halfrot
/

sft-mt5-base

Text2Text Generation

Inference Endpoints

Model card Files Files and versions Community

sft-mt5-base / README.md

halfrot's picture

Update README.md

13c576d verified 8 months ago

|

history blame contribute delete

289 Bytes

metadata

license: apache-2.0
datasets:
  - Helsinki-NLP/europarl

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.