FastFlowLM/Gemma3-4B-NPU2 warn
The chat template differs from its base model, which changes behavior.
claims base: google/gemma-3-4b-it · chat template: present · view on Hugging Face ↗
Scan coverageStatic battery2026-08-22Weights batteryn/aBehavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-22 |
| Weights battery | Weights forensics: no GPU, no download | n/arepo ships no scannable weights (no safetensors and no pickle checkpoints — GGUF/CoreML/other formats) |
| Behavioral battery | Live-inference differentials | not run |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-22 · published from a community scan.
medium Chat template differs from claimed parent
The chat template does not match google/gemma-3-4b-it'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.
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 FastFlowLM/Gemma3-4B-NPU2
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 2026-08-22.
| architecture | gemma3_text · 34 layers · 2560-dim |
| vocabulary | 262,208 tokens |
| license | gemma |
| serialization | no safetensors |
| chat template | present · sha256:c50e5c571cdf0fcf |
| claimed lineage | google/gemma-3-4b-it |
| lineage verified | unverified — weights battery pending |
Full measured fingerprint
| library | transformers |
| repo files | 14 |
| revision | a5ad9dbc7bdf |
| HF snapshot | 359 downloads · 0 likes · updated 2026-08-04 · captured 2026-08-21 |
| weights battery | token-embedding scan n/a — repo ships no scannable weights (no safetensors and no pickle checkpoints — GGUF/CoreML/other formats) |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-21 05:32 | 0s | 1 |
weights run 2026-08-21 — measurements
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/FastFlowLM/Gemma3-4B-NPU2)