DUAL-GPO
/

zephyr-7b-dpo-0k-15k-i1-merged

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

zephyr-7b-dpo-0k-15k-i1-merged / model.safetensors.index.json

Commit History

Upload MistralForCausalLM

634773f
verified

BraylonDash commited on Sep 19