Chat-Error
/

deberta-xlarge-reward

Model card Files Files and versions

Metrics Training metrics Community

deberta-xlarge-reward / README.md

Phương

Create README.md

0eb970a about 2 years ago

|

history blame contribute delete

107 Bytes

This is Deberta V2 xlarge trained on my https://huggingface.co/datasets/nRuaif/RLHF-hh dataset, using trl.