zfz1
/

deepseek-8b-orpo-lora

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

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

Commit History

Model save

9cb3e8d
verified

zfz1 commited on Jul 18

Model save

3cbea15
verified

zfz1 commited on Jul 15