llamafactory/tiny-random-qwen2.5 warn
Glitch tokens that can silently corrupt ordinary input; the weights don't match the model it claims to be based on.
claims base: Qwen/Qwen2.5-7B-Instruct · chat template: present · view on Hugging Face ↗
Scan coverageStatic battery2026-08-21Weights battery2026-08-21Behavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-21 |
| Weights battery | Weights forensics — no GPU, no download | complete 2026-08-21152,064-token embedding scanned · 7210 undertrained · lineage inconsistent |
| Behavioral battery | Live-inference differentials | not run |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-21 · published from a community scan.
medium Undertrained (glitch) token surface in vocabulary
Embedding-norm scan flagged 7210 undertrained tokens (norm < 0.3× the vocabulary median of 0.054), including 189 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "TokenNameIdentifier", "ForCanBeConverted", "ForCanBeConvertedToF", "PostalCodesNL", "$PostalCodesNL", "<unk>", "(stypy", "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/Qwen2.5-7B-Instruct
This model declares Qwen/Qwen2.5-7B-Instruct as its base (relation: unspecified), but its token-embedding geometry is incompatible: 16-dim embeddings vs the parent's 3584-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 | qwen2 · 2 layers · 16-dim |
| parameters | 4.9M |
| vocabulary | 152,064 tokens |
| license | apache-2.0 |
| serialization | safetensors |
| chat template | present · sha256:cd8e9439f0570856 |
| claimed lineage | Qwen/Qwen2.5-7B-Instruct |
| lineage verified | inconsistent vs Qwen/Qwen2.5-7B-Instruct |
| glitch-token surface | 7,210 undertrained candidates, 189 plain-ASCII |
Full measured fingerprint
| architectures | Qwen2ForCausalLM |
| pipeline | text-generation |
| repo files | 9 |
| revision | af5f49df7661 |
| HF snapshot | 1.9k downloads · 0 likes · updated 2025-10-15 · captured 2026-08-21 |
| embedding tensor | model.embed_tokens.weight · BF16 · 152,064×16 |
| embedding norms | median 0.0538 · mean 0.0518 |
| lineage check | inconsistent — cosine undefined over undefined sampled rows vs Qwen/Qwen2.5-7B-Instruct |
| glitch-token samples | "TokenNameIdentifier", "ForCanBeConverted", "ForCanBeConvertedToF", "PostalCodesNL", "$PostalCodesNL", "<unk>", "(stypy", "thuisontvangst", "useRalative", "useRal", "prostituerte", "Cumhurba" |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-21 05:11 | 17s | 1 |
weights run 2026-08-21 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | model.embed_tokens.weight · BF16 · 152,064×16 |
| glitch surface | 7,210 undertrained, 189 plain-ASCII |
| lineage check | inconsistent — cosine undefined over undefined rows vs Qwen/Qwen2.5-7B-Instruct |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/llamafactory/tiny-random-qwen2.5)