I’m experimenting with Kimi K2 but can’t find a way to distinguish between the thoughts and the final output. Isn’t the standard to wap thoughts in <think></think> so ti can be filtered out?Â
I’ve tried instructing the model doing so but with limited success.
Â
Has anyone a solution to filter thoughts and only retrieve final output?
Could you share your system / user prompt, or a screenshot of the playground (https://console.groq.com/playground?model=moonshotai/kimi-k2-instruct) where this is happening? I’d love to take a stab on it; I think we can do it through system prompting.
No account yet? Create an account
Enter your E-mail address. We'll send you an e-mail with instructions to reset your password.