Bahushruth/Qwen3.6-35B-A3B-abliterated-v4 warn
The chat template was dropped from its base model, which changes behavior; glitch tokens that can silently corrupt ordinary input.
claims base: Qwen/Qwen3.6-35B-A3B · chat template: present · view on Hugging Face ↗
Scan coverageStatic battery2026-08-22Weights battery2026-08-22Behavioral batteryfaileddetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-22 |
| Weights battery | Weights forensics: no GPU, no download | complete 2026-08-22248,320-token embedding scanned · 1117 undertrained · lineage consistent |
| Behavioral battery | Live-inference differentials | failedTraceback (most recent call last): | raise HTTPStatusError(message, request=request, response=self) | httpx.HTTPStatusError: Client error '429 Too Many Requests' for url 'https://huggingface.co/api/models/Bahushruth/Qwen3.6-35B-A3B-abliterated-v4' | Traceback (most recent call last): | raise _format(HfHubHTTPError, message, response) from e | huggingface_hub.errors.HfHubHTTPError: (Request ID: Root=1-6a8e1645-05e24159311c58a7232233dc;069b9d8d-118f-47cf-80bf-8cba188164fa) |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-22 · published from a community scan.
medium Chat template dropped vs parent
Qwen/Qwen3.6-35B-A3B 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.
medium Undertrained (glitch) token surface in vocabulary
Embedding-norm scan flagged 1117 undertrained tokens (norm < 0.3× the vocabulary median of 0.567), including 341 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "tedothi", "ForCanBeConvertedToF", "ForCanBeConverted", "szexf", "Kinhted", "xfabl", "PostalCodesNL", "useRalative". 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.
info Weights consistent with claimed parent Qwen/Qwen3.6-35B-A3B
Mean cosine similarity of 64 sampled token-embedding rows against Qwen/Qwen3.6-35B-A3B is 1.000 — the weights plausibly descend from the declared base (relation: unspecified).
Check every checkpoint before it ships
Use the web app, API, CLI, or CI gate to scan candidate checkpoints and catch model drift before deployment. Public-model scans publish to the open database; paid plans add the volume needed for continuous checks.
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 Bahushruth/Qwen3.6-35B-A3B-abliterated-v4
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 2026-08-22.
| architecture | qwen3_5_moe_text · 40 layers · 2048-dim |
| parameters | 34660.6M |
| vocabulary | 248,320 tokens |
| license | apache-2.0 |
| serialization | safetensors |
| chat template | none |
| claimed lineage | Qwen/Qwen3.6-35B-A3B |
| lineage verified | consistent vs Qwen/Qwen3.6-35B-A3B — embedding-row cosine 1.000 |
| glitch-token surface | 1,117 undertrained candidates, 341 plain-ASCII |
Full measured fingerprint
| architectures | Qwen3_5MoeForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 10 |
| revision | 1c28f5014d7e |
| HF snapshot | 1.1M downloads · 8 likes · updated 2026-07-03 · captured 2026-08-21 |
| embedding tensor | model.language_model.embed_tokens.weight · BF16 · 248,320×2048 |
| embedding norms | median 0.5666 · mean 0.5547 |
| lineage check | consistent — cosine 0.9998 over 64 sampled rows vs Qwen/Qwen3.6-35B-A3B |
| glitch-token samples | "tedothi", "ForCanBeConvertedToF", "ForCanBeConverted", "szexf", "Kinhted", "xfabl", "PostalCodesNL", "useRalative", "tarsker", "useRal", "ejahter", "echslungs" |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-21 07:43 | 71s | 1 |
weights run 2026-08-21 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | model.language_model.embed_tokens.weight · BF16 · 248,320×2048 |
| glitch surface | 1,117 undertrained, 341 plain-ASCII |
| lineage check | consistent — cosine 0.9998 over 64 rows vs Qwen/Qwen3.6-35B-A3B |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/Bahushruth/Qwen3.6-35B-A3B-abliterated-v4)