Model page

alphaedge-ai/gemma-3-4b-it-mya-16384 pass

downloads 226likes 1license gemmaarch gemma3params 3670.8Mupdated 2026-05-20

claims base: google/gemma-3-4b-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 2026-08-2116,384-token embedding scanned · 0 undertrained · lineage inconclusive
Behavioral batteryLive-inference differentialsnot run

Findings

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

info Embedding-norm glitch scan clean

No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (1.007). The glitch-token data-corruption class has no candidate surface in this model.

low Lineage vs claimed parent google/gemma-3-4b-it inconclusive

Mean embedding-row cosine similarity to the declared base is 0.411 — 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.

  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.

architecturegemma3
parameters3670.8M
vocabulary16,384 tokens
licensegemma
serializationsafetensors
chat templatepresent · sha256:7de1c58e208eda46
claimed lineagegoogle/gemma-3-4b-it
lineage verifiedinconclusive vs google/gemma-3-4b-it — embedding-row cosine 0.411
glitch-token surfaceclean no undertrained tokens
Full measured fingerprint
architecturesGemma3ForConditionalGeneration
librarytransformers
pipelinetext-generation
repo files12
revision3edb3600a3cc
HF snapshot237 downloads · 1 likes · updated 2026-05-20 · captured 2026-08-21
embedding tensorlanguage_model.model.embed_tokens.weight · BF16 · 16,384×2560
embedding normsmedian 1.007 · mean 1.0071
lineage checkinconclusive — cosine 0.4107 over 64 sampled rows vs google/gemma-3-4b-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 05:1630s1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, lineage-norm-correlation
embedding tensorlanguage_model.model.embed_tokens.weight · BF16 · 16,384×2560
glitch surface0 undertrained, 0 plain-ASCII
lineage checkinconclusive — cosine 0.4107 over 64 rows vs google/gemma-3-4b-it

Verdict badge

Ship the verdict in your README — it always shows the latest published analysis:

Ingot verdict: pass

[![Ingot scan](https://ingot.tools/api/v1/models/alphaedge-ai/gemma-3-4b-it-mya-16384/badge.svg)](https://ingot.tools/models/alphaedge-ai/gemma-3-4b-it-mya-16384)
Gate it in CI