Inoxoft/whitelightning
WhiteLightning distills massive, state-of-the-art language models into lightweight, hyper-efficient text classifiers. It's a command-line tool that lets you create specialized models that run anywhere—from the cloud to the edge—using the universal ONNX format for maximum compatibility.
WhiteLightning helps you create specialized tools that categorize text efficiently. You provide a description of how you want to sort text, or your own labeled data, and it produces a small, fast text classifier. This is ideal for developers or machine learning engineers who need to deploy text classification features that work quickly and reliably in various applications, even on devices with limited power.
152 stars. No commits in the last 6 months.
Use this if you need to build and deploy lightweight text classification models for tasks like sentiment analysis, spam detection, or topic labeling, especially when large language models are too slow or expensive.
Not ideal if you require a general-purpose conversational AI or a model that generates new text rather than classifying existing text.
Stars
152
Forks
4
Language
Python
License
GPL-3.0
Category
Last pushed
Aug 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Inoxoft/whitelightning"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
keras-team/keras
Deep Learning for humans
Lightning-AI/torchmetrics
Machine learning metrics for distributed, scalable PyTorch applications.
Lightning-AI/pytorch-lightning
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
lanpa/tensorboardX
tensorboard for pytorch (and chainer, mxnet, numpy, ...)