Model page

Qwen/Qwen2.5-VL-3B-Instruct warn

downloads 6.5Mlikes 688license none declaredarch qwen2_5_vlparams 3754.6Mupdated 2025-04-06

chat template: present · view on Hugging Face ↗

Ingot findings

Static battery: 1 medium finding(s). Deep battery (behavioral differential, glitch-token pass) not yet run. Weights battery: embedding-norm scan over 151936 tokens (BF16, 2048-dim) found 0 undertrained candidates, 0 plain-ASCII. Scanned 2026-08-20 (published from a community scan).

medium No license declared

The model card declares no license. You have no usage rights by default — treat as all-rights-reserved until the owner clarifies.

How to fix

Get a license from the owner or pick a licensed alternative — this is a legal gap, not a technical one.

  1. With no declared license you have no usage rights by default; treat the weights as all-rights-reserved.
  2. Open an issue or discussion on the repo asking the owner to declare a license, or use the licensed upstream/parent model instead.

info Embedding-norm glitch scan clean

No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (1.009). The glitch-token data-corruption class has no candidate surface in this model.

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 weights-and-metadata profile of this model, rebuilt on every scan and deep-battery run. Updated 2026-08-20.

architectureqwen2_5_vl · 36 layers · 2048-dim
parameters3754.6M
vocabulary151,936 tokens
licensenone declared
serializationsafetensors
chat templatepresent · sha256:a0bc6f6fc7a29a80
glitch-token surfaceclean no undertrained tokens
Full fingerprint
architecturesQwen2_5_VLForConditionalGeneration
librarytransformers
pipelineimage-text-to-text
repo files14
revision66285546d2b8
HF snapshot6.5M downloads · 688 likes · updated 2025-04-06 · captured 2026-08-20
embedding tensormodel.embed_tokens.weight · BF16 · 151,936×2048
embedding normsmedian 1.0087 · mean 1.0074
lineage checkno 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/Qwen/Qwen2.5-VL-3B-Instruct/badge.svg)](https://ingot.tools/models/Qwen/Qwen2.5-VL-3B-Instruct)
Gate it in CI