numind/NuExtract warn
Loading it runs custom code from the repo; the chat template differs from its base model, which changes behavior; glitch tokens that can silently corrupt ordinary input. Plus 1 minor note.
claims base: microsoft/Phi-3-mini-4k-instruct · chat template: present · view on Hugging Face ↗
Scan coverageStatic battery2026-08-21Weights battery2026-08-21Behavioral batteryfaileddetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-21 |
| Weights battery | Weights forensics: no GPU, no download | complete 2026-08-2132,064-token embedding scanned · 600 undertrained · lineage inconclusive |
| Behavioral battery | Live-inference differentials | failedTraceback (most recent call last): | RuntimeError: Task error: File reconstruction error: IO Error: No space left on device (os error 28) |
Ingot runs three batteries against a model. What each one checks →
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 Chat template differs from claimed parent
The chat template does not match microsoft/Phi-3-mini-4k-instruct'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.
- Run `ingot patch <owner/model>` — the patch manifest carries the parent's template and applies it to a local copy's `tokenizer_config.json`.
- 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.
- 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.
medium Undertrained (glitch) token surface in vocabulary
Embedding-norm scan flagged 600 undertrained tokens (norm < 0.3× the vocabulary median of 1.650), including 99 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "<0xFC>", "Mediabestanden", "<0xFB>", "autorytatywna", "<0xFF>", "<0xFD>", "<0xFA>", "<0xFE>". 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 microsoft/Phi-3-mini-4k-instruct inconclusive
Mean embedding-row cosine similarity to the declared base is 0.745 — 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.
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.
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 numind/NuExtract
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 | phi3 · 32 layers · 3072-dim |
| parameters | 3821.1M |
| vocabulary | 32,064 tokens |
| license | mit |
| serialization | safetensors custom code |
| chat template | present · sha256:268b6082ceb7176d |
| claimed lineage | microsoft/Phi-3-mini-4k-instruct |
| lineage verified | inconclusive vs microsoft/Phi-3-mini-4k-instruct — embedding-row cosine 0.745 |
| glitch-token surface | 600 undertrained candidates, 99 plain-ASCII |
Full measured fingerprint
| architectures | Phi3ForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 16 |
| revision | cc8190e34b19 |
| HF snapshot | 504 downloads · 236 likes · updated 2026-05-19 · captured 2026-08-21 |
| embedding tensor | model.embed_tokens.weight · F32 · 32,064×3072 |
| embedding norms | median 1.6499 · mean 1.5585 |
| lineage check | inconclusive — cosine 0.745 over 64 sampled rows vs microsoft/Phi-3-mini-4k-instruct |
| glitch-token samples | "<0xFC>", "Mediabestanden", "<0xFB>", "autorytatywna", "<0xFF>", "<0xFD>", "<0xFA>", "<0xFE>", "Webachiv", "regnigaste", "Genomsnitt", "Genomsnittlig" |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-21 05:30 | 45s | 1 |
weights run 2026-08-21 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | model.embed_tokens.weight · F32 · 32,064×3072 |
| glitch surface | 600 undertrained, 99 plain-ASCII |
| lineage check | inconclusive — cosine 0.745 over 64 rows vs microsoft/Phi-3-mini-4k-instruct |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/numind/NuExtract)