Note: Despite the "FP16" in the filename, the original weights in this repo are actually in BF16 instead, which makes them safe for DF11 compression.

Downloads last month
10
Safetensors
Model size
16B params
Tensor type
I64
BF16
U8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for mingyi456/Project0_PJ0_Krea_v3_FP8_FP16-DF11

Quantized
(2)
this model