zfz1
/

deepseek-8b-orpo-lora

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

deepseek-8b-orpo-lora

Commit History

Training in progress, step 312

062e283
verified

zfz1 commited on Jul 18

End of training

1075d3a
verified

zfz1 commited on Jul 15

Model save

3cbea15
verified

zfz1 commited on Jul 15

Training in progress, step 312

759010b
verified

zfz1 commited on Jul 15

initial commit

81d9374
verified

zfz1 commited on Jul 15