The goal is to post-train Kimi-K2-Thinking. My success criteria is both qualitative and quantitative: loss should go down and the model should change behavior in line with the dataset we train on.
PRs: #10337 #10401 #11089 #11109 #9594，详情可参考新收录的资料
Москвичи пожаловались на зловонную квартиру-свалку с телами животных и тараканами18:04。新收录的资料对此有专业解读
Hugging Face Spaces (What is Spaces?)