xqlin98/INSTINCT
This is the official implementation for the paper: Use Your INSTINCT: INSTruction optimization usIng Neural bandits Coupled with Transformers
This project helps developers and researchers fine-tune instructions for large language models (LLMs) to achieve better performance on various tasks without extensive manual effort. It takes an initial instruction, runs experiments with an LLM, and outputs an optimized instruction that yields improved results. Data scientists and AI researchers who work with LLMs would find this useful.
No commits in the last 6 months.
Use this if you are a developer or researcher looking to automatically optimize prompts for LLMs like ChatGPT to improve their accuracy and performance on tasks such as instruction induction or chain-of-thought reasoning.
Not ideal if you are a business user looking for a no-code solution to improve LLM outputs without any programming or technical setup.
Stars
53
Forks
6
Language
Python
License
MIT
Category
Last pushed
Jun 09, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/xqlin98/INSTINCT"
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