martimfasantos/tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_rmsprop_2epochs_new Text Generation • Updated 30 days ago • 13
martimfasantos/tinyllama-1.1b-mt-dpo-full_LR1e-7_BS32_rmsprop_3epochs_compare Text Generation • Updated 28 days ago • 16
martimfasantos/tinyllama-1.1b-mt-simpo_beta2.0_gamma1.6_LR1e-7_BS32_rmsprop_3epochs_compare Text Generation • Updated 28 days ago • 10