amd-shark
/

sdxl-quant-int8

Model card Files Files and versions

sdxl-quant-int8

12 GB

Ctrl+K

Ctrl+K

4 contributors

History: 33 commits

nickfraser's picture

Feat (script): Added pre-generated `captions.tsv`

b2f369f about 2 years ago

quant_sdxl
Feat (script): Added pre-generated `captions.tsv` about 2 years ago
.gitattributes

1.57 kB
Upload quant_param.json with huggingface_hub about 2 years ago
config.json

1.68 kB
Add config.json from stable-diffusion-xl-base-1.0/unet about 2 years ago
math_model.py

8.55 kB
Remove potential overflow / saturation error. about 2 years ago
out.safetensors

6.76 GB
xet

Output reference tensors about 2 years ago
params.safetensors

5.14 GB
xet

Upload params.safetensors with huggingface_hub about 2 years ago
quant_param.json

85.1 MB
xet

add missing smoothquant factors about 2 years ago
test_quant_conv2d.py

1.11 kB
Updated math model to target int8 x int8 kernels. about 2 years ago
test_quant_linear.py

969 Bytes
Updated math model to target int8 x int8 kernels. about 2 years ago