Goedel-LM/Goedel-Prover-V2-8B warn
Loading it runs custom code from the repo; glitch tokens that can silently corrupt ordinary input.
Could not load this model from the Hugging Face API (private, gated, or nonexistent). Findings below are from our archive.
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 2026-08-21151,936-token embedding scanned · 3002 undertrained · lineage consistent |
| Behavioral battery | Live-inference differentials | not run |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-21 · 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 3002 undertrained tokens (norm < 0.3× the vocabulary median of 1.452), including 102 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "$PostalCodesNL", "ForCanBeConvertedToF", "PostalCodesNL", "ForCanBeConverted", "useRalative", "thuisontvangst", "useRal", "sexkontakte". 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/Qwen3-8B
Mean cosine similarity of 64 sampled token-embedding rows against Qwen/Qwen3-8B is 1.000 — 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 · 4096-dim |
| parameters | 8190.7M |
| vocabulary | 151,936 tokens |
| license | apache-2.0 |
| serialization | safetensors custom code |
| chat template | present · sha256:a55ee1b1660128b7 |
| claimed lineage | Qwen/Qwen3-8B |
| lineage verified | consistent vs Qwen/Qwen3-8B — embedding-row cosine 1.000 |
| glitch-token surface | 3,002 undertrained candidates, 102 plain-ASCII |
Full measured fingerprint
| architectures | Qwen3ForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 17 |
| revision | dfd02e6271a5 |
| HF snapshot | 7.6k downloads · 27 likes · updated 2025-08-09 · captured 2026-08-21 |
| embedding tensor | model.embed_tokens.weight · BF16 · 151,936×4096 |
| embedding norms | median 1.4516 · mean 1.3765 |
| lineage check | consistent — cosine 0.9996 over 64 sampled rows vs Qwen/Qwen3-8B |
| glitch-token samples | "$PostalCodesNL", "ForCanBeConvertedToF", "PostalCodesNL", "ForCanBeConverted", "useRalative", "thuisontvangst", "useRal", "sexkontakte", "NdrFc", "webElementX", "sextreffen", "wannonce" |
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 | 2m | 1 |
weights run 2026-08-21 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | model.embed_tokens.weight · BF16 · 151,936×4096 |
| glitch surface | 3,002 undertrained, 102 plain-ASCII |
| lineage check | consistent — cosine 0.9996 over 64 rows vs Qwen/Qwen3-8B |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/Goedel-LM/Goedel-Prover-V2-8B)