48 yesterday

Astria is a multimodal model built by combining a LLaVA vision encoder with the new Ministral model, producing a unified system capable of detailed visual understanding and strong general-purpose reasoning.

vision tools 4b 8b
3325398b03de · 89B
{
"num_ctx": 32768,
"repeat_penalty": 1.1,
"seed": 0,
"temperature": 0.7,
"top_k": 40,
"top_p": 0.9
}