datasets
| datasets | |
|---|---|
|
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'
| datasets | |
|---|---|
|
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'