Model page

ByteDance-Seed/UI-TARS-1.5-7B warn

downloads 812.5klikes 595license apache-2.0arch qwen2_5_vlparams 8292.2Mupdated 2025-04-18

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 2026-08-22152,064-token embedding scanned · 5762 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 5762 undertrained tokens (norm < 0.3× the vocabulary median of 0.947), including 126 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "ForCanBeConverted", "ForCanBeConvertedToF", "PostalCodesNL", "$PostalCodesNL", "<unk>", "(stypy", "useRalative", "TokenNameIdentifier". 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.

architectureqwen2_5_vl · 28 layers · 3584-dim
parameters8292.2M
vocabulary152,064 tokens
licenseapache-2.0
serializationsafetensors
chat templatepresent · sha256:44d5f08f3f72b837
glitch-token surface5,762 undertrained candidates, 126 plain-ASCII
Full measured fingerprint
architecturesQwen2_5_VLForConditionalGeneration
librarytransformers
pipelineimage-text-to-text
repo files19
revision683d002dd99d
HF snapshot813.9k downloads · 594 likes · updated 2025-04-18 · captured 2026-08-21
embedding tensormodel.embed_tokens.weight · F32 · 152,064×3584
embedding normsmedian 0.9467 · mean 0.8817
lineage checkno claimed base model
glitch-token samples"ForCanBeConverted", "ForCanBeConvertedToF", "PostalCodesNL", "$PostalCodesNL", "<unk>", "(stypy", "useRalative", "TokenNameIdentifier", "useRal", "thuisontvangst", "NdrFc", "Cumhurba"

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 07:432m1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, lineage-norm-correlation
embedding tensormodel.embed_tokens.weight · F32 · 152,064×3584
glitch surface5,762 undertrained, 126 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/ByteDance-Seed/UI-TARS-1.5-7B/badge.svg)](https://ingot.tools/models/ByteDance-Seed/UI-TARS-1.5-7B)
Gate it in CI