90 1 month ago

Building upon Mistral Small 3.2 (2506) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance. With 24 billion parameters, this model achieves top-t

vision tools
21979b2e7992 · 102B
{
"min_p": 0,
"num_ctx": 40960,
"repeat_penalty": 1,
"stop": [
"</s>"
],
"temperature": 0.15,
"top_p": 1
}