Lichang-Chen/InstructZero
Official Implementation of InstructZero; the first framework to optimize bad prompts of ChatGPT(API LLMs) and finally obtain good prompts!
This project helps prompt engineers and researchers refine their instructions for large language models (LLMs) like ChatGPT or Claude. It takes a 'bad' or inefficient prompt and, through an automated optimization process, outputs an improved prompt that yields better responses from the black-box LLM. This is ideal for those who work with LLMs and need to achieve precise, high-quality outputs without the ability to fine-tune the model itself.
199 stars. No commits in the last 6 months.
Use this if you are a prompt engineer or AI researcher looking for an automated way to generate optimal prompts for black-box LLMs, enhancing performance without model access.
Not ideal if you have full access to the LLM's internal parameters and can perform traditional model fine-tuning or backpropagation.
Stars
199
Forks
15
Language
Python
License
—
Category
Last pushed
Jul 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Lichang-Chen/InstructZero"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MantisAI/sieves
Plug-and-play document AI with zero-shot models.
xiaoya-li/Instruction-Tuning-Survey
Project for the paper entitled `Instruction Tuning for Large Language Models: A Survey`
TencentARC-QQ/TagGPT
TagGPT: Large Language Models are Zero-shot Multimodal Taggers
rafaelpierre/bullet
bullet: A Zero-Shot / Few-Shot Learning, LLM Based, text classification framework
amazon-science/adaptive-in-context-learning
AdaICL: Which Examples to Annotate of In-Context Learning? Towards Effective and Efficient Selection