amd-shark
/

sdxl-quant-int8

Model card Files Files and versions Community

sdxl-quant-int8

Ctrl+K

Ctrl+K

4 contributors

History: 24 commits

nickfraser's picture

Feat (script): Added calibration size argument.

8324b6e about 1 year ago

.gitattributes

1.57 kB

Upload quant_param.json with huggingface_hub about 1 year ago
config.json

1.68 kB

Add config.json from stable-diffusion-xl-base-1.0/unet about 1 year ago
math_model.py

8.55 kB

Remove potential overflow / saturation error. about 1 year ago
minimal_script.py

10.6 kB

Feat (script): Added calibration size argument. about 1 year ago
out.safetensors

6.76 GB
LFS

Output reference tensors about 1 year ago
params.safetensors

5.14 GB
LFS

Upload params.safetensors with huggingface_hub about 1 year ago
quant_param.json

85.1 MB
LFS

add missing smoothquant factors about 1 year ago
requirements.txt

223 Bytes

Quantization script about 1 year ago
test_quant_conv2d.py

1.11 kB

Updated math model to target int8 x int8 kernels. about 1 year ago
test_quant_linear.py

969 Bytes

Updated math model to target int8 x int8 kernels. about 1 year ago