AIFunOver/Llama-3.2-3B-Instruct-openvino-4bit warn
Weights only ship in a format that can run code when loaded.
claims base: meta-llama/Llama-3.2-3B-Instruct · chat template: present · view on Hugging Face ↗
Scan coverageStatic battery2026-08-25Weights batteryfailedBehavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-25 |
| Weights battery | Weights forensics: no GPU, no download | failed429 Too Many Requests for https://huggingface.co/api/models/AIFunOver/Llama-3.2-3B-Instruct-openvino-4bit |
| 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 Pickle-serialized weights, no safetensors
Weights ship only as pickle-based files (openvino_detokenizer.bin, openvino_model.bin, openvino_tokenizer.bin). Loading pickle executes arbitrary code from the file — prefer a safetensors release or load in a sandbox.
How to fix
Convert the weights to safetensors before loading them anywhere that matters.
- Do not load the pickle files in-process — pickle deserialization executes arbitrary code from the file.
- Convert locally in a sandbox: `pip install safetensors` and use `safetensors.torch.save_file` on a state dict loaded with `torch.load(..., weights_only=True)` (refuses most code-execution payloads), or use Hugging Face's `convert.py` space/script.
- Pin the exact revision hash you converted from, and load only your converted safetensors artifact from then on.
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 2026-08-25.
| architecture | llama · 28 layers · 3072-dim |
| vocabulary | 128,256 tokens |
| license | llama3.2 |
| serialization | no safetensors pickle |
| chat template | present · sha256:5816fce10444e03c |
| claimed lineage | meta-llama/Llama-3.2-3B-Instruct |
| lineage verified | unverified — weights battery pending |
Full measured fingerprint
| architectures | LlamaForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 15 — pickle: openvino_detokenizer.bin, openvino_model.bin, openvino_tokenizer.bin |
| revision | 632bda948f22 |
| HF snapshot | 31 downloads · 0 likes · updated 2024-11-07 · captured 2026-08-25 |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/AIFunOver/Llama-3.2-3B-Instruct-openvino-4bit)