Krea@krea_ai · XAI 摘要
感谢Thinking Machines团队，我们使用Tinker原型化了我们的奖励模型，并通过RL训练了提示词扩展器。 更多信息，请阅读关于Krea 2背后数据、架构和训练的完整技术报告 👇
thanks to the Thinking Machines team， we used Tinker to prototype our reward models and train the prompt expander via RL.
for more information， read the full technical report on the data， architecture， and training behind Krea 2 👇
Training image models requires a surprising amount of Tinkering: prototyping reward models, training a prompt expander, and creating the RL environment. We love...