| --- |
| license: unknown |
| tags: |
| - mirror |
| - cuvis-ai |
| - clip |
| - vision-language |
| - backbone |
| --- |
| |
| # OpenAI CLIP ViT-L/14@336px checkpoint (mirror) |
|
|
| Byte-identical mirror of [`openai/CLIP`](https://github.com/openai/CLIP), checkpoint served from `openaipublic.azureedge.net` for the |
| [Cuvis.AI](https://github.com/cubert-hyperspectral/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 |
|
|
| ```text |
| 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. |
|
|
