Pinned Loading

1. tied-representation-learning tied-representation-learning Public

   Improving zero-shot performance in pretrained neural machine translation models

   Python 1 1

2. rc rc Public

   Public-facing codebase accompanying: "Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL"

   Python 26 10

3. verl-megatron verl-megatron Public

   Forked from verl-project/verl

   verl: Volcano Engine Reinforcement Learning for LLMs

   Python