CharlesLi
/

OpenELM-1_1B-DPO-full-max-10-reward

Text Generation

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

OpenELM-1_1B-DPO-full-max-10-reward / runs /Oct07_05-34-18_xe8545-a100-15

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

CharlesLi's picture

Model save

c70833e verified 10 months ago

events.out.tfevents.1728272812.xe8545-a100-15.1096845.0

226 kB
LFS

Model save 10 months ago