22nd of 2 in Open models
clip
OpenAI's reference PyTorch code and weights for contrastive image-text embeddings
Live demo ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 34.5k
- License
- MIT
- Last commit
- Mar 2026
- Language
- Jupyter Notebook
32,703 on 24 Mar 202634,462 on 13 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
OpenAI is hiring: 806 open roles
Overview
CLIP is a Python package that loads OpenAI's pretrained image-text models and exposes encode_image, encode_text and a similarity forward pass. It supports zero-shot image classification from natural-language labels and feature extraction for linear-probe training. The README targets PyTorch 1.7.1 or later on CUDA or CPU, with weights downloaded on demand.
Who it is for: ML engineers needing image-text embeddings or zero-shot classification
Strengths
- Small API: clip.load, clip.tokenize, encode_image, encode_text
- Zero-shot classification from text labels without task-specific training
- MIT license; runs on CPU or CUDA GPU
- README has runnable zero-shot and linear-probe examples on CIFAR-100
Weaknesses
- Inference and evaluation only; no training code in this repo
- Installed from git via pip; no tagged releases
- Text context length defaults to 77 tokens
- Larger independently trained models are in OpenCLIP, not here
What it needs
- GPU optional
- Needs PyTorch 1.7.1+, torchvision, ftfy, regex, tqdm
- Models: CLIP ViT-B/32, other names via clip.available_models()
Head to head
Also in Open models
See all 2| Rank | Project | Score |
|---|---|---|
| 1 | timesfmPretrained time-series foundation model for zero-shot forecasting from Google Research | 74 out of 100 |