amd-shark
/

sdxl-quant-int8

Model card Files Files and versions

sdxl-quant-int8

12.3 GB

4 contributors

History: 24 commits

GiusFra's picture

Updated params.safetensors

36c8b73 verified over 1 year ago

.gitattributes

1.57 kB

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

1.68 kB

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

8.55 kB

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

10.2 kB

Quantization script over 1 year ago
out.safetensors

7.11 GB
xet

Output reference tensors over 1 year ago
params.safetensors

5.14 GB
xet

Updated params.safetensors over 1 year ago
quant_param.json

85.1 MB
xet

add missing smoothquant factors over 1 year ago
requirements.txt

223 Bytes

Quantization script over 1 year ago
test_quant_conv2d.py

1.11 kB

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

969 Bytes

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