nyu-visionx/Cambrian-S-7B pass
No major issues. Minor: a small glitch-token surface (non-English text only).
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 batteryn/adetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-21 |
| Weights battery | Weights forensics — no GPU, no download | complete 2026-08-21152,064-token embedding scanned · 7366 undertrained · lineage consistent |
| Behavioral battery | Live-inference differentials | n/anot applicable — image-to-text 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.
low Undertrained tokens in vocabulary (non-ASCII tail)
Embedding-norm scan flagged 7366 undertrained tokens (norm < 0.3× the vocabulary median), but 0 decode to plain-ASCII strings, so exposure in English-language pipelines is limited. 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/Qwen2.5-7B-Instruct
Mean cosine similarity of 64 sampled token-embedding rows against Qwen/Qwen2.5-7B-Instruct is 0.998 — 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 | cambrian_qwen · 28 layers · 3584-dim |
| parameters | 8030.3M |
| vocabulary | 152,064 tokens |
| license | apache-2.0 |
| serialization | safetensors |
| chat template | present · sha256:cd8e9439f0570856 |
| claimed lineage | Qwen/Qwen2.5-7B-Instruct |
| lineage verified | consistent vs Qwen/Qwen2.5-7B-Instruct — embedding-row cosine 0.998 |
| glitch-token surface | 7,366 undertrained candidates, 0 plain-ASCII |
Full measured fingerprint
| architectures | CambrianQwenForCausalLM |
| library | transformers |
| pipeline | image-to-text |
| repo files | 17 |
| revision | 556e72fded09 |
| HF snapshot | 1.7k downloads · 5 likes · updated 2025-11-07 · captured 2026-08-21 |
| embedding tensor | model.embed_tokens.weight · F32 · 152,064×3584 |
| embedding norms | median 0.8604 · mean 0.7921 |
| lineage check | consistent — cosine 0.9984 over 64 sampled rows vs Qwen/Qwen2.5-7B-Instruct |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-21 05:12 | 3m | 1 |
weights run 2026-08-21 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| probes skipped | token-decode: no tokenizer.json |
| embedding tensor | model.embed_tokens.weight · F32 · 152,064×3584 |
| glitch surface | 7,366 undertrained, 0 plain-ASCII |
| lineage check | consistent — cosine 0.9984 over 64 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/nyu-visionx/Cambrian-S-7B)