auhide/chef-gpt warn
Weights only ship in a format that can run code when loaded; Special token id outside the vocabulary; its tokenizer differs from its claimed base model.
claims base: auhide/chef-gpt-base · chat template: not found · view on Hugging Face ↗
Scan coverageStatic battery2026-08-27Weights battery2026-08-27Behavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-27 |
| Weights battery | Weights forensics: no GPU, no download | complete 2026-08-2730,006-token embedding scanned · 0 undertrained · lineage consistent · pickle audit clean |
| Behavioral battery | Live-inference differentials | not run |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-27 · published from a community scan.
medium Pickle-serialized weights, no safetensors
Weights ship only as pickle-based files (pytorch_model.bin, training_args.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 Special token id outside the vocabulary
eos_token_id=50256, bos_token_id=50256 is outside the declared vocab_size of 30006. Runtimes either crash on it or silently ignore the setting (e.g. pad_token_id: -1), which breaks batching and stop handling.
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`).
medium Vocabulary size differs from claimed parent (30006 vs 30005)
A changed vocab means changed tokenization: strings will split differently than on auhide/chef-gpt-base, which can shift behavior on identifiers, codes, and non-English text.
How to fixweight-level
Not patchable: the vocab size mirrors the embedding matrix in the weights. Verify the change was intentional.
- Do not edit `vocab_size` in config.json to "match the parent" — it must equal the embedding table in the shipped weights or the model won't load.
- Diff the tokenizers (`tokenizer.json` / added_tokens) against the parent to see what was added or removed, and test your own identifiers, codes, and non-English text through both.
- If the drift is unexplained by the model card, treat tokenization-sensitive behavior as unvalidated on this model.
info Embedding-norm glitch scan clean
No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (4.130). The glitch-token data-corruption class has no candidate surface in this model.
info Pickle static analysis clean
Opcode-level parse of pytorch_model.bin (no code executed) found only standard serialization globals (4 distinct, all torch/collections/numpy). Pickle remains an executable format — this verifies the current bytes, not future uploads; prefer a safetensors release.
info Weights consistent with claimed parent auhide/chef-gpt-base
Mean cosine similarity of 64 sampled token-embedding rows against auhide/chef-gpt-base is 0.990 — the weights plausibly descend from the declared base (relation: unspecified).
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 auhide/chef-gpt
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 2026-08-27.
| architecture | gpt2 · 12 layers · 768-dim |
| vocabulary | 30,006 tokens |
| license | mit |
| serialization | no safetensors pickle |
| chat template | none |
| claimed lineage | auhide/chef-gpt-base |
| lineage verified | consistent vs auhide/chef-gpt-base — embedding-row cosine 0.990 |
| glitch-token surface | clean no undertrained tokens |
Full measured fingerprint
| architectures | GPT2LMHeadModel |
| library | transformers |
| pipeline | text-generation |
| repo files | 13 — pickle: pytorch_model.bin, training_args.bin |
| revision | 8f77a731c598 |
| HF snapshot | 13 downloads · 1 likes · updated 2023-09-26 · captured 2026-08-25 |
| pickle audit | pytorch_model.bin — 4 standard global(s) |
| embedding tensor | transformer.wte.weight · F32 · 30,006×768 |
| embedding norms | median 4.1299 · mean 4.1878 |
| lineage check | consistent — cosine 0.9898 over 64 sampled rows vs auhide/chef-gpt-base |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-25 22:34 | 28s | 1 |
weights run 2026-08-25 — measurements
| probes run | glitch-norm-scan, zero-template-token-scan, pickle-static-analysis, lineage-norm-correlation |
| embedding tensor | transformer.wte.weight · F32 · 30,006×768 |
| glitch surface | 0 undertrained, 0 plain-ASCII |
| lineage check | consistent — cosine 0.9898 over 64 rows vs auhide/chef-gpt-base |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/auhide/chef-gpt)