bhi5hmaraj / personal-content-ranker

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

personal-content-ranker

Draft design doc (Feedback appreciated)

Steps to train a ranker

  1. Create preference data by running the colab
  2. Start reward model training using accelerate launch reward_modeling.py

About


Languages

Language:Jupyter Notebook 93.6%Language:Python 6.4%