VITA-Group/DP-OPT
[ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
This project helps anyone working with large language models who needs to generate specific instructions or prompts for their models without compromising sensitive information. It takes your private data and automatically creates optimized prompts that maintain data privacy, even when used with cloud-based LLMs. Data scientists, machine learning engineers, and researchers can use this to get better results from LLMs while adhering to strict privacy regulations.
No commits in the last 6 months.
Use this if you need to fine-tune prompts for a large language model using sensitive, private data, but want to keep that data confidential and not send it to a third-party LLM provider.
Not ideal if your data is not sensitive and you are comfortable with traditional prompt engineering methods or sending your data directly to a cloud LLM provider for tuning.
Stars
47
Forks
10
Language
Python
License
MIT
Category
Last pushed
May 30, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/VITA-Group/DP-OPT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
linshenkx/prompt-optimizer
一款提示词优化器，助力于编写高质量的提示词
Undertone0809/promptulate
🚀Lightweight Large language model automation and Autonomous Language Agents development...
CTLab-ITMO/CoolPrompt
Automatic Prompt Optimization Framework
microsoft/sammo
A library for prompt engineering and optimization (SAMMO = Structure-aware Multi-Objective...
Eladlev/AutoPrompt
A framework for prompt tuning using Intent-based Prompt Calibration