Model page

microsoft/phi-1_5 warn

Glitch tokens that can silently corrupt ordinary input. Plus 1 minor note.

downloads 56.8klikes 1.4klicense mitarch phiparams 1418.3Mupdated 2025-11-24

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 2026-08-2551,200-token embedding scanned · 1158 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.

medium Undertrained (glitch) token surface in vocabulary

Embedding-norm scan flagged 1158 undertrained tokens (norm < 0.3× the vocabulary median of 1.245), including 157 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "TheNitrome", "guiIcon", "TheNitromeFan", "guiActive", "unfocusedRange", "channelAvailability", "GoldMagikarp", "srfN". 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.

low Undertrained tokens present; echo probe skipped (no chat template)

1158 undertrained tokens found (16 ASCII candidates) but the repo ships no chat template, so the behavioral echo probe was skipped. Treat the candidates as unverified risk surface.

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.

architecturephi · 24 layers · 2048-dim
parameters1418.3M
vocabulary51,200 tokens
licensemit
serializationsafetensors
chat templatenone
glitch-token surface1,158 undertrained candidates, 157 plain-ASCII
Full measured fingerprint
architecturesPhiForCausalLM
librarytransformers
pipelinetext-generation
repo files16
revision77aa61eeac94
HF snapshot56.8k downloads · 1.4k likes · updated 2025-11-24 · captured 2026-08-25
embedding tensormodel.embed_tokens.weight · F16 · 51,200×2048
embedding normsmedian 1.2449 · mean 1.2054
lineage checkno claimed base model
glitch-token samples"TheNitrome", "guiIcon", "TheNitromeFan", "guiActive", "unfocusedRange", "channelAvailability", "GoldMagikarp", "srfN", "rawdownload", "Dragonbound", "Downloadha", "externalToEVAOnly"
Battery runs (2)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
gpucomplete2026-08-25 21:4733s1
weightscomplete2026-08-25 20:3418s1
gpu run 2026-08-25 measurements
probes runglitch
probes skippedglitch-echo: no chat template
weights run 2026-08-25 measurements
probes runglitch-norm-scan, zero-template-token-scan, lineage-norm-correlation
embedding tensormodel.embed_tokens.weight · F16 · 51,200×2048
glitch surface1,158 undertrained, 157 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/microsoft/phi-1_5/badge.svg)](https://ingot.tools/models/microsoft/phi-1_5)
Gate it in CI