Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
amd-shark
/
sdxl-quant-int8
like
2
Follow
AMD SHARK
19
Transformers
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
17638f5
sdxl-quant-int8
Ctrl+K
Ctrl+K
4 contributors
History:
26 commits
GiusFra
Reference inputs
17638f5
verified
11 months ago
.gitattributes
Safe
1.63 kB
Updated quant_params
11 months ago
config.json
Safe
1.68 kB
Add config.json from stable-diffusion-xl-base-1.0/unet
12 months ago
math_model.py
Safe
8.55 kB
Remove potential overflow / saturation error.
12 months ago
minimal_script.py
10.2 kB
Quantization script
12 months ago
out.safetensors
Safe
7.11 GB
LFS
Output reference tensors
11 months ago
params.safetensors
Safe
5.14 GB
LFS
Updated params.safetensors
11 months ago
punet_inputs.safetensors
Safe
661 kB
LFS
Reference inputs
11 months ago
quant_param.json
Safe
85.1 MB
LFS
add missing smoothquant factors
12 months ago
quant_params.json
Safe
86.8 MB
LFS
Updated quant_params
11 months ago
requirements.txt
Safe
223 Bytes
Quantization script
12 months ago
test_quant_conv2d.py
Safe
1.11 kB
Updated math model to target int8 x int8 kernels.
12 months ago
test_quant_linear.py
Safe
969 Bytes
Updated math model to target int8 x int8 kernels.
12 months ago
