Model page

sarvamai/sarvam-translate warn

Its license differs from its base model's; the chat template was dropped from its base model, which changes behavior.

Could not load this model from the Hugging Face API (private, gated, or nonexistent). Findings below are from our archive.

Scan coverageStatic battery2026-08-21Weights battery2026-08-21Behavioral batterynot rundetails
BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-21
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-21262,208-token embedding scanned · 0 undertrained · lineage consistent
Behavioral batteryLive-inference differentialsnot run

Ingot runs three batteries against a model. What each one checks →

Findings

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

medium License differs from claimed parent (gpl-3.0 vs gemma)

This model declares gpl-3.0 while its claimed base google/gemma-3-4b-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 dropped vs parent

google/gemma-3-4b-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.

  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.

info Embedding-norm glitch scan clean

No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (0.943). The glitch-token data-corruption class has no candidate surface in this model.

info Weights consistent with claimed parent google/gemma-3-4b-it

Mean cosine similarity of 64 sampled token-embedding rows against google/gemma-3-4b-it is 0.940 — 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.

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 sarvamai/sarvam-translate

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
parameters4300.1M
vocabulary262,208 tokens
licensegpl-3.0
serializationsafetensors
chat templatenone
claimed lineagegoogle/gemma-3-4b-it
lineage verifiedconsistent vs google/gemma-3-4b-it — embedding-row cosine 0.940
glitch-token surfaceclean no undertrained tokens
Full measured fingerprint
architecturesGemma3ForConditionalGeneration
librarytransformers
pipelinetranslation
repo files16
revisione0a7a6bc2166
HF snapshot36.1k downloads · 154 likes · updated 2026-07-13 · captured 2026-08-21
embedding tensorlanguage_model.model.embed_tokens.weight · BF16 · 262,208×2560
embedding normsmedian 0.9425 · mean 0.9519
lineage checkconsistent — cosine 0.9403 over 64 sampled rows vs google/gemma-3-4b-it
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightscomplete2026-08-21 05:1074s1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, lineage-norm-correlation
embedding tensorlanguage_model.model.embed_tokens.weight · BF16 · 262,208×2560
glitch surface0 undertrained, 0 plain-ASCII
lineage checkconsistent — cosine 0.9403 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: warn

[![Ingot scan](https://ingot.tools/api/v1/models/sarvamai/sarvam-translate/badge.svg)](https://ingot.tools/models/sarvamai/sarvam-translate)
Gate it in CI