RadixArk
@radixark
The full technical report for Miles is now available.
Miles is built for production-level post-training, with stability, efficiency, and flexibility at its core. The report covers its system design and how it works in practice.
Miles is built for production-level post-training, with stability, efficiency, and flexibility at its core. The report covers its system design and how it works in practice.
RadixArk@radixark · Aug 18Today we're launching Miles v0.1, an open-source RL framework for LLMs and multimodal models.
RL training is easy to start and hard to debug. Miles helps you ensure your run is correct, use hardware efficiently, and keep RL running at scale.
Over the past 9 months, 72
RL training is easy to start and hard to debug. Miles helps you ensure your run is correct, use hardware efficiently, and keep RL running at scale.
Over the past 9 months, 72
0:03 7 541