CharlesLi
/

OpenELM-1_1B-DPO-full-max-14-reward

Text Generation

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

OpenELM-1_1B-DPO-full-max-14-reward / runs /Sep16_21-23-53_xe8545-a100-29

1 contributor

History: 1 commit

CharlesLi's picture

Model save

b33a043 verified 3 months ago

events.out.tfevents.1726515695.xe8545-a100-29.16638.0

226 kB
LFS

Model save 3 months ago