google/electra-base-discriminator warn
Weights only ship in a format that can run code when loaded.
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 2026-08-2530,522-token embedding scanned · 0 undertrained · 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). 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.
info Embedding-norm glitch scan clean
No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (1.677). 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.
Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.
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.
Fingerprint
The durable profile of this model: measured weights-and-metadata facts, rebuilt on every scan and battery run. Updated 2026-08-25.
| architecture | electra · 12 layers · 768-dim |
| vocabulary | 30,522 tokens |
| license | apache-2.0 |
| serialization | no safetensors pickle |
| chat template | none |
| glitch-token surface | clean no undertrained tokens |
Full measured fingerprint
| architectures | ElectraForPreTraining |
| library | transformers |
| repo files | 10 — pickle: pytorch_model.bin |
| revision | 1ae76a97c7e8 |
| HF snapshot | 54.2M downloads · 154 likes · updated 2024-02-29 · captured 2026-08-25 |
| pickle audit | pytorch_model.bin — 3 standard global(s) · legacy (pre-1.6) format, head-scan only |
| embedding tensor | electra.embeddings.word_embeddings.weight · F32 · 30,522×768 |
| embedding norms | median 1.6768 · mean 1.6077 |
| lineage check | no claimed base model |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-25 20:26 | 10s | 1 |
weights run 2026-08-25 — measurements
| probes run | glitch-norm-scan, zero-template-token-scan, pickle-static-analysis, lineage-norm-correlation |
| embedding tensor | electra.embeddings.word_embeddings.weight · F32 · 30,522×768 |
| glitch surface | 0 undertrained, 0 plain-ASCII |
| lineage check | not checked (no claimed base model) |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/google/electra-base-discriminator)