sentence-transformers/all-MiniLM-L6-v2 warn
claims base: nreimers/MiniLM-L6-H384-uncased · chat template: not in config · view on Hugging Face ↗
Ingot findings
Static battery: 2 medium finding(s). Deep battery (behavioral differential, glitch-token pass) not yet run. Weights battery: embedding-norm scan over 30522 tokens (F32, 384-dim) found 0 undertrained candidates, 0 plain-ASCII. Scanned 2026-08-20 (published from a community scan).
medium Repo ships executable Python (trust_remote_code)
The repository contains custom code files that run in-process when loaded with trust_remote_code=True. Pin the revision hash and review the code before loading.
How to fix
Review and pin the custom code; never float on `main` with trust_remote_code=True.
- Read every `.py` file in the repo before first load — this code runs in your process.
- Pin the revision: `from_pretrained(model_id, revision="<commit sha>", trust_remote_code=True)` so a later push can't swap the code under you.
- Prefer a version of the architecture already in `transformers` if one exists, which removes the remote-code requirement entirely.
medium License differs from claimed parent (apache-2.0 vs mit)
This model declares apache-2.0 while its claimed base nreimers/MiniLM-L6-H384-uncased declares mit. Verify the re-license is permitted before commercial use.
How to fix
Verify the re-license is actually permitted before relying on it.
- Read the parent's license for derivative-work and re-licensing terms — many open-weight licenses (e.g. Llama-family) do not permit arbitrary re-licensing.
- If the re-license is not permitted, the parent's terms govern your use regardless of what this repo declares.
info Embedding-norm glitch scan clean
No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (1.111). The glitch-token data-corruption class has no candidate surface in this model.
How to fixruntime guardweight-level
Keep the affected token strings out of the model's input — the scan-derived runtime guard carries this model's exact blocklist.
- Fetch this model's guard artifact (`/api/v1/guard/<owner>/<model>`): the confirmed corrupting tokens and the low-norm candidate list, derived from the published scan.
- Screen inbound text with it (the `@ingotai/guard` package is a reference implementation) and route flagged records to a different model or human review — verbatim-copy tasks on flagged strings are the failure mode.
- The underlying cause is undertrained embeddings in the weights; a true fix is weight-level (continued pretraining on the affected tokens) — that is not a patch, it's a training job.
Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.
Fingerprint
The durable weights-and-metadata profile of this model, rebuilt on every scan and deep-battery run. Updated 2026-08-20.
| architecture | bert · 6 layers · 384-dim |
| parameters | 22.7M |
| vocabulary | 30,522 tokens |
| license | apache-2.0 |
| serialization | safetensors pickle custom code |
| chat template | none |
| claimed lineage | nreimers/MiniLM-L6-H384-uncased |
| lineage verified | unverified — deep battery pending |
| glitch-token surface | clean no undertrained tokens |
Full fingerprint
| architectures | BertModel |
| library | sentence-transformers |
| pipeline | sentence-similarity |
| repo files | 30 — pickle: openvino/openvino_model.bin, openvino/openvino_model_qint8_quantized.bin, pytorch_model.bin |
| revision | 1110a243fdf4 |
| HF snapshot | 257.7M downloads · 5.2k likes · updated 2026-06-01 · captured 2026-08-20 |
| embedding tensor | embeddings.word_embeddings.weight · F32 · 30,522×384 |
| embedding norms | median 1.111 · mean 1.0656 |
| lineage check | parent weights unreadable (repo ships no safetensors weights) |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/sentence-transformers/all-MiniLM-L6-v2)