halfrot
/

sft-mt5-base

Text2Text Generation Transformers Safetensors

mt5 Inference Endpoints text-generation-inference

Model card Files Files and versions Community

Edit model card

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: 4

Safetensors

Model size

582M params

Tensor type

F32

·

Dataset used to train halfrot/sft-mt5-base