Model page

Qwen/Qwen3-4B pass

downloads 4.9Mlikes 684license apache-2.0arch qwen3params 4022.5Mupdated 2025-07-26

claims base: Qwen/Qwen3-4B-Base · chat template: present · view on Hugging Face ↗

Ingot findings

Census parent model — see the derivative-drift report. Weights battery: embedding-norm scan over 151936 tokens (BF16, 2560-dim) found 0 undertrained candidates, 0 plain-ASCII. Lineage vs Qwen/Qwen3-4B-Base: consistent. Scanned 2026-08-20 (published from a community scan). Full write-up: read the report.

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.

How to fixruntime guardweight-level

Keep the affected token strings out of the model's input — the scan-derived runtime guard carries this model's exact blocklist.

  1. Fetch this model's guard artifact (`/api/v1/guard/<owner>/<model>`): the confirmed corrupting tokens and the low-norm candidate list, derived from the published scan.
  2. Screen inbound text with it (the `@ingotai/guard` package is a reference implementation) and route flagged records to a different model or human review — verbatim-copy tasks on flagged strings are the failure mode.
  3. The underlying cause is undertrained embeddings in the weights; a true fix is weight-level (continued pretraining on the affected tokens) — that is not a patch, it's a training job.

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

Mean cosine similarity of 64 sampled token-embedding rows against Qwen/Qwen3-4B-Base is 0.994 — 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 weights-and-metadata profile of this model, rebuilt on every scan and deep-battery run. Updated 2026-08-20.

architectureqwen3 · 36 layers · 2560-dim
parameters4022.5M
vocabulary151,936 tokens
licenseapache-2.0
serializationsafetensors
chat templatepresent · sha256:a55ee1b1660128b7
claimed lineageQwen/Qwen3-4B-Base
lineage verifiedconsistent vs Qwen/Qwen3-4B-Base — embedding-row cosine 0.994
glitch-token surfaceclean no undertrained tokens
Full fingerprint
architecturesQwen3ForCausalLM
librarytransformers
pipelinetext-generation
repo files13
revision1cfa9a720891
HF snapshot4.9M downloads · 684 likes · updated 2025-07-26 · captured 2026-08-20
embedding tensormodel.embed_tokens.weight · BF16 · 151,936×2560
embedding normsmedian 1.1262 · mean 1.0974
lineage checkconsistent — cosine 0.994 over 64 sampled rows vs Qwen/Qwen3-4B-Base

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