SimonPu/
Devstral-Small:2507-Q4_K_XL

123 1 month ago

It is finetuned from Mistral-Small-3.1, therefore it has a long context window of up to 128k tokens. As a coding agent, Devstral is text-only and before fine-tuning from Mistral-Small-3.1 the vision encoder was removed.

vision tools
... /
params
645dadab8336 · 127B
{
"min_p": 0.01,
"num_ctx": 32768,
"repeat_penalty": 1,
"stop": [
"<s>",
"[INST]"
],
"temperature": 0.15,
"top_k": 64,
"top_p": 0.95
}