HKUSTAudio/Llasa-3B warn
Its license differs from its base model's.
claims base: meta-llama/Llama-3.2-3B-Instruct · chat template: not found · view on Hugging Face ↗
Scan coverageStatic battery2026-08-21Weights battery2026-08-21Behavioral batteryn/adetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-21 |
| Weights battery | Weights forensics: no GPU, no download | complete 2026-08-21193,800-token embedding scanned · 0 undertrained |
| Behavioral battery | Live-inference differentials | n/anot applicable: text-to-speech model has no text-generation surface to probe |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-21 · published from a community scan.
medium License differs from claimed parent (cc-by-nc-4.0 vs llama3.2)
This model declares cc-by-nc-4.0 while its claimed base meta-llama/Llama-3.2-3B-Instruct declares llama3.2. 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 (0.997). The glitch-token data-corruption class has no candidate surface in this model.
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 | llama · 28 layers · 3072-dim |
| parameters | 4009.5M |
| vocabulary | 193,800 tokens |
| license | cc-by-nc-4.0 |
| serialization | safetensors |
| chat template | none |
| claimed lineage | meta-llama/Llama-3.2-3B-Instruct |
| lineage verified | unverified — weights battery pending |
| glitch-token surface | clean no undertrained tokens |
Full measured fingerprint
| architectures | LlamaForCausalLM |
| pipeline | text-to-speech |
| repo files | 13 |
| revision | 740b08c956fd |
| HF snapshot | 770 downloads · 530 likes · updated 2025-05-10 · captured 2026-08-21 |
| embedding tensor | model.embed_tokens.weight · BF16 · 193,800×3072 |
| embedding norms | median 0.9974 · mean 0.891 |
| lineage check | parent weights unreadable (403 Forbidden for https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/resolve/main/model.safetensors.index.json (gated repo — the HF_TOKEN account has not accepted this repo's license, or the token lacks gated-repo read scope)) |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-21 05:13 | 59s | 1 |
weights run 2026-08-21 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | model.embed_tokens.weight · BF16 · 193,800×3072 |
| glitch surface | 0 undertrained, 0 plain-ASCII |
| lineage check | not checked (parent weights unreadable (403 Forbidden for https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/resolve/main/model.safetensors.index.json (gated repo — the HF_TOKEN account has not accepted this repo's license, or the token lacks gated-repo read scope))) |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/HKUSTAudio/Llasa-3B)