Model page

openai/clip-vit-large-patch14 warn

downloads 6.3Mlikes 2.1klicense none declaredarch clipparams 427.6Mupdated 2023-09-15

chat template: not in config · 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 49408 tokens (F32, 768-dim) found 215 undertrained candidates, 7 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.

medium Undertrained (glitch) token surface in vocabulary

Embedding-norm scan flagged 215 undertrained tokens (norm < 0.3× the vocabulary median of 0.389), including 7 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "flyeagles", "coscino</w>", "sundaywithmarsha</w>", "instaweather", "mikequind", "pational</w>", "pknot</w>". 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 GPU deep 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 weights-and-metadata profile of this model, rebuilt on every scan and deep-battery run. Updated 2026-08-20.

architectureclip
parameters427.6M
vocabulary49,408 tokens
licensenone declared
serializationsafetensors pickle
chat templatenone
glitch-token surface215 undertrained candidates, 7 plain-ASCII
Full fingerprint
architecturesCLIPModel
librarytransformers
pipelinezero-shot-image-classification
repo files13 — pickle: pytorch_model.bin
revision32bd64288804
HF snapshot6.3M downloads · 2.1k likes · updated 2023-09-15 · captured 2026-08-20
embedding tensortext_model.embeddings.token_embedding.weight · F32 · 49,408×768
embedding normsmedian 0.3886 · mean 0.3854
lineage checkno claimed base model
glitch-token samples"flyeagles", "coscino</w>", "sundaywithmarsha</w>", "instaweather", "mikequind", "pational</w>", "pknot</w>"

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/openai/clip-vit-large-patch14/badge.svg)](https://ingot.tools/models/openai/clip-vit-large-patch14)
Gate it in CI