SeerAttention/SeerAttention-Decode-Qwen3-4B-AttnGates warn
Weights only ship in a format that can run code when loaded; its license differs from its base model's; the chat template was dropped from its base model, which changes behavior.
claims base: Qwen/Qwen3-4B · chat template: not found · view on Hugging Face ↗
Scan coverageStatic battery2026-08-21Weights battery2026-08-21Behavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-21 |
| Weights battery | Weights forensics: no GPU, no download | complete 2026-08-21no token vocabulary — pickle audit only · pickle audit clean |
| Behavioral battery | Live-inference differentials | not run |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-21 · published from a community scan.
medium Pickle-serialized weights, no safetensors
Weights ship only as pickle-based files (attn_gate_weights.pth). 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 (mit vs apache-2.0)
This model declares mit while its claimed base Qwen/Qwen3-4B declares apache-2.0. 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 dropped vs parent
Qwen/Qwen3-4B ships a chat template; this repo does not. Serving stacks will silently fall back to a generic template, changing behavior. (In our 296-model census, 78% of pure quantization re-releases changed or dropped the template.)
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.
info Pickle static analysis clean
Opcode-level parse of attn_gate_weights.pth (no code executed) found only standard serialization globals (3 distinct, all torch/collections/numpy). Pickle remains an executable format — this verifies the current bytes, not future uploads; prefer a safetensors release.
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.
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 SeerAttention/SeerAttention-Decode-Qwen3-4B-AttnGates
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 2026-08-21.
| architecture | qwen3 · 36 layers · 2560-dim |
| vocabulary | 151,936 tokens |
| license | mit |
| serialization | no safetensors pickle |
| chat template | none |
| claimed lineage | Qwen/Qwen3-4B |
| lineage verified | unverified — weights battery pending |
Full measured fingerprint
| architectures | Qwen3ForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 4 — pickle: attn_gate_weights.pth |
| revision | d29752cb96b6 |
| HF snapshot | 636 downloads · 2 likes · updated 2025-06-09 · captured 2026-08-21 |
| weights battery | token-embedding scan n/a — no token-embedding tensor found in the pickle checkpoint(s) — pickle checkpoint(s) statically analyzed anyway |
| pickle audit | attn_gate_weights.pth — 3 standard global(s) |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-21 05:14 | 2s | 1 |
weights run 2026-08-21 — measurements
| probes run | pickle-static-analysis |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/SeerAttention/SeerAttention-Decode-Qwen3-4B-AttnGates)