/o1-preview-llama

This project makes llama 3.1 as o1 preview with Chain of thought , Reflection and verbal reinforcement.

Primary LanguagePython

This repo has code and dataset

  1. I modified code from https://github.com/bklieger-groq/g1 according to my experiment
  2. I attached zip files which has screenshot of llama3.1 8b solving reasoning
  3. I attached zip files has screenshot of Claude Sonnet solving IMO 2023