zfz1
/

deepseek-8b-orpo-lora

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

deepseek-8b-orpo-lora / all_results.json

Commit History

End of training

dd36c6b
verified

zfz1 commited on Jul 18

Model save

9cb3e8d
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