Tandogan
/

MNLP_M2_dpo_model

instruction-tuning

preference-modeling

Model card Files Files and versions

MNLP_M2_dpo_model / generation_config.json

Commit History

Upload best checkpoint from DPO on SFT (Tandogan/MNLP_M2_SFT) model finetuning

ca13d5c
verified

Tandogan commited on May 25