Model page

google-bert/bert-base-uncased pass

downloads 105.4Mlikes 2.7klicense apache-2.0arch bertparams 110.1Mupdated 2024-02-19

chat template: not in config · view on Hugging Face ↗

Ingot findings

Static battery clean: safetensors weights, license declared, no template/tokenizer drift detected. Deep battery not yet run. Weights battery: embedding-norm scan over 30522 tokens (F32, 768-dim) found 0 undertrained candidates, 0 plain-ASCII. Scanned 2026-08-20 (published from a community scan).

info Embedding-norm glitch scan clean

No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (1.401). 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.

  1. 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.
  2. 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.
  3. 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.

architecturebert · 12 layers · 768-dim
parameters110.1M
vocabulary30,522 tokens
licenseapache-2.0
serializationsafetensors pickle
chat templatenone
glitch-token surfaceclean no undertrained tokens
Full fingerprint
architecturesBertForMaskedLM
librarytransformers
pipelinefill-mask
repo files16 — pickle: coreml/fill-mask/float32_model.mlpackage/Data/com.apple.CoreML/weights/weight.bin, pytorch_model.bin
revision86b5e0934494
HF snapshot105.4M downloads · 2.7k likes · updated 2024-02-19 · captured 2026-08-20
embedding tensorbert.embeddings.word_embeddings.weight · F32 · 30,522×768
embedding normsmedian 1.4007 · mean 1.4014
lineage checkno claimed base model

Verdict badge

Ship the verdict in your README — it always shows the latest published analysis:

Ingot verdict: pass

[![Ingot scan](https://ingot.tools/api/v1/models/google-bert/bert-base-uncased/badge.svg)](https://ingot.tools/models/google-bert/bert-base-uncased)
Gate it in CI