Pinned Loading

1. sail-sg/oat sail-sg/oat Public

   🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

   Python 582 51

2. axon-rl/gem axon-rl/gem Public

   A Gym for Agentic LLMs

   Python 408 27

3. sail-sg/understand-r1-zero sail-sg/understand-r1-zero Public

   Understanding R1-Zero-Like Training: A Critical Perspective

   Python 1.2k 54

4. mosecorg/mosec mosecorg/mosec Public

   A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine

   Python 885 67

5. spiral-rl/spiral spiral-rl/spiral Public

   SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning

   Python 171 19

6. sail-sg/Precision-RL sail-sg/Precision-RL Public

   Defeating the Training-Inference Mismatch via FP16

   Python 165 13