Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
amd-shark
/
sdxl-quant-int8
like
1
Follow
AMD SHARK
17
Transformers
Inference Endpoints
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
ecec5b7
sdxl-quant-int8
4 contributors
History:
22 commits
GiusFra
Quantization script
ecec5b7
verified
5 months ago
.gitattributes
Safe
1.57 kB
Upload quant_param.json with huggingface_hub
6 months ago
config.json
Safe
1.68 kB
Add config.json from stable-diffusion-xl-base-1.0/unet
6 months ago
math_model.py
Safe
8.55 kB
Remove potential overflow / saturation error.
6 months ago
minimal_script.py
Safe
10.2 kB
Quantization script
5 months ago
out.safetensors
Safe
6.76 GB
LFS
Output reference tensors
6 months ago
params.safetensors
Safe
5.14 GB
LFS
Upload params.safetensors with huggingface_hub
6 months ago
quant_param.json
Safe
85.1 MB
LFS
add missing smoothquant factors
6 months ago
requirements.txt
Safe
223 Bytes
Quantization script
5 months ago
test_quant_conv2d.py
Safe
1.11 kB
Updated math model to target int8 x int8 kernels.
6 months ago
test_quant_linear.py
Safe
969 Bytes
Updated math model to target int8 x int8 kernels.
6 months ago
