Miles is open-source reinforcement learning as a service, a user says
Miles’ GitHub description calls it an enterprise-facing framework for post-training large language models and vision-language models.
TLDR
A user shared Miles as “open-source RL-as-a-service”—reinforcement learning as a service. Its GitHub description presents it as an enterprise-facing framework for post-training large language models and vision-language models, forked from and co-evolving with slime.
Combined views
69.3K
1 Source, first seen ago