> 好的，用户发来消息：“hello do you speak english” (Hunyuan-T1 thinking response)
It's kind of wild that even a Chinese model replies "好的" as the first tokens, which basically means "Ok, so..." like R1 and the other models respond. Is this RL'ed or just somehow a natural effect of the training?
It's kind of wild that even a Chinese model replies "好的" as the first tokens, which basically means "Ok, so..." like R1 and the other models respond. Is this RL'ed or just somehow a natural effect of the training?