tlc4418/pythia_70m_sft
0943
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'
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'