Package profile
open-clip-torch
- Summary: Open reproduction of consastive language-image pretraining (CLIP) and related.
- Author: Gabriel Ilharco, Mitchell Wortsman, Romain Beaumont
- License: MIT License
- Homepage: https://github.com/mlfoundations/open_clip
- Source: https://github.com/mlfoundations/open_clip
- Number of releases: 55
- First release: 0.2.0 on 2022-04-04
- Latest release: 3.3.0 on 2026-02-27
- Latest release size: 1.5 MB (pure Python wheel)
Dependencies
Open-clip-torch has 16 dependencies, 8 of which optional.Dependent packages
| Package | Optional | Group |
|---|---|---|
| megatron-bridge | false | |
| crfm-helm | true | vlm |
| docling-slim | true | all |
| lancedb | true | clip |
| modelscope | true | cv |
Similar packages
- transformersTransformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
- language-dataSupplementary data about languages used by the langcodes module
- plotnineA Grammar of Graphics for Python
- sglangSGLang is a fast serving framework for large language models and vision language models.
- trlTrain transformer language models with reinforcement learning.
- tooth-pythonGenerating text.
- ascii-magicConverts pictures into ASCII art