metadata
license: apache-2.0
An Autoregressive Reward Model finetuned from allenai/tulu-2-7b
on the Ultrafeedback dataset. See https://arxiv.org/abs/2410.08193
license: apache-2.0
An Autoregressive Reward Model finetuned from allenai/tulu-2-7b
on the Ultrafeedback dataset. See https://arxiv.org/abs/2410.08193