oneonlee/llama-3.1-nemoguard-8b-content-safety-merged warn
claims base: meta-llama/Llama-3.1-8B-Instruct, nvidia/llama-3.1-nemoguard-8b-content-safety · chat template: present · view on Hugging Face ↗
Scan coverage
Ingot runs three batteries against a model. What each one checks →
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-21 |
| Weights battery | Weights forensics — no GPU, no download | complete 2026-08-21128,256-token embedding scanned · 497 undertrained · lineage consistent |
| Behavioral battery | Live-inference differentials | not run |
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.
- Read every `.py` file in the repo before first load — this code runs in your process.
- 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.
- Prefer a version of the architecture already in `transformers` if one exists, which removes the remote-code requirement entirely.
medium Undertrained (glitch) token surface in vocabulary
Embedding-norm scan flagged 497 undertrained tokens (norm < 0.3× the vocabulary median of 0.685), including 140 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "ilmektedir", "$PostalCodesNL", "ForCanBeConvertedToF", "TokenNameIdentifier", "CLIIIK", "useRalative", "PostalCodesNL", "_ComCallableWrapper". 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.
info Weights consistent with claimed parent meta-llama/Llama-3.1-8B-Instruct
Mean cosine similarity of 64 sampled token-embedding rows against meta-llama/Llama-3.1-8B-Instruct 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 2026-08-21.
| architecture | llama · 32 layers · 4096-dim |
| parameters | 8030.3M |
| vocabulary | 128,256 tokens |
| license | llama3.1 |
| serialization | safetensors custom code |
| chat template | present · sha256:e10ca381b1ccc5cf |
| claimed lineage | meta-llama/Llama-3.1-8B-Instruct, nvidia/llama-3.1-nemoguard-8b-content-safety |
| lineage verified | consistent vs meta-llama/Llama-3.1-8B-Instruct — embedding-row cosine 1.000 |
| glitch-token surface | 497 undertrained candidates, 140 plain-ASCII |
Full measured fingerprint
| architectures | LlamaForCausalLM |
| repo files | 13 |
| revision | 390e05cccf2d |
| HF snapshot | 315 downloads · 0 likes · updated 2025-08-13 · captured 2026-08-21 |
| embedding tensor | model.embed_tokens.weight · F16 · 128,256×4096 |
| embedding norms | median 0.6849 · mean 0.6713 |
| lineage check | consistent — cosine 1 over 64 sampled rows vs meta-llama/Llama-3.1-8B-Instruct |
| glitch-token samples | "ilmektedir", "$PostalCodesNL", "ForCanBeConvertedToF", "TokenNameIdentifier", "CLIIIK", "useRalative", "PostalCodesNL", "_ComCallableWrapper", "ForCanBeConverted", "krvldkf", "sahuje", "webElementXpaths" |
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.
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-21 05:15 | 2m | 1 |
weights run 2026-08-21 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | model.embed_tokens.weight · F16 · 128,256×4096 |
| glitch surface | 497 undertrained, 140 plain-ASCII |
| lineage check | consistent — cosine 1 over 64 rows vs meta-llama/Llama-3.1-8B-Instruct |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/oneonlee/llama-3.1-nemoguard-8b-content-safety-merged)