OBLITERATUS/Qwen3.8-27B-OBLITERATED warn
The chat template differs from its base model, which changes behavior.
claims base: Qwen/Qwen3.8-27B · chat template: present · view on Hugging Face ↗
Scan coverageStatic battery2026-08-25Weights battery2026-08-25Behavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-25 |
| Weights battery | Weights forensics — no GPU, no download | complete 2026-08-25248,320-token embedding scanned · 1620 undertrained · lineage consistent |
| Behavioral battery | Live-inference differentials | not run |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-25 · published from a community scan.
medium Chat template differs from claimed parent
The chat template does not match Qwen/Qwen3.8-27B's. Template drift silently changes model behavior even when weights are identical — 37% of drifted derivatives in our census left it undisclosed. Diff the templates before deploying.
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.
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 OBLITERATUS/Qwen3.8-27B-OBLITERATED
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 2026-08-25.
| architecture | qwen3_5 |
| parameters | 27781.4M |
| vocabulary | 248,320 tokens |
| license | apache-2.0 |
| serialization | safetensors + gguf |
| chat template | present (chat_template.jinja) · sha256:4c2b3eabcdd87d5f |
| claimed lineage | Qwen/Qwen3.8-27B |
| lineage verified | consistent vs Qwen/Qwen3.8-27B — embedding-row cosine 1.000 |
| glitch-token surface | 1,620 undertrained candidates, 410 plain-ASCII |
Full measured fingerprint
| architectures | Qwen3_5ForConditionalGeneration |
| library | mlx |
| pipeline | text-generation |
| repo files | 70 |
| revision | a58c3b53b3ce |
| HF snapshot | 389.7k downloads · 742 likes · updated 2026-08-24 · captured 2026-08-25 |
| embedding tensor | model.language_model.embed_tokens.weight · BF16 · 248,320×5120 |
| embedding norms | median 0.9288 · mean 0.8991 |
| lineage check | consistent — cosine 1 over 64 sampled rows vs Qwen/Qwen3.8-27B |
| glitch-token samples | "szexf", "tedothi", "ForCanBeConvertedToF", "ForCanBeConverted", "Kinhted", "tarsker", "PostalCodesNL", "useRalative", "ejahter", "tarskereso", "useRal", "Purtro" |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-25 19:00 | 3m | 1 |
weights run 2026-08-25 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | model.language_model.embed_tokens.weight · BF16 · 248,320×5120 |
| glitch surface | 1,620 undertrained, 410 plain-ASCII |
| lineage check | consistent — cosine 1 over 64 rows vs Qwen/Qwen3.8-27B |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/OBLITERATUS/Qwen3.8-27B-OBLITERATED)