aburnazy/opt-350m-hy-instruct warn
Weights only ship in a format that can run code when loaded; no license declared — no usage rights by default; its tokenizer differs from its claimed base model.
claims base: aburnazy/opt-350m-hy · chat template: not found · view on Hugging Face ↗
Scan coverageStatic battery2026-08-25Weights batteryqueuedBehavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-25 |
| Weights battery | Weights forensics — no GPU, no download | queued |
| 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 (pytorch_model.bin, training_args.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.
medium No license declared
The model card declares no license. You have no usage rights by default — treat as all-rights-reserved until the owner clarifies.
How to fix
Get a license from the owner or pick a licensed alternative — this is a legal gap, not a technical one.
- With no declared license you have no usage rights by default; treat the weights as all-rights-reserved.
- Open an issue or discussion on the repo asking the owner to declare a license, or use the licensed upstream/parent model instead.
medium Vocabulary size differs from claimed parent (50265 vs 50272)
A changed vocab means changed tokenization: strings will split differently than on aburnazy/opt-350m-hy, which can shift behavior on identifiers, codes, and non-English text.
How to fixweight-level
Not patchable: the vocab size mirrors the embedding matrix in the weights. Verify the change was intentional.
- Do not edit `vocab_size` in config.json to "match the parent" — it must equal the embedding table in the shipped weights or the model won't load.
- Diff the tokenizers (`tokenizer.json` / added_tokens) against the parent to see what was added or removed, and test your own identifiers, codes, and non-English text through both.
- If the drift is unexplained by the model card, treat tokenization-sensitive behavior as unvalidated on this model.
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 2026-08-25.
| architecture | opt · 24 layers · 1024-dim |
| vocabulary | 50,265 tokens |
| license | none declared |
| serialization | no safetensors pickle |
| chat template | none |
| claimed lineage | aburnazy/opt-350m-hy |
| lineage verified | unverified — weights battery pending |
Full measured fingerprint
| architectures | OPTForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 13 — pickle: pytorch_model.bin, training_args.bin |
| revision | ae848cacef4c |
| HF snapshot | 13 downloads · 0 likes · updated 2023-07-24 · captured 2026-08-25 |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | queued | 2026-08-25 22:33 | — | 0 |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/aburnazy/opt-350m-hy-instruct)