zjunlp/EasyInstruct

[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.

51
/ 100
Established

This tool helps researchers and AI practitioners systematically experiment with different ways to prompt Large Language Models (LLMs). It takes in an initial set of instructions, then uses various techniques to generate new instructions, evaluate their quality, and create optimized prompts. The output is a refined set of instructions and prompts designed to get better results from LLMs like GPT-4 or Claude.

409 stars. No commits in the last 6 months. Available on PyPI.

Use this if you are developing or fine-tuning LLMs and need a structured way to create, evaluate, and select high-quality instructions for training or prompting.

Not ideal if you are an end-user simply looking to interact with an LLM for daily tasks, as this is a framework for developing with LLMs.

LLM-development AI-research prompt-engineering natural-language-processing machine-learning-engineering
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 16 / 25

How are scores calculated?

Stars

409

Forks

37

Language

Python

License

MIT

Last pushed

Dec 23, 2024

Commits (30d)

0

Dependencies

21

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/zjunlp/EasyInstruct"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.