Skip to content

ChasmNetwork/llm-as-a-judge

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LLM as a judge

A quick CLI tool to test whether an LLM outperform another LLM based on the paper LLM-as-a-judge method.

Installation

  1. Install all the libraries
pip install -r requirements.txt
  1. Setup .env
cp .env.sample .env

by default it's using OLLAMA to run the judge work.

  1. Run the code
python main.py

The CLI will ask the question and response of LLM A and LLM B, and then will run the benchmark using MODELS as jury.

demo

About

CLI tools for LLM as a judge

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages