dyyyyyyyy/FAPO-GenRM-4B

Text Generation • 4B • Updated Oct 31 • 100 • 1

Note 4B Generative Reward Model for FAPO Reinforcement Learning.

dyyyyyyyy/FAPO-32B

33B • Updated Oct 28 • 14 • 1

Note 32B FAPO Reasoning Model Trained with Generative Reward.

Note Training and Evaluation Dataset for FAPO-GenRM-4B (Generative Reward Model).

Note Training and Evaluation Dataset for FAPO-32B (Reasoning Model).