yiran-wang3
/

ds_chat_sppo_hard_new_iter0_constant_1e-6

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

ds_chat_sppo_hard_new_iter0_constant_1e-6

1 contributor

History: 1 commit

yiran-wang3's picture

initial commit

27b3244 verified about 2 months ago

.gitattributes

1.52 kB

initial commit about 2 months ago