Pinned Loading

1. Archer2.0 Archer2.0 Public

   Archer2.0 evolves from its predecessor by introducing ASPO, which overcomes fundamental PPO-Clip limitations to prevent premature convergence and unlock greater RL potential.

   Python 27 2

2. ArcherCodeR ArcherCodeR Public

   ArcherCodeR is an open-source initiative enhancing code reasoning in large language models through scalable, rule-governed reinforcement learning.

   Python 43 2