drawais/DeepSeek-R1-Distill-Qwen-32B-HQQ-INT4 warn
Weights only ship in a format that can run code when loaded. Plus 1 minor note.
claims base: deepseek-ai/DeepSeek-R1-Distill-Qwen-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 (qmodel.pt). 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.
low Padding token is the EOS token
The pad token and the (only) EOS token are the same. Fine-tuning frameworks mask pad positions out of the loss, so training on this checkpoint teaches the model to never emit EOS — the Phi-4 / Qwen 2.5 / DeepSeek R1 infinite-generation bug. Safe to serve, hazardous to fine-tune; repoint pad_token at a dedicated token first.
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`).
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 drawais/DeepSeek-R1-Distill-Qwen-32B-HQQ-INT4
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 · 64 layers · 5120-dim |
| vocabulary | 152,064 tokens |
| license | mit |
| serialization | no safetensors pickle |
| chat template | present (chat_template.jinja) · sha256:56a1447ad31926fd |
| claimed lineage | deepseek-ai/DeepSeek-R1-Distill-Qwen-32B |
| lineage verified | unverified — weights battery pending |
Full measured fingerprint
| architectures | Qwen2ForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 9 — pickle: qmodel.pt |
| revision | 5275fa952f7e |
| HF snapshot | 16 downloads · 0 likes · updated 2026-05-03 · 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/drawais/DeepSeek-R1-Distill-Qwen-32B-HQQ-INT4)