7 lines
201 B
Markdown
7 lines
201 B
Markdown
---
|
|
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' |