durgasai299792458/qwen35-4b-openvino-genai-npu warn
Weights only ship in a format that can run code when loaded; Chat template ends turns with <|im_end|>, which is not a configured stop token. Plus 1 minor note.
claims base: Qwen/Qwen3.5-4B · chat template: present · view on Hugging Face ↗
Scan coverageStatic battery2026-08-26Weights battery2026-08-26Behavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-26 |
| Weights battery | Weights forensics: no GPU, no download | complete 2026-08-26no 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 2026-08-26 · published from a community scan.
medium Pickle-serialized weights, no safetensors
Weights ship only as pickle-based files (embed_tokens.bin, layer_0.bin, layer_1.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 Chat template ends turns with <|im_end|>, which is not a configured stop token
The chat template terminates assistant turns with <|im_end|>, but the effective EOS set (config.json ∪ generation_config.json = [248044] → ["<|endoftext|>"]) never stops on it. Config-honoring runtimes generate past the terminator until the token budget is exhausted — runaway cost and self-continuing fake turns. Add <|im_end|>'s id to generation_config.json's eos_token_id.
How to fixingot patch
Align the stop-token declarations — a pure metadata fix to `generation_config.json` (and `config.json`).
- Identify the token the chat template actually ends assistant turns with (e.g. `<|eot_id|>`, `<end_of_turn>`, `<|im_end|>`) and make sure its id is in `generation_config.json`'s `eos_token_id` list.
- Keep `config.json`'s `eos_token_id` consistent with (or a subset of) `generation_config.json`'s — runtimes differ in which file they read.
- For the pad-equals-EOS hazard: repoint `pad_token` at a dedicated padding token before fine-tuning; serving is unaffected.
- Until the repo is fixed, pass explicit stop tokens to your serving stack (e.g. vLLM `stop_token_ids`, llama.cpp `--override-kv tokenizer.ggml.eos_token_id`).
info Pickle static analysis clean
Opcode-level parse of embed_tokens.bin, layer_0.bin, layer_1.bin, layer_10.bin (no code executed) found only standard serialization globals (0 distinct, all torch/collections/numpy). Pickle remains an executable format — this verifies the current bytes, not future uploads; prefer a safetensors release.
low Pickle checkpoint only partially analyzable
Static analysis could not fully parse: embed_tokens.bin: legacy parse stopped after 0 pickle(s): truncated pickle, layer_0.bin: legacy parse stopped after 0 pickle(s): unsupported pickle opcode 0x0 at 0, layer_1.bin: legacy parse stopped after 0 pickle(s): unsupported pickle opcode 0x39 at 1, +1 more. Unparsed content is unverified.
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 durgasai299792458/qwen35-4b-openvino-genai-npu
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 2026-08-26.
| architecture | qwen3_5 |
| license | apache-2.0 |
| serialization | no safetensors pickle |
| chat template | present (chat_template.jinja) · sha256:a4aee8afcf2e0711 |
| claimed lineage | Qwen/Qwen3.5-4B |
| lineage verified | unverified — weights battery pending |
Full measured fingerprint
| architectures | Qwen3_5ForConditionalGeneration |
| library | openvino |
| pipeline | text-generation |
| repo files | 84 — pickle: embed_tokens.bin, layer_0.bin, layer_1.bin, layer_10.bin, layer_11.bin, layer_12.bin, layer_13.bin, layer_14.bin, layer_15.bin, layer_16.bin |
| revision | 0fe64d705ff9 |
| HF snapshot | 15 downloads · 0 likes · updated 2026-06-14 · captured 2026-08-25 |
| 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 | embed_tokens.bin, layer_0.bin, layer_1.bin, layer_10.bin — 0 standard global(s) · legacy (pre-1.6) format, head-scan only |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-25 22:25 | 7s | 1 |
weights run 2026-08-25 — 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/durgasai299792458/qwen35-4b-openvino-genai-npu)