Tag: 大模型训练 (2 articles)

NVIDIA experts argue that open data and synthetic data are key to building reliable AI agents: open data for explainability, synthetic data for scaling without exposing secrets.

Hugging Face's TRL library introduces delta weight sync, transmitting only the ~1-2% of weights that change between RL steps, reducing sync overhead by two orders of magnitude and making trillion-parameter async RL training dramatically cheaper.