superwhisper/s1-mini warn
Its license differs from its base model's.
claims base: Qwen/Qwen3-0.6B · chat template: present · view on Hugging Face ↗
Scan coverageStatic battery2026-08-25Weights battery2026-08-25Behavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-25 |
| Weights battery | Weights forensics — no GPU, no download | complete 2026-08-25151,936-token embedding scanned · 0 undertrained · lineage consistent |
| Behavioral battery | Live-inference differentials | not run |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-25 · published from a community scan.
medium License differs from claimed parent (other vs apache-2.0)
This model declares other while its claimed base Qwen/Qwen3-0.6B declares apache-2.0. Verify the re-license is permitted before commercial use.
How to fix
Verify the re-license is actually permitted before relying on it.
- Read the parent's license for derivative-work and re-licensing terms — many open-weight licenses (e.g. Llama-family) do not permit arbitrary re-licensing.
- If the re-license is not permitted, the parent's terms govern your use regardless of what this repo declares.
info Embedding-norm glitch scan clean
No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (0.936). The glitch-token data-corruption class has no candidate surface in this model.
info Weights consistent with claimed parent Qwen/Qwen3-0.6B
Mean cosine similarity of 64 sampled token-embedding rows against Qwen/Qwen3-0.6B 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.
- 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.
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 2026-08-25.
| architecture | qwen3 · 28 layers · 1024-dim |
| parameters | 751.6M |
| vocabulary | 151,936 tokens |
| license | other |
| serialization | safetensors |
| chat template | present (chat_template.jinja) · sha256:a55ee1b1660128b7 |
| claimed lineage | Qwen/Qwen3-0.6B |
| lineage verified | consistent vs Qwen/Qwen3-0.6B — embedding-row cosine 1.000 |
| glitch-token surface | clean no undertrained tokens |
Full measured fingerprint
| architectures | Qwen3ForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 12 |
| revision | ae016a2cc6e4 |
| HF snapshot | 3.5k downloads · 237 likes · updated 2026-08-21 · captured 2026-08-25 |
| embedding tensor | model.embed_tokens.weight · BF16 · 151,936×1024 |
| embedding norms | median 0.9356 · mean 0.9251 |
| lineage check | consistent — cosine 1 over 64 sampled rows vs Qwen/Qwen3-0.6B |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-25 19:00 | 47s | 1 |
weights run 2026-08-25 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | model.embed_tokens.weight · BF16 · 151,936×1024 |
| glitch surface | 0 undertrained, 0 plain-ASCII |
| lineage check | consistent — cosine 1 over 64 rows vs Qwen/Qwen3-0.6B |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/superwhisper/s1-mini)