sentence-transformers/all-MiniLM-L6-v2 warn
Loading it runs custom code from the repo; its license differs from its base model's.
claims base: nreimers/MiniLM-L6-H384-uncased · chat template: not found · view on Hugging Face ↗
Scan coverageStatic battery2026-08-25Weights battery2026-08-25Behavioral batteryn/adetails
| 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 · lineage consistent |
| Behavioral battery | Live-inference differentials | n/anot applicable: sentence-similarity model has no text-generation surface to probe |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-25 · 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 Partial coverage — not a generative language model
sentence-similarity model — no generation surface, so behavioral (live-inference) checks are not applicable; packaging, license, and weights forensics apply.
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.
info Weights consistent with claimed parent nreimers/MiniLM-L6-H384-uncased
Mean cosine similarity of 64 sampled token-embedding rows against nreimers/MiniLM-L6-H384-uncased is 0.873 — the weights plausibly descend from the declared base (relation: unspecified).
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 | 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 | consistent vs nreimers/MiniLM-L6-H384-uncased — embedding-row cosine 0.873 |
| glitch-token surface | clean no undertrained tokens |
Full measured 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 | 256.2M downloads · 5.3k likes · updated 2026-06-01 · captured 2026-08-25 |
| embedding tensor | embeddings.word_embeddings.weight · F32 · 30,522×384 |
| embedding norms | median 1.111 · mean 1.0656 |
| lineage check | consistent — cosine 0.8732 over 64 sampled rows vs nreimers/MiniLM-L6-H384-uncased |
Battery runs (3)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-25 20:26 | 27s | 1 |
| weights | complete | 2026-08-20 18:02 | 3s | 1 |
| weights | complete | 2026-08-20 08:10 | 3s | 1 |
weights run 2026-08-25 — measurements
| probes run | glitch-norm-scan, zero-template-token-scan, lineage-norm-correlation |
| embedding tensor | embeddings.word_embeddings.weight · F32 · 30,522×384 |
| glitch surface | 0 undertrained, 0 plain-ASCII |
| lineage check | consistent — cosine 0.8732 over 64 rows vs nreimers/MiniLM-L6-H384-uncased |
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)