Organization: Oxen
Paper: https://www.oxen.ai/blog/training-a-rust-1-5b-coder-lm-with-reinforcement-learning-grpo
Code: https://github.com/Oxen-AI/GRPO-With-Cargo-Feedback/blob/main/train.py
Train/Eval?: Train
Owner: https://x.com/Ljt019117161
Difficulty: Easy