pythia_70m_sft / README.md
tlc4418's picture
Create README.md
4f0328e verified
metadata
datasets:
  - tatsu-lab/alpaca_farm

70m Pythia model after SFT on the AlpacaFarm dataset 'sft' split.

Model used as a base for reward models in 'Reward Model Ensembles Mitigate Overoptimization'