zfz1
/

deepseek-8b-orpo-lora

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

deepseek-8b-orpo-lora / runs /Jul18_00-59-35_phe108-jieyuzhao-01

Commit History

End of training

dd36c6b
verified

zfz1 commited on Jul 18

Training in progress, step 312

062e283
verified

zfz1 commited on Jul 18