https://github.com/rahulbhalley/mlx-models

Pre-trained models for Apple's MLX.
https://github.com/rahulbhalley/mlx-models

apple deep-learning mlx

Last synced: 17 days ago
JSON representation

Pre-trained models for Apple's MLX.

• Host: GitHub
• URL: https://github.com/rahulbhalley/mlx-models
• Owner: RahulBhalley
• Created: 2024-02-02T02:14:52.000Z (10 months ago)
• Default Branch: main
• Last Pushed: 2024-02-24T04:52:07.000Z (9 months ago)
• Last Synced: 2024-10-14T23:40:14.086Z (about 1 month ago)
• Topics: apple, deep-learning, mlx
• Language: Python
• Homepage:
• Size: 14.6 KB
• Stars: 2
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# MLX-Models

Provides various pre-trained models for Apple's MLX framework.

## Installation

Open your terminal and run the following command:

```bash

pip3 install "git+https://github.com/RahulBhalley/mlx-models.git"

```

This command will fetch the latest version of the MLX-Models package from the GitHub repository and install it on your system.

## Usage

### Loading Pre-trained Models

MLX-Models simplifies the process of loading and utilizing pre-trained models. For instance, to load a pre-trained models, you can use the following code snippet:

```python

import mlx.models as mlx_models

# Load the pre-trained VGG19 model

vgg19 = mlx_models.vision.VGG19(load_weights=True)

# Load the pre-trained AlexNet model

alexnet = mlx_models.vision.AlexNet(load_weights=True)

```

This will initialize the respective models with pre-trained weights.

### Available Models

At present, the MLX-Models package primarily supports vision models. Later, we'll add support for audio and text models as well.

## Contributing

We welcome contributions to the MLX-Models project! Whether it's adding new models, improving the existing ones, or fixing bugs, your contributions are valuable to us. Just create a pull request (PR).

## License

This project is licensed under the MIT License.

## Support

If you encounter any issues please file an issue and if you have questions please use Discussions.