MAIRK/abab warn
Weights only ship in a format that can run code when loaded; loading it runs custom code from the repo.
claims base: mistralai/Mistral-6A-v1.6 · 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 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 Claimed parent mistralai/Mistral-6A-v1.6 not readable
The declared base model could not be fetched from the Hugging Face API, so lineage differentials (template, license, tokenizer) could not be verified.
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 2026-08-25.
| architecture | mistral · 32 layers · 4096-dim |
| vocabulary | 32,768 tokens |
| license | apache-2.0 |
| serialization | no safetensors pickle custom code |
| chat template | present · sha256:e16746b40344d6c5 |
| claimed lineage | mistralai/Mistral-6A-v1.6 |
| lineage verified | unverified — weights battery pending |
Full measured fingerprint
| architectures | MistralForCausalLM |
| pipeline | text-generation |
| repo files | 14 — pickle: pytorch_model.bin |
| revision | 15c931d1e8c6 |
| HF snapshot | 13 downloads · 0 likes · updated 2025-06-28 · 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 22:37 | — | 0 |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/MAIRK/abab)