senmasa/llama3.2-1b-preskripsi-summarization-16bit warn
Weights only ship in a format that can run code when loaded; its license differs from its base model's; the chat template differs from its base model, which changes behavior. Plus 2 more issues.
claims base: unsloth/llama-3.2-1b-instruct-bnb-4bit · chat template: present · 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). 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 License differs from claimed parent (apache-2.0 vs llama3.2)
This model declares apache-2.0 while its claimed base unsloth/llama-3.2-1b-instruct-bnb-4bit declares llama3.2. Verify the re-license is permitted before commercial use.
How to fix
Verify the re-license is actually permitted before relying on it.
- Read the parent's license for derivative-work and re-licensing terms — many open-weight licenses (e.g. Llama-family) do not permit arbitrary re-licensing.
- If the re-license is not permitted, the parent's terms govern your use regardless of what this repo declares.
medium Chat template differs from claimed parent
The chat template does not match unsloth/llama-3.2-1b-instruct-bnb-4bit's. Template drift silently changes model behavior even when weights are identical — 37% of drifted derivatives in our census left it undisclosed. Diff the templates before deploying.
How to fixingot patch
Restore the parent's chat template in `tokenizer_config.json` — a pure metadata fix.
- Run `ingot patch <owner/model>` — the patch manifest carries the parent's template and applies it to a local copy's `tokenizer_config.json`.
- Or fix by hand: copy the `chat_template` value from the parent repo's `tokenizer_config.json` into this model's, and pin your serving stack to that file.
- If the drift was intentional (the author retrained on a new template), confirm that in the model card before "fixing" it — restoring the parent template on retrained weights changes behavior too.
medium Architecture differs from claimed parent (qwen2 vs llama)
This model declares unsloth/llama-3.2-1b-instruct-bnb-4bit as its base, but its config declares architecture 'qwen2' while the parent is 'llama'. A finetune, merge, or quantization cannot change the architecture family — the lineage label is wrong or misleading, so treat provenance claims (training data, safety posture, licensing) as unverified.
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.
medium Vocabulary size differs from claimed parent (151936 vs 128256)
A changed vocab means changed tokenization: strings will split differently than on unsloth/llama-3.2-1b-instruct-bnb-4bit, 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.
Fix it
Some findings are metadata-level and patchable — apply the fixes to your local copy (your weights never leave your machine):
npx @ingotai/scan patch senmasa/llama3.2-1b-preskripsi-summarization-16bit
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 | qwen2 · 24 layers · 896-dim |
| vocabulary | 151,936 tokens |
| license | apache-2.0 |
| serialization | no safetensors pickle |
| chat template | present · sha256:cd8e9439f0570856 |
| claimed lineage | unsloth/llama-3.2-1b-instruct-bnb-4bit |
| lineage verified | unverified — weights battery pending |
Full measured fingerprint
| architectures | Qwen2ForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 11 — pickle: pytorch_model.bin |
| revision | c083fa3195ff |
| HF snapshot | 17 downloads · 0 likes · updated 2024-11-14 · 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 22:21 | — | 0 |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/senmasa/llama3.2-1b-preskripsi-summarization-16bit)