pavelslab-nyu/Llama-3.2-3B-ThinkSFT warn
Loading it runs custom code from the repo.
claims base: meta-llama/Llama-3.2-3B-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 2026-08-21128,256-token embedding scanned · 0 undertrained |
| 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.
info Embedding-norm glitch scan clean
No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (1.151). The glitch-token data-corruption class has no candidate surface in this model.
Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.
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.
Fingerprint
The durable profile of this model: measured weights-and-metadata facts, rebuilt on every scan and battery run. Updated 2026-08-21.
| architecture | llama · 28 layers · 3072-dim |
| parameters | 3212.7M |
| vocabulary | 128,256 tokens |
| license | llama3.2 |
| serialization | safetensors pickle custom code |
| chat template | none |
| claimed lineage | meta-llama/Llama-3.2-3B-Instruct |
| lineage verified | unverified — weights battery pending |
| glitch-token surface | clean no undertrained tokens |
Full measured fingerprint
| architectures | LlamaForCausalLM |
| repo files | 18 — pickle: rng_state_0.pth, rng_state_1.pth, rng_state_2.pth, rng_state_3.pth, scheduler.pt |
| revision | 1b8575bde916 |
| HF snapshot | 513 downloads · 0 likes · updated 2026-04-20 · captured 2026-08-21 |
| embedding tensor | model.embed_tokens.weight · BF16 · 128,256×3072 |
| embedding norms | median 1.1512 · mean 1.1466 |
| lineage check | parent weights unreadable (403 Forbidden for https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/resolve/main/model.safetensors.index.json (gated repo — the HF_TOKEN account has not accepted this repo's license, or the token lacks gated-repo read scope)) |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-21 05:30 | 48s | 1 |
weights run 2026-08-21 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | model.embed_tokens.weight · BF16 · 128,256×3072 |
| glitch surface | 0 undertrained, 0 plain-ASCII |
| lineage check | not checked (parent weights unreadable (403 Forbidden for https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/resolve/main/model.safetensors.index.json (gated repo — the HF_TOKEN account has not accepted this repo's license, or the token lacks gated-repo read scope))) |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/pavelslab-nyu/Llama-3.2-3B-ThinkSFT)