к каталогу

📦 miles/ radixark

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

Открыть на GitHubобновлён 5ч назад
Звёзды
2.0k
Форки
360
За неделю
За месяц
Рост %
Язык
Python

Установка и запуск

Установка

@misc{miles2026,
  title        = {Miles: Enterprise-Grade Reinforcement Learning for Large-Scale Model Post-Training},
  author       = {Miles Team},
  year         = {2026},
  howpublished = {\url{https://github.com/radixark/miles}}
}

Из README репозитория · полный README на GitHub

Категории