huihui_ai/
deepseek-v3:671b-q2_K

7,103 9 months ago

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

... /
params
f4d24e9138dd · 148B
{
"stop": [
"<｜begin▁of▁sentence｜>",
"<｜end▁of▁sentence｜>",
"<｜User｜>",
"<｜Assistant｜>"
]
}