Ahjeong/dpo_gemma_7b_bf16_lr5e-7_origindset_default_kl0.01_epoch4-epoch4 Text Generation • Updated Jul 29 • 6
Ahjeong/dpo_gemma_7b_bf16_lr5e-7_origindset_beta1.1_kl0.01_epoch4-epoch4 Text Generation • Updated Jul 29 • 9
Ahjeong/ipo_gemma_7b_bf16_lr5e-7_origindset_default_kl0.01-epoch3 Text Generation • Updated Jul 28 • 6
Ahjeong/ipo_gemma_7b_bf16_lr5e-7_origindset_default_kl0.01-epoch2 Text Generation • Updated Jul 28 • 6
Ahjeong/ipo_gemma_7b_bf16_lr5e-7_origindset_default_kl0.01-epoch1 Text Generation • Updated Jul 28 • 11