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 /Oct06_22-40-26_xe8545-a100-22

Commit History

Model save

3ee5d97
verified

CharlesLi commited on Oct 7

Model save

53b0e31
verified

CharlesLi commited on Oct 7