PoungPoung/fen_chess warn
Weights only ship in a format that can run code when loaded; its tokenizer differs from its claimed base model. Plus 1 minor note.
claims base: gpt2, openai-community/gpt2 · chat template: not found · view on Hugging Face ↗
Scan coverageStatic battery2026-08-25Weights battery2026-08-25Behavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-25 |
| Weights battery | Weights forensics — no GPU, no download | complete 2026-08-2515,839-token embedding scanned · 0 undertrained · lineage inconsistent · pickle audit clean |
| Behavioral battery | Live-inference differentials | not run |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-25 · 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 Vocabulary size differs from claimed parent (15839 vs 50257)
A changed vocab means changed tokenization: strings will split differently than on openai-community/gpt2, 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 (0.577). 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 (3 distinct, all torch/collections/numpy). Pickle remains an executable format — this verifies the current bytes, not future uploads; prefer a safetensors release.
low Weights diverge from claimed parent openai-community/gpt2
This model declares openai-community/gpt2 as its base (relation: unspecified), but mean cosine similarity of 64 sampled token-embedding rows against that parent is only -0.005 (true finetunes, merges, and quantizations sit above 0.8; independently trained weights sit near 0). Either the lineage label is wrong, or the model was so heavily re-trained, pruned, or distilled that the parent's properties (safety posture, evaluated behavior, licensing basis) should not be assumed to carry over. Verify provenance before relying on the parent's reputation.
How to fix
Fix or verify the `base_model` declaration so lineage checks can run.
- If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
- If you don't: identify the true parent (config architecture + weight shapes narrow it fast) and re-scan with that lineage in mind.
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 | gpt2 · 12 layers · 768-dim |
| vocabulary | 15,839 tokens |
| license | mit |
| serialization | no safetensors pickle |
| chat template | none |
| claimed lineage | openai-community/gpt2 |
| lineage verified | inconsistent vs openai-community/gpt2 — embedding-row cosine -0.005 |
| glitch-token surface | clean no undertrained tokens |
Full measured fingerprint
| architectures | GPT2LMHeadModel |
| library | transformers |
| pipeline | text-generation |
| repo files | 11 — pickle: pytorch_model.bin, training_args.bin |
| revision | 488e5dc557f0 |
| HF snapshot | 499 downloads · 0 likes · updated 2023-09-11 · captured 2026-08-25 |
| pickle audit | pytorch_model.bin — 3 standard global(s) |
| embedding tensor | transformer.wte.weight · F32 · 15,839×768 |
| embedding norms | median 0.5773 · mean 0.5775 |
| lineage check | inconsistent — cosine -0.0052 over 64 sampled rows vs openai-community/gpt2 |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-25 21:48 | 29s | 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 · 15,839×768 |
| glitch surface | 0 undertrained, 0 plain-ASCII |
| lineage check | inconsistent — cosine -0.0052 over 64 rows vs openai-community/gpt2 |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/PoungPoung/fen_chess)