CharlesLi
/

OpenELM-1_1B-DPO-full-max-8-reward

Text Generation

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

OpenELM-1_1B-DPO-full-max-8-reward / runs

1 contributor

History: 4 commits

CharlesLi's picture

Model save

3ee5d97 verified 3 months ago