GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment
Paper
•
2410.08193
•
Published
•
4
An Autoregressive Reward Model finetuned from allenai/tulu-2-7b on the Ultrafeedback dataset. See https://arxiv.org/abs/2410.08193
- Downloads last month
- 6
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support