Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
SoraWatermarkRemover
Log In
Sign Up
amd-shark
/
sdxl-quant-int8
like
2
Follow
AMD SHARK
21
Transformers
Model card
Files
Files and versions
xet
Community
2
Deploy
Use this model
dc6d4e1
sdxl-quant-int8
/
mi250_all_linear_sym_7_5
5.2 GB
4 contributors
History:
5 commits
GiusFra
MI250 QKV fused and all linear layers sym, guidance scale 7.5
48152a7
verified
over 1 year ago
params.safetensors
5.14 GB
xet
MI250 QKV fused and all linear layers sym, guidance scale 7.5
over 1 year ago
quant_params.json
62.1 MB
xet
MI250 QKV fused and all linear layers sym, guidance scale 7.5
over 1 year ago