lindafei001
/

llama-8b-instruct-safeRLHF-dpo-10epochs-1e-5-64-128-0.5

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

llama-8b-instruct-safeRLHF-dpo-10epochs-1e-5-64-128-0.5 / runs

70.8 kB

1 contributor

History: 1 commit

lindafei001's picture

Upload trained model checkpoint

07c1037 verified 23 days ago

Sep22_07-43-31_w-yanli-sudolm-88776406705d4aceac34e7a04afadc53-85df665cbcpx44f
Upload trained model checkpoint 23 days ago