rebuilt on every scan and battery run. Updated 2026-08-21.
| architecture | qwen2 · 28 layers · 3584-dim |
| parameters | 7615.6M |
| vocabulary | 152,064 tokens |
| license | none declared |
| serialization | safetensors |
| chat template | present · sha256:cd8e9439f0570856 |
| claimed lineage | Qwen/Qwen2.5-Coder-7B-Instruct, Qwen/Qwen2.5-7B-Instruct, Qwen/Qwen2.5-Math-7B-Instruct |
| lineage verified | inconclusive vs Qwen/Qwen2.5-Coder-7B-Instruct — embedding-row cosine 0.633 |
| glitch-token surface | 8,983 undertrained candidates, 189 plain-ASCII |
Full measured fingerprint
| architectures | Qwen2ForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 15 |
| revision | 56adc8972416 |
| HF snapshot | 332 downloads · 2 likes · updated 2025-02-23 · captured 2026-08-21 |
| embedding tensor | model.embed_tokens.weight · F16 · 152,064×3584 |
| embedding norms | median 0.965 · mean 0.8848 |
| lineage check | inconclusive — cosine 0.6335 over 64 sampled rows vs Qwen/Qwen2.5-Coder-7B-Instruct |
| glitch-token samples | "PostalCodesNL", "(stypy", "<unk>", "$PostalCodesNL", "TokenNameIdentifier", "Cumhurba", "wannonce", "NdrFc", "prostituerte", "thuisontvangst", "aincontri", "bakeka" |
Battery runs (2)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| gpu | complete | 2026-08-27 04:31 | 2m | 1 |
| weights | complete | 2026-08-21 05:15 | 2m | 1 |
gpu run 2026-08-27 — measurements
| probes run | glitch |
weights run 2026-08-21 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | model.embed_tokens.weight · F16 · 152,064×3584 |
| glitch surface | 8,983 undertrained, 189 plain-ASCII |
| lineage check | inconclusive — cosine 0.6335 over 64 rows vs Qwen/Qwen2.5-Coder-7B-Instruct |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/mergekit-community/Qwen3-7B-Instruct)