Model page

koalajun/Gemma-2-9b-it-Ko-Crypto-Translate warn

downloads 466likes 1license mitarch gemma2params 9241.7Mupdated 2024-10-03

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 →

BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-21
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-21256,002-token embedding scanned · 0 undertrained · lineage consistent
Behavioral batteryLive-inference differentialsnot run

Findings

Scanned 2026-08-21 · published from a community scan.

medium License differs from claimed parent (mit vs gemma)

This model declares mit while its claimed base google/gemma-2-9b-it declares gemma. Verify the re-license is permitted before commercial use.

How to fix

Verify the re-license is actually permitted before relying on it.

  1. 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.
  2. If the re-license is not permitted, the parent's terms govern your use regardless of what this repo declares.

medium Chat template differs from claimed parent

The chat template does not match google/gemma-2-9b-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.

  1. Run `ingot patch <owner/model>` — the patch manifest carries the parent's template and applies it to a local copy's `tokenizer_config.json`.
  2. 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.
  3. 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 Vocabulary size differs from claimed parent (256002 vs 256000)

A changed vocab means changed tokenization: strings will split differently than on google/gemma-2-9b-it, which can shift behavior on identifiers, codes, and non-English text.

How to fixweight-level

Not patchable: the vocab size mirrors the embedding matrix in the weights. Verify the change was intentional.

  1. Do not edit `vocab_size` in config.json to "match the parent" — it must equal the embedding table in the shipped weights or the model won't load.
  2. Diff the tokenizers (`tokenizer.json` / added_tokens) against the parent to see what was added or removed, and test your own identifiers, codes, and non-English text through both.
  3. If the drift is unexplained by the model card, treat tokenization-sensitive behavior as unvalidated on this model.

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.

  1. If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
  2. 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.

architecturegemma2 · 42 layers · 3584-dim
parameters9241.7M
vocabulary256,002 tokens
licensemit
serializationsafetensors
chat templatepresent · sha256:153280e3ff55d19d
claimed lineagegoogle/gemma-2-9b-it
lineage verifiedconsistent vs google/gemma-2-9b-it — embedding-row cosine 1.000
glitch-token surfaceclean no undertrained tokens
Full measured fingerprint
architecturesGemma2ForCausalLM
librarytransformers
pipelinetext-generation
repo files14
revision9870f802460a
HF snapshot506 downloads · 1 likes · updated 2024-10-03 · captured 2026-08-21
embedding tensormodel.embed_tokens.weight · F16 · 256,002×3584
embedding normsmedian 1.701 · mean 1.7215
lineage checkconsistent — cosine 1 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.

batterystatusqueueddurationattempts
weightscomplete2026-08-21 05:303m1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, lineage-norm-correlation
embedding tensormodel.embed_tokens.weight · F16 · 256,002×3584
glitch surface0 undertrained, 0 plain-ASCII
lineage checkconsistent — cosine 1 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 koalajun/Gemma-2-9b-it-Ko-Crypto-Translate

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:

Ingot verdict: warn

[![Ingot scan](https://ingot.tools/api/v1/models/koalajun/Gemma-2-9b-it-Ko-Crypto-Translate/badge.svg)](https://ingot.tools/models/koalajun/Gemma-2-9b-it-Ko-Crypto-Translate)
Gate it in CI