lxuechen/private-transformers
A codebase that makes differentially private training of transformers easy.
This project helps machine learning engineers or researchers fine-tune large language models and other transformer-based models while ensuring data privacy. It takes your pre-trained Hugging Face transformer model and training data, applying differential privacy to produce a privacy-preserving fine-tuned model. This is for AI developers who need to build NLP models or image classification models that handle sensitive data.
185 stars. No commits in the last 6 months.
Use this if you are a machine learning engineer building natural language processing or image classification models that require strong privacy guarantees, such as when working with sensitive user data.
Not ideal if you are not working with Hugging Face transformer models, or if privacy is not a primary concern for your application.
Stars
185
Forks
25
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 09, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/lxuechen/private-transformers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/x-transformers
A concise but complete full-attention transformer with a set of promising experimental features...
kanishkamisra/minicons
Utility for behavioral and representational analyses of Language Models
lucidrains/simple-hierarchical-transformer
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
Nicolepcx/Transformers-in-Action
This is the corresponding code for the book Transformers in Action