DUAL-GPO
/

phi-2-gpo-test-longest-iter-random2-4

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

phi-2-gpo-test-longest-iter-random2-4

Commit History

End of training

654e0d5
verified

BraylonDash commited on Mar 27

Model save

b60293c
verified

BraylonDash commited on Mar 27

initial commit

947a1d3
verified

BraylonDash commited on Mar 27