zeroentropy/zerank-1-small-reranker warn
Loading it runs custom code from the repo; glitch tokens that can silently corrupt ordinary input; the weights don't match the model it claims to be based on.
claims base: Qwen/Qwen3-4B · chat template: present · view on Hugging Face ↗
Scan coverageStatic battery2026-08-21Weights battery2026-08-21Behavioral batteryn/adetails
| 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 · 3109 undertrained · lineage inconsistent |
| Behavioral battery | Live-inference differentials | n/anot applicable — text-ranking model has no text-generation surface to probe |
Ingot runs three batteries against a model. What each one checks →
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 Undertrained (glitch) token surface in vocabulary
Embedding-norm scan flagged 3109 undertrained tokens (norm < 0.3× the vocabulary median of 1.581), including 21 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "useRalative", "<unk>", "PostalCodesNL", "ForCanBeConverted", "ForCanBeConvertedToF", "useRal", "$PostalCodesNL", "thuisontvangst". In models where this class was tested behaviorally, such tokens silently rewrote user input into confident, schema-valid, wrong output. These are candidates from the weights alone; behavioral confirmation requires the behavioral battery.
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.
- 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.
- 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.
- 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.
medium Weights inconsistent with claimed parent Qwen/Qwen3-4B
This model declares Qwen/Qwen3-4B as its base (relation: unspecified), but its token-embedding geometry is incompatible: 2048-dim embeddings vs the parent's 2560-dim. A finetune cannot change embedding width — the lineage label is wrong or misleading. Treat provenance claims on this repo (training data, safety posture, licensing) as unverified.
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 · 28 layers · 2048-dim |
| parameters | 1720.6M |
| vocabulary | 151,936 tokens |
| license | apache-2.0 |
| serialization | safetensors custom code |
| chat template | present · sha256:a55ee1b1660128b7 |
| claimed lineage | Qwen/Qwen3-4B |
| lineage verified | inconsistent vs Qwen/Qwen3-4B |
| glitch-token surface | 3,109 undertrained candidates, 21 plain-ASCII |
Full measured fingerprint
| architectures | Qwen3ForCausalLM |
| library | sentence-transformers |
| pipeline | text-ranking |
| repo files | 13 |
| revision | a65fd51c450e |
| HF snapshot | 6.8k downloads · 66 likes · updated 2026-07-24 · captured 2026-08-21 |
| embedding tensor | model.embed_tokens.weight · BF16 · 151,936×2048 |
| embedding norms | median 1.5807 · mean 1.5394 |
| lineage check | inconsistent — cosine undefined over undefined sampled rows vs Qwen/Qwen3-4B |
| glitch-token samples | "useRalative", "<unk>", "PostalCodesNL", "ForCanBeConverted", "ForCanBeConvertedToF", "useRal", "$PostalCodesNL", "thuisontvangst", "NdrFc", "sexdate", "wannonce", "davidjl" |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-21 05:10 | 49s | 1 |
weights run 2026-08-21 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | model.embed_tokens.weight · BF16 · 151,936×2048 |
| glitch surface | 3,109 undertrained, 21 plain-ASCII |
| lineage check | inconsistent — cosine undefined over undefined rows vs Qwen/Qwen3-4B |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/zeroentropy/zerank-1-small-reranker)