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 /Jul14_23-51-02_allegro-adams

Commit History

Training in progress, step 312

759010b
verified

zfz1 commited on Jul 15