Model page

openbmb/MiniCPM5-1B warn

downloads 1.0Mlikes 1.1klicense apache-2.0arch llamaparams 1080.6Mupdated 2026-08-17

chat template: present · view on Hugging Face ↗

Scan coverage

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

BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-22
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-22130,560-token embedding scanned · 2177 undertrained
Behavioral batteryLive-inference differentialsnot run

Findings

Scanned 2026-08-22 · published from a community scan.

medium Undertrained (glitch) token surface in vocabulary

Embedding-norm scan flagged 2177 undertrained tokens (norm < 0.3× the vocabulary median of 1.068), including 1803 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "PSAkKC", "MestradoData", "QCCWAAKxBBCIJYB", "IEwubWFya", "/vanchukartur", "dLCBbMzcu", "pOwoKICAgICAgICAgICAgCiAgICAgICAgICAgICAgICB", "scrambletrial". In models where this class was tested behaviorally, such tokens silently rewrote user input into confident, schema-valid, wrong output. These are candidates from the weights alone; 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 2026-08-22.

architecturellama · 24 layers · 1536-dim
parameters1080.6M
vocabulary130,560 tokens
licenseapache-2.0
serializationsafetensors
chat templatenone
glitch-token surface2,177 undertrained candidates, 1,803 plain-ASCII
Full measured fingerprint
architecturesLlamaForCausalLM
librarytransformers
pipelinetext-generation
repo files11
revision87179e5c1f45
HF snapshot1.0M downloads · 1.1k likes · updated 2026-08-17 · captured 2026-08-21
embedding tensormodel.embed_tokens.weight · BF16 · 130,560×1536
embedding normsmedian 1.0677 · mean 1.0283
lineage checkno claimed base model
glitch-token samples"PSAkKC", "MestradoData", "QCCWAAKxBBCIJYB", "IEwubWFya", "/vanchukartur", "dLCBbMzcu", "pOwoKICAgICAgICAgICAgCiAgICAgICAgICAgICAgICB", "scrambletrial", "apothieka", "KZRRHCN", "OwoKICAgICAgICAK", "CiAgICAgICAgCiAgICAK"

Battery runs

The run trace behind the findings above: every deep-battery job for this model, with what each run measured or why it failed. Findings are only as good as the runs that produced them.

batterystatusqueueddurationattempts
weightscomplete2026-08-21 07:4322s1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, lineage-norm-correlation
embedding tensormodel.embed_tokens.weight · BF16 · 130,560×1536
glitch surface2,177 undertrained, 1,803 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: warn

[![Ingot scan](https://ingot.tools/api/v1/models/openbmb/MiniCPM5-1B/badge.svg)](https://ingot.tools/models/openbmb/MiniCPM5-1B)
Gate it in CI