Model page

mistralai/Mistral-7B-Instruct-v0.2 warn

downloads 1.2Mlikes 3.2klicense apache-2.0arch mistralparams 7241.7Mupdated 2025-07-24

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 2026-08-2232,000-token embedding scanned · 194 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 194 undertrained tokens (norm < 0.3× the vocabulary median of 0.175), including 10 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "<0xFB>", "<0xFD>", "<0xFF>", "<0xFA>", "<0xFC>", "<0xFE>", "iNdEx", "febbra". 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.

architecturemistral · 32 layers · 4096-dim
parameters7241.7M
vocabulary32,000 tokens
licenseapache-2.0
serializationsafetensors pickle
chat templatepresent · sha256:796853172235ab3a
glitch-token surface194 undertrained candidates, 10 plain-ASCII
Full measured fingerprint
architecturesMistralForCausalLM
librarytransformers
pipelinetext-generation
repo files16 — pickle: pytorch_model-00001-of-00003.bin, pytorch_model-00002-of-00003.bin, pytorch_model-00003-of-00003.bin
revision63a8b0818953
HF snapshot1.2M downloads · 3.2k likes · updated 2025-07-24 · captured 2026-08-21
embedding tensormodel.embed_tokens.weight · BF16 · 32,000×4096
embedding normsmedian 0.1747 · mean 0.1719
lineage checkno claimed base model
glitch-token samples"<0xFB>", "<0xFD>", "<0xFF>", "<0xFA>", "<0xFC>", "<0xFE>", "iNdEx", "febbra", "NdEx", "uitgen"

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 07:437s1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, lineage-norm-correlation
embedding tensormodel.embed_tokens.weight · BF16 · 32,000×4096
glitch surface194 undertrained, 10 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/mistralai/Mistral-7B-Instruct-v0.2/badge.svg)](https://ingot.tools/models/mistralai/Mistral-7B-Instruct-v0.2)
Gate it in CI