> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/mlfoundations/open_clip/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> OpenCLIP is an open-source implementation of OpenAI's CLIP (Contrastive Language-Image Pre-training) for training and using vision-language models.

# OpenCLIP

Welcome to OpenCLIP, an open-source implementation of OpenAI's [CLIP](https://arxiv.org/abs/2103.00020) (Contrastive Language-Image Pre-training). This codebase provides production-ready models for zero-shot image classification, image-text retrieval, and transfer learning tasks.

<Note>
  OpenCLIP is actively maintained by researchers at UW, Google, Stanford, Amazon, Columbia, and Berkeley, with continuous contributions from the open-source community.
</Note>

## What is CLIP?

CLIP learns visual concepts from natural language supervision by training on image-text pairs. This approach enables powerful zero-shot transfer capabilities, allowing models to classify images into categories they've never explicitly seen during training.

<img src="https://raw.githubusercontent.com/mlfoundations/open_clip/main/docs/CLIP.png" alt="CLIP Architecture" />

## Key Features

<Accordion title="80+ Pretrained Models">
  OpenCLIP provides a comprehensive collection of pretrained models trained on various datasets including LAION-400M, LAION-2B, and DataComp-1B. Models range from efficient mobile architectures to large-scale transformers achieving up to 85.4% zero-shot accuracy on ImageNet.
</Accordion>

<Accordion title="Distributed Training Support">
  Battle-tested on up to 1024 A100 GPUs with native support for SLURM clusters. Includes optimizations like gradient accumulation, local loss computation, and efficient memory management for large-scale training.
</Accordion>

<Accordion title="Zero-Shot Capabilities">
  Perform image classification without training examples. Simply describe the classes in natural language and the model can identify them in images.
</Accordion>

<Accordion title="Multiple Model Architectures">
  * Vision Transformers (ViT-B, ViT-L, ViT-H, ViT-bigG)
  * ConvNet architectures (ConvNext, ResNet)
  * SigLIP models for improved efficiency
  * CoCa models for generative captioning
</Accordion>

<Accordion title="Production-Ready API">
  Clean, well-documented Python API with support for:

  * Loading models from Hugging Face Hub
  * Custom preprocessing pipelines
  * Mixed precision training (FP16, BF16)
  * JIT compilation
  * WebDataset for large-scale datasets
</Accordion>

## State-of-the-Art Results

OpenCLIP models achieve competitive or superior performance compared to proprietary alternatives:

| Model            | Training Data | Resolution | ImageNet Zero-Shot Acc. |
| ---------------- | ------------- | ---------- | ----------------------- |
| ViT-bigG-14      | LAION-2B      | 224px      | 80.1%                   |
| ViT-L-14         | DataComp-1B   | 224px      | 79.2%                   |
| ConvNext-XXLarge | LAION-2B      | 256px      | 79.5%                   |
| ViT-H-14         | LAION-2B      | 224px      | 78.0%                   |

View the complete model zoo and zero-shot results across 38 datasets in our [model documentation](https://github.com/mlfoundations/open_clip/blob/main/docs/PRETRAINED.md).

## Research Foundation

OpenCLIP is backed by rigorous research on reproducible scaling laws for contrastive language-image learning:

<Note>
  **Paper**: [Reproducible Scaling Laws for Contrastive Language-Image Learning](https://arxiv.org/abs/2212.07143)\
  Published at CVPR 2023
</Note>

The research demonstrates how model performance scales with:

* Training compute budget
* Dataset size and quality
* Model architecture choices
* Training hyperparameters

## Use Cases

OpenCLIP powers a wide range of applications:

* **Zero-Shot Classification**: Classify images without training data
* **Image-Text Retrieval**: Search images using natural language queries
* **Transfer Learning**: Fine-tune on downstream tasks with robust pretrained features
* **Embedding Generation**: Create semantic embeddings for images and text
* **Content Moderation**: Filter and classify visual content
* **Multimodal Search**: Build search engines that understand both images and text
* **Data Curation**: Automatically label and organize image datasets

## Model Availability

All models are available through multiple channels:

* PyPI package: `open_clip_torch`
* Hugging Face Hub: [OpenCLIP library tag](https://huggingface.co/models?library=open_clip)
* Direct download from model zoo

Model cards with additional details are available on Hugging Face Hub.

## Community and Support

OpenCLIP is an active open-source project:

* GitHub: [mlfoundations/open\_clip](https://github.com/mlfoundations/open_clip)
* Issues and feature requests welcome
* Contributions from the community encouraged

<Warning>
  Portions of the modeling and tokenizer code are adaptations of OpenAI's official [CLIP repository](https://github.com/openai/CLIP).
</Warning>

## Next Steps

<Steps>
  <Step title="Install OpenCLIP">
    Get started by installing the package via pip
  </Step>

  <Step title="Try the Quickstart">
    Run your first zero-shot classification example
  </Step>

  <Step title="Explore Models">
    Browse the pretrained model zoo
  </Step>

  <Step title="Train Your Own">
    Learn how to train CLIP on your own data
  </Step>
</Steps>