arxiv:2404.08495
kiante
xkianteb
AI & ML interests
None yet
Organizations
None yet
Papers
1
models
16
xkianteb/dpo_top1_nolog_equal_weight_lr_1e-6_beta_0.5_555134_1725236314
Text Generation
•
Updated
•
9
xkianteb/dpo_top1_nolog_lr_3e-7_beta_1.0_555134_1725219001
Text Generation
•
Updated
•
11
xkianteb/simpo_1e-6_sigmoid
Text Generation
•
Updated
•
10
xkianteb/simpo_1e-6_squared
Text Generation
•
Updated
•
8
xkianteb/ipo_scale_1e-6_0.001_1723740002
Text Generation
•
Updated
•
8
xkianteb/ipo_scale_1e-6_beta_0.1_1723688553
Text Generation
•
Updated
•
9
xkianteb/ipo_1e-6_beta_0.1_1723688553
Text Generation
•
Updated
•
10
xkianteb/ipo_scale_3e-7_1723651980
Text Generation
•
Updated
•
10
xkianteb/ipo_scale_1e-6_1723651982
Text Generation
•
Updated
•
10
xkianteb/dpo_1e-6_1723651057
Text Generation
•
Updated
•
9
datasets
None public yet