Model page

google/flan-t5-base pass

No major issues. Minor: a small glitch-token surface (non-English text only).

downloads 1.7Mlikes 1.1klicense apache-2.0arch t5params 247.6Mupdated 2023-07-17

chat template: not found · view on Hugging Face ↗

Scan coverageStatic battery2026-08-25Weights battery2026-08-25Behavioral batterynot rundetails
BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-25
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-2532,128-token embedding scanned · 30 undertrained
Behavioral batteryLive-inference differentialsnot run

Ingot runs three batteries against a model. What each one checks →

Findings

Scanned 2026-08-25 · published from a community scan.

low Undertrained tokens in vocabulary (non-ASCII tail)

Embedding-norm scan flagged 30 undertrained tokens (norm < 0.3× the vocabulary median), but 0 decode to plain-ASCII strings, so exposure in English-language pipelines is limited. Behavioral confirmation requires the behavioral battery.

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 profile of this model: measured weights-and-metadata facts, rebuilt on every scan and battery run. Updated 2026-08-25.

architecturet5 · 12 layers · 768-dim
parameters247.6M
vocabulary32,128 tokens
licenseapache-2.0
serializationsafetensors pickle
chat templatenone
glitch-token surface30 undertrained candidates, 0 plain-ASCII
Full measured fingerprint
architecturesT5ForConditionalGeneration
librarytransformers
repo files12 — pickle: pytorch_model.bin
revision7bcac572ce56
HF snapshot1.7M downloads · 1.1k likes · updated 2023-07-17 · captured 2026-08-25
embedding tensorshared.weight · F32 · 32,128×768
embedding normsmedian 301.5545 · mean 300.427
lineage checkno claimed base model
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightscomplete2026-08-25 20:264s1
weights run 2026-08-25 measurements
probes runglitch-norm-scan, zero-template-token-scan, lineage-norm-correlation
embedding tensorshared.weight · F32 · 32,128×768
glitch surface30 undertrained, 0 plain-ASCII
lineage checknot checked (no 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/flan-t5-base/badge.svg)](https://ingot.tools/models/google/flan-t5-base)
Gate it in CI