Skip to main content

MLX-MOE Models Package

The mlx-moe package offers custom MLX Mixture of Experts (MoE) models, streamlining the process of leveraging sophisticated MoE models for text generation, particularly in conjunction with the mlx-lm package. This tool is designed for developers and researchers who require advanced text generation capabilities, providing an easy pathway to utilize and integrate MoE models into their projects.

Features

  • Custom MoE Model Support: Easily load and utilize your custom MLX MoE models for text generation.
  • Easy Installation: Get started quickly with a simple pip installation command.

Installation

To install mlx-moe, simply run the following command in your terminal:

pip install mlx-moe

Usage

The mlx-moe package is designed to be used in conjunction with the mlx-lm package for generating text. After installing mlx-moe, you can load your custom MoE models as follows:

from mlx_moe.load import load_moe

model_path = "path_to_your_model"
model = load_moe(model_path)

Metadata

Release files for mlx-moe 0.0.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mlx-moe 0.0.2
File Size Uploaded
mlx-moe-0.0.2.tar.gz 8.0 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for mlx-moe 0.0.2
File Interpreter ABI Platform
mlx_moe-0.0.2-py3-none-any.whl Python 3 none any Details

Total release size: 17.5 kB

Release files / mlx-moe-0.0.2.tar.gz

Download URL mlx-moe-0.0.2.tar.gz
Size 8.0 kB
Tags Source
SHA-256 checksum
How to use checksums
47349ce7f47a9623955df86ecbc8f9419c168d74f0f87dcd478b3f644713472d
BLAKE2b-256 checksum
How to use checksums
d12a7d4a38a3c0d28d9b102efabebdd86c3d8315725065fd048085f97832a739
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.10.13

Release files / mlx_moe-0.0.2-py3-none-any.whl

Download URL mlx_moe-0.0.2-py3-none-any.whl
Size 9.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c49be49dda17ad3f43f807f42e74527c895893885b2149cb1627ed01d384432a
BLAKE2b-256 checksum
How to use checksums
da866ef399585cb36ec3c23150e80642c207f64bd2d8fc1cd2e7942938c272c8
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.10.13

Release history Release notifications | RSS feed

This release

0.0.2 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page