methods: sdft + sdpo — self-distillation trainers for SFT and RL - #13
Open
ghanshyam-lyzr wants to merge 1 commit into
Open
methods: sdft + sdpo — self-distillation trainers for SFT and RL#13ghanshyam-lyzr wants to merge 1 commit into
ghanshyam-lyzr wants to merge 1 commit into
