Inside Kimi 1.5: A self-contained summary of its reinforcement learning efforts(yashmore.notion.site)
yashmore.notion.site
Inside Kimi 1.5: A self-contained summary of its reinforcement learning efforts
https://yashmore.notion.site/Inside-Kimi-1-5-A-self-contained-summary-of-its-reinforcement-learning-efforts-2587262c17f78011a2c6f62acb2ea143
0 comments
—