Trained SFT policy for MT task in the paper "ALaRM: Align Language Models via Hierarchical Rewards Modeling".

Check out our project page for more information.

Downloads last month
86
Safetensors
Model size
582M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Dataset used to train halfrot/sft-mt5-base