OpenAI CLIP ViT-L/14@336px checkpoint (mirror)

Byte-identical mirror of openai/CLIP, checkpoint served from openaipublic.azureedge.net for the Cuvis.AI plugins. No fine-tuning, conversion or re-serialization: the files below are the upstream release as published, with the upstream licence text in LICENSE.

Why this mirror exists

Cuvis.AI provisions model weights once into a shared cache (download-model download <name> from cuvis-ai-core) and then runs its pipelines in an offline, token-free runtime that only reads that cache. Hosting the exact upstream files under the cubert-gmbh organisation makes that provisioning reproducible (commit-pinned and sha256-verified) and takes the per-user Hugging Face account and token out of the users' path.

Files and provenance

File	Upstream source	Upstream revision / id	sha256	Size
ViT-L-14-336px.pt	https://openaipublic.azureedge.net/clip/models/3035c92b350959924f9f00213499208652fc7ea050643e8b385c2dac08641f02/ViT-L-14-336px.pt	n/a (URL; sha256 pinned)	3035c92b350959924f9f00213499208652fc7ea050643e8b385c2dac08641f02	934.1 MB
LICENSE	https://raw.githubusercontent.com/openai/CLIP/main/LICENSE	n/a (URL; sha256 pinned)	987e63b32f6c89ff5160e429458a872ff048e6860b590a3912e938f9da8f14db	1.1 kB

Mirrored on 2026-09-04 by Cubert GmbH from the sources above. The sha256 values are the upstream values; tools/mirror_weights.py check in cuvis-ai-core re-verifies this repository against them and against the upstream licence text.

Licence

The openai/CLIP repository is published under the MIT License, Copyright (c) 2021 OpenAI (LICENSE, verbatim). OpenAI publishes this checkpoint through that repository's clip.load("ViT-L/14@336px") loader (served from openaipublic.azureedge.net; the sha256 is the hash OpenAI encodes in the download URL) without a separate licence statement for the weights, and OpenAI's own Hugging Face copies (for example openai/clip-vit-large-patch14-336) carry no licence tag. The file is redistributed here unchanged, as released; the license: unknown tag reflects that no explicit licence statement covers the weights. If you are a rights holder and object to this redistribution, open a discussion on this repository and the file will be taken down.

Usage with Cuvis.AI

uv run download-model download clip_vit_l_14_336

download-model (from cuvis-ai-core) provisions the file into the shared Hugging Face cache and verifies its sha256. From cuvis-ai-core 0.16.0 on, ModelWeights.resolve("<name>") returns the cached path and the cuvis-ai-adaclip nodes resolve their weights through it, so a pipeline needs no manual step once the weights are provisioned; earlier plugin releases still fetch from their original upstream sources.