Model page

NeuronUz/NeuronAI-Uzbek warn

downloads 274likes 7license apache-2.0arch qwen3params 4094.3Mupdated 2026-01-21

claims base: Qwen/Qwen3-4B · 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 2026-08-21180,000-token embedding scanned · 0 undertrained · lineage consistent
Behavioral batteryLive-inference differentialsnot run

Findings

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

medium Chat template dropped vs parent

Qwen/Qwen3-4B 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.

medium Vocabulary size differs from claimed parent (180000 vs 151936)

A changed vocab means changed tokenization: strings will split differently than on Qwen/Qwen3-4B, 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 (1.150). The glitch-token data-corruption class has no candidate surface in this model.

info Weights consistent with claimed parent Qwen/Qwen3-4B

Mean cosine similarity of 54 sampled token-embedding rows against Qwen/Qwen3-4B is 0.999 — 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.

architectureqwen3 · 36 layers · 2560-dim
parameters4094.3M
vocabulary180,000 tokens
licenseapache-2.0
serializationsafetensors pickle
chat templatenone
claimed lineageQwen/Qwen3-4B
lineage verifiedconsistent vs Qwen/Qwen3-4B — embedding-row cosine 0.999
glitch-token surfaceclean no undertrained tokens
Full measured fingerprint
architecturesQwen3ForCausalLM
pipelinetext-generation
repo files17 — pickle: training_args.bin
revisione53811493580
HF snapshot252 downloads · 7 likes · updated 2026-01-21 · captured 2026-08-21
embedding tensormodel.embed_tokens.weight · BF16 · 180,000×2560
embedding normsmedian 1.15 · mean 1.1897
lineage checkconsistent — cosine 0.9992 over 54 sampled rows vs Qwen/Qwen3-4B

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 05:1679s1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, lineage-norm-correlation
embedding tensormodel.embed_tokens.weight · BF16 · 180,000×2560
glitch surface0 undertrained, 0 plain-ASCII
lineage checkconsistent — cosine 0.9992 over 54 rows vs Qwen/Qwen3-4B

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 NeuronUz/NeuronAI-Uzbek

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/NeuronUz/NeuronAI-Uzbek/badge.svg)](https://ingot.tools/models/NeuronUz/NeuronAI-Uzbek)
Gate it in CI