Model page

mobilint/Qwen3-4B warn

downloads 567likes 0license apache-2.0arch mobilint-qwen3params 389.0Mupdated 2026-06-29

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 2026-08-21151,936-token embedding scanned · 0 undertrained · lineage inconsistent
Behavioral batteryLive-inference differentialsnot run

Findings

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

medium Repo ships executable Python (trust_remote_code)

The repository contains custom code files that run in-process when loaded with trust_remote_code=True. Pin the revision hash and review the code before loading.

How to fix

Review and pin the custom code; never float on `main` with trust_remote_code=True.

  1. Read every `.py` file in the repo before first load — this code runs in your process.
  2. Pin the revision: `from_pretrained(model_id, revision="<commit sha>", trust_remote_code=True)` so a later push can't swap the code under you.
  3. Prefer a version of the architecture already in `transformers` if one exists, which removes the remote-code requirement entirely.

info Embedding-norm glitch scan clean

No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (1.126). The glitch-token data-corruption class has no candidate surface in this model.

low Weights diverge from claimed parent Qwen/Qwen3-4B

This model declares Qwen/Qwen3-4B as its base (relation: unspecified), but mean cosine similarity of 64 sampled token-embedding rows against that parent is only 0.001 (true finetunes, merges, and quantizations sit above 0.8; independently trained weights sit near 0). Either the lineage label is wrong, or the model was so heavily re-trained, pruned, or distilled that the parent's properties (safety posture, evaluated behavior, licensing basis) should not be assumed to carry over. Verify provenance before relying on the parent's reputation.

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.

architecturemobilint-qwen3 · 36 layers · 2560-dim
parameters389.0M
vocabulary151,936 tokens
licenseapache-2.0
serializationsafetensors custom code
chat templatepresent · sha256:a55ee1b1660128b7
claimed lineageQwen/Qwen3-4B
lineage verifiedinconsistent vs Qwen/Qwen3-4B — embedding-row cosine 0.001
glitch-token surfaceclean no undertrained tokens
Full measured fingerprint
architecturesMobilintQwen3ForCausalLM
librarytransformers
pipelinetext-generation
repo files12
revisionb6f17025d76b
HF snapshot560 downloads · 0 likes · updated 2026-06-29 · captured 2026-08-21
embedding tensormodel.embed_tokens.weight · F32 · 151,936×2560
embedding normsmedian 1.1262 · mean 1.0974
lineage checkinconsistent — cosine 0.0009 over 64 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 05:146m1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, lineage-norm-correlation
embedding tensormodel.embed_tokens.weight · F32 · 151,936×2560
glitch surface0 undertrained, 0 plain-ASCII
lineage checkinconsistent — cosine 0.0009 over 64 rows vs Qwen/Qwen3-4B

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/mobilint/Qwen3-4B/badge.svg)](https://ingot.tools/models/mobilint/Qwen3-4B)
Gate it in CI