PaTaRM PaTaRM is a Generative Reward Model (GRM) for RLHF alignment. AIJian/PaTaRM-8B Text Generation • 0.5B • Updated 21 days ago • 757 AIJian/PaTaRM-data Preview • Updated 22 days ago • 28 AIJian/PaTaRM-14B Text Generation • 0.5B • Updated 22 days ago • 1.29k AIJian/PaTaRM Updated 22 days ago
PaTaRM PaTaRM is a Generative Reward Model (GRM) for RLHF alignment. AIJian/PaTaRM-8B Text Generation • 0.5B • Updated 21 days ago • 757 AIJian/PaTaRM-data Preview • Updated 22 days ago • 28 AIJian/PaTaRM-14B Text Generation • 0.5B • Updated 22 days ago • 1.29k AIJian/PaTaRM Updated 22 days ago