Skip to content

ttrangia/ScalableOversightProject

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ScalableOversightProject

Setup

Install the required packages listed in requirements.txt. This is best done through a virtual environment; for example, on a Unix-like system:

python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

Running the Project

First, ensure that the correct dataset is located in data/dataset/. The dataset should be a three-column .csv file, with exactly the columns description, resume_accept, resume_reject. Each row represents one resume pair and one experiment.

Next, run the run_houdini.py script to let the Houdini models generate resume selections. For example, this can be done using:

source .venv/bin/activate
cd src/
python run_houdini.py --dataset cnamuangtoun_subset_50.csv --models openai/gpt-4o meta-llama/Llama-3.1-8B-Instruct

Use the dataset filename located in data/dataset.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Jupyter Notebook 79.6%
  • Python 20.4%