Together AI 推出后训练服务，支持 RL 与 SFT 定制模型
原标题：Introducing Together Post-Training: Better models, faster runs, lower costs →
AI 摘要
Together AI 推出 Together Post-Training 服务，支持通过强化学习环境奖励和 SFT 监督数据构建定制模型。该服务提供专属 GPU 资源、可自定义训练循环、异步 RL 及多种标准损失函数，并首发支持 Muse Spark Open、GLM 5.3、Kimi K3 和 Qwen 3.8-27B 等开源权重模型。其目标是降低后训练基础设施门槛，让企业以更低成本获得任务专用模型。
正文节选
We are introducing Together Post-Training, a new service for building custom models on our platform — both from environment rewards via RL and supervision data via SFT. This service is designed to give you flexible and efficient model shaping without the heavy infra burden. Together Post-Training makes it easy to define the training loop, while we co-optimize the systems and infrastructure underneath for model quality and training speed. Nothing now stands between you and the best model that is