thoughtworks/cbd-gemma2-9b-100pair-refusal-v1 warn
claims base: google/gemma-2-9b-it · 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 2026-08-21256,000-token embedding scanned · 0 undertrained · lineage consistent |
| Behavioral battery | Live-inference differentials | not run |
Findings
Scanned 2026-08-21 · published from a community scan.
medium Chat template dropped vs parent
google/gemma-2-9b-it ships a chat template; this repo does not. Serving stacks will silently fall back to a generic template, changing behavior. (In our 296-model census, 78% of pure quantization re-releases changed or dropped the template.)
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.
info Embedding-norm glitch scan clean
No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (1.701). The glitch-token data-corruption class has no candidate surface in this model.
info Weights consistent with claimed parent google/gemma-2-9b-it
Mean cosine similarity of 64 sampled token-embedding rows against google/gemma-2-9b-it 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 | gemma2 · 42 layers · 3584-dim |
| parameters | 9241.7M |
| vocabulary | 256,000 tokens |
| license | gemma |
| serialization | safetensors pickle |
| chat template | none |
| claimed lineage | google/gemma-2-9b-it |
| lineage verified | consistent vs google/gemma-2-9b-it — embedding-row cosine 1.000 |
| glitch-token surface | clean no undertrained tokens |
Full measured fingerprint
| architectures | Gemma2ForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 19 — pickle: training_args.bin |
| revision | e08317fccdf3 |
| HF snapshot | 247 downloads · 0 likes · updated 2026-07-19 · captured 2026-08-21 |
| embedding tensor | model.embed_tokens.weight · BF16 · 256,000×3584 |
| embedding norms | median 1.7011 · mean 1.7216 |
| lineage check | consistent — cosine 0.9999 over 64 sampled rows vs google/gemma-2-9b-it |
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 05:16 | 2m | 1 |
weights run 2026-08-21 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | model.embed_tokens.weight · BF16 · 256,000×3584 |
| glitch surface | 0 undertrained, 0 plain-ASCII |
| lineage check | consistent — cosine 0.9999 over 64 rows vs google/gemma-2-9b-it |
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 thoughtworks/cbd-gemma2-9b-100pair-refusal-v1
Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/thoughtworks/cbd-gemma2-9b-100pair-refusal-v1)