DUAL-GPO
/

phi-2-gpo-renew2-b0.001-vllm-i1

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

phi-2-gpo-renew2-b0.001-vllm-i1 / merges.txt

Commit History

Training in progress, step 100

d1efcdc
verified

BraylonDash commited on May 3