DCAgent/g1_min_episodes_e1_gpt_long_thinking_tacc-Qwen3-32B warn
Weights only ship in a format that can run code when loaded; loading it runs custom code from the repo.
claims base: Qwen/Qwen3-32B · 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-00001-of-00027.bin, pytorch_model-00002-of-00027.bin, pytorch_model-00003-of-00027.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.
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 | qwen3 · 64 layers · 5120-dim |
| vocabulary | 151,936 tokens |
| license | apache-2.0 |
| serialization | no safetensors pickle custom code |
| chat template | present (chat_template.jinja) · sha256:a55ee1b1660128b7 |
| claimed lineage | Qwen/Qwen3-32B |
| lineage verified | unverified — weights battery pending |
Full measured fingerprint
| architectures | Qwen3ForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 48 — pickle: pytorch_model-00001-of-00027.bin, pytorch_model-00002-of-00027.bin, pytorch_model-00003-of-00027.bin, pytorch_model-00004-of-00027.bin, pytorch_model-00005-of-00027.bin, pytorch_model-00006-of-00027.bin, pytorch_model-00007-of-00027.bin, pytorch_model-00008-of-00027.bin, pytorch_model-00009-of-00027.bin, pytorch_model-00010-of-00027.bin |
| revision | 5f7127727f57 |
| HF snapshot | 16 downloads · 0 likes · updated 2026-04-17 · 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 22:22 | — | 0 |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/DCAgent/g1_min_episodes_e1_gpt_long_thinking_tacc-Qwen3-32B)