fauxpaslife/ Mellum2-Thinking-A2.5B-12B:latest

1,106 1 month ago

Mellum 2 Thinking is a Mixture-of-Experts reasoning model (64 experts, 8 activated per token, 131,072-token context) that emits its chain of thought. (Q4_K_M)

... /
params
3f340a3a3d33 ยท 101B
{
"stop": [
"<|im_end|>",
"<|im_start|>"
],
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95
}