AAPA Official AAPA release: processed training data and A-GRPO checkpoints for adversarially anchored preference alignment. Jingleqian/AAPA-data Viewer • Updated Jun 20 • 500 • 232 Jingleqian/AAPA-8B Text Generation • 8B • Updated Jun 20 • 15 • 1 Jingleqian/AAPA-06B Text Generation • 0.8B • Updated Jun 20 • 22
AAPA Official AAPA release: processed training data and A-GRPO checkpoints for adversarially anchored preference alignment. Jingleqian/AAPA-data Viewer • Updated Jun 20 • 500 • 232 Jingleqian/AAPA-8B Text Generation • 8B • Updated Jun 20 • 15 • 1 Jingleqian/AAPA-06B Text Generation • 0.8B • Updated Jun 20 • 22
