7 lines
214 B
Markdown
7 lines
214 B
Markdown
|
---
|
||
|
|
datasets:
|
||
|
|
- tatsu-lab/alpaca_farm
|
||
|
|
---
|
||
|
|
1.4b Pythia model after SFT on the AlpacaFarm dataset 'sft' split.
|
||
|
|
|
||
|
|
Policy model from '[Reward Model Ensembles Mitigate Overoptimization](https://arxiv.org/abs/2310.02743)'
|