llava-hf/llava-onevision-qwen2-0.5b-ov-hf pass
chat template: present · view on Hugging Face ↗
Scan coverage
Ingot runs three batteries against a model. What each one checks →
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-22 |
| Weights battery | Weights forensics — no GPU, no download | complete 2026-08-22152,000-token embedding scanned · 0 undertrained |
| Behavioral battery | Live-inference differentials | not run |
Findings
Scanned 2026-08-22 · published from a community scan.
info Embedding-norm glitch scan clean
No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (0.432). The glitch-token data-corruption class has no candidate surface in this model.
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.
| architecture | llava_onevision |
| parameters | 893.7M |
| vocabulary | 152,000 tokens |
| license | apache-2.0 |
| serialization | safetensors |
| chat template | present · sha256:793202280c0910ab |
| glitch-token surface | clean no undertrained tokens |
Full measured fingerprint
| architectures | LlavaOnevisionForConditionalGeneration |
| library | transformers |
| pipeline | image-text-to-text |
| repo files | 41 |
| revision | 74dd0bf867a4 |
| HF snapshot | 796.8k downloads · 58 likes · updated 2025-06-18 · captured 2026-08-21 |
| embedding tensor | language_model.model.embed_tokens.weight · F16 · 152,000×896 |
| embedding norms | median 0.432 · mean 0.4332 |
| lineage check | no claimed base model |
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.
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-21 07:43 | 46s | 1 |
weights run 2026-08-21 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | language_model.model.embed_tokens.weight · F16 · 152,000×896 |
| glitch surface | 0 undertrained, 0 plain-ASCII |
| lineage check | not checked (no claimed base model) |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/llava-hf/llava-onevision-qwen2-0.5b-ov-hf)