twnlp/ChineseErrorCorrector3-4B warn
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 →
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-21 |
| Weights battery | Weights forensics — no GPU, no download | complete 2026-08-21151,936-token embedding scanned · 0 undertrained · lineage consistent |
| Behavioral battery | Live-inference differentials | not 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.
- Read every `.py` file in the repo before first load — this code runs in your process.
- 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.
- Prefer a version of the architecture already in `transformers` if one exists, which removes the remote-code requirement entirely.
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.
- Run `ingot patch <owner/model>` — the patch manifest carries the parent's template and applies it to a local copy's `tokenizer_config.json`.
- 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.
- 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 (1.135). 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 64 sampled token-embedding rows against Qwen/Qwen3-4B is 0.975 — 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.
- If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
- 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.
| architecture | qwen3 · 36 layers · 2560-dim |
| parameters | 4022.5M |
| vocabulary | 151,936 tokens |
| license | apache-2.0 |
| serialization | safetensors custom code |
| chat template | none |
| claimed lineage | Qwen/Qwen3-4B |
| lineage verified | consistent vs Qwen/Qwen3-4B — embedding-row cosine 0.975 |
| glitch-token surface | clean no undertrained tokens |
Full measured fingerprint
| architectures | Qwen3ForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 15 |
| revision | e6d757fa285d |
| HF snapshot | 511 downloads · 19 likes · updated 2026-06-03 · captured 2026-08-21 |
| embedding tensor | model.embed_tokens.weight · BF16 · 151,936×2560 |
| embedding norms | median 1.1353 · mean 1.1097 |
| lineage check | consistent — cosine 0.9746 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.
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-21 05:30 | 69s | 1 |
weights run 2026-08-21 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | model.embed_tokens.weight · BF16 · 151,936×2560 |
| glitch surface | 0 undertrained, 0 plain-ASCII |
| lineage check | consistent — cosine 0.9746 over 64 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 twnlp/ChineseErrorCorrector3-4B
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:
[](https://ingot.tools/models/twnlp/ChineseErrorCorrector3-4B)