Barrrrry
/

DeepSeek-R1-W4AFP8

8-bit precision

Model card Files Files and versions

Resources

View closed (0)

how to convert a bf16 model to W4AFP8 model

#3 opened 3 months ago by

Quantzation for 0528 version

#2 opened 7 months ago by

Can yo show some accuracy results comparing to original DeepSeek-R1?

#1 opened 7 months ago by