A tool to generate text with mlx-moe model.
Project description
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)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file mlx-moe-0.0.2.tar.gz
.
File metadata
- Download URL: mlx-moe-0.0.2.tar.gz
- Upload date:
- Size: 8.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.13
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 47349ce7f47a9623955df86ecbc8f9419c168d74f0f87dcd478b3f644713472d |
|
MD5 | 6c54132a0e67a01cf8b14e018cd0d4d5 |
|
BLAKE2b-256 | d12a7d4a38a3c0d28d9b102efabebdd86c3d8315725065fd048085f97832a739 |
File details
Details for the file mlx_moe-0.0.2-py3-none-any.whl
.
File metadata
- Download URL: mlx_moe-0.0.2-py3-none-any.whl
- Upload date:
- Size: 9.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.13
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | c49be49dda17ad3f43f807f42e74527c895893885b2149cb1627ed01d384432a |
|
MD5 | 53eb538ae3e2dfa69b73cdbde691c8b4 |
|
BLAKE2b-256 | da866ef399585cb36ec3c23150e80642c207f64bd2d8fc1cd2e7942938c272c8 |