Skip to main content

A lightweight AI framework for using Meta/Facebook models with pure Python

Project description

MathyKit

MathyKit is a lightweight Python framework for building and using AI models, with a focus on Meta/Facebook models. It provides a simple and efficient way to use state-of-the-art AI models without the need for API keys or local model installations.

Features

  • Easy-to-use interface for AI model integration
  • Support for Meta/Facebook models
  • Pure Python implementation
  • No API keys required
  • Lightweight and efficient

Installation

pip install mathykit

Quick Start

from mathkit import Model
from mathkit.models import MetaOPT

# Load a pre-trained model
model = MetaOPT.from_pretrained("meta-opt-1.3b")

# Generate text
output = model.generate("What is artificial intelligence?")
print(output)

Documentation

For detailed documentation and examples, visit our documentation page.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mathykit-0.1.0.tar.gz (7.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mathykit-0.1.0-py3-none-any.whl (8.0 kB view details)

Uploaded Python 3

File details

Details for the file mathykit-0.1.0.tar.gz.

File metadata

  • Download URL: mathykit-0.1.0.tar.gz
  • Upload date:
  • Size: 7.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for mathykit-0.1.0.tar.gz
Algorithm Hash digest
SHA256 a3eaa43dfcfdfad3384187aab2fa9bb0697eca015b54650da4d6c5a3a08f57ed
MD5 54cb5dec18743e3a51d4aeece931920a
BLAKE2b-256 12461cf474ad4d4fa04e1de90de8bf7201173fca6db8e44d27b7d509174cec47

See more details on using hashes here.

File details

Details for the file mathykit-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: mathykit-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 8.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for mathykit-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 11bf167753a3cd24857ea7e751f7de3c254165f62d3bc9c85227cd0c809b97bb
MD5 9ed5ec136af5951410615fc7006812a3
BLAKE2b-256 c83be0fec0a7b27ba9e265f78d7a00a0bb1b8e2b372f88c59ae53ec293359a0d

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page