mistralai

/

Ministral-3-14B-Reasoning-2512

like 54

Follow

Mistral AI_ 13.4k

The current template is actually correct, its intended to be used with the following approach if used via mistral-common for example:

{
  "role": "system",
  "content": [
    {
      "type": "text",
      "text": "# HOW YOU SHOULD THINK AND ANSWER\n\nFirst draft your thinking process (inner monologue) until you arrive at a response. Format your response using Markdown, and use LaTeX for any mathematical equations. Write both your thoughts and the response in the same language as the input.\n\nYour thinking process must follow the template below:"
    },
    {
      "type": "thinking",
      "thinking": [
        {
          "type": "text",
          "text": "Your thoughts or/and draft, like working through an exercise on scratch paper. Be as casual and as long as you want until you are confident to generate the response to the user."
        }
      ]
    },
    {
      "type": "text",
      "text": "Here, provide a self-contained response."
    }
  ]
}

I hope this helps !

Thanks for your answer! Sorry I'm not familiar with mistral-common. I already used it but never look at the prompt constructing logic. I'm actually running the inference through llama.cpp most of the time.
But it is however still missing for the GGUF embedded template no? As in this case it's just hard-coded as a string.