secfa/
DeepSeek-R1-UD-IQ1_S:latest

170.9K 8 months ago

Unsloth's DeepSeek-R1 , I just merged the thing and uploaded it here. This is the full 671b model. MoE Bits:1.58bit Type:UD-IQ1_S Disk Size:131GB Accuracy:Fair Details:MoE all 1.56bit. down_proj in MoE mixture of 2.06/1.56bit

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