Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
amd-shark
/
sdxl-quant-int8
like
2
Follow
AMD SHARK
21
Transformers
Model card
Files
Files and versions
xet
Community
2
Deploy
Use this model
f20a0bf
sdxl-quant-int8
33.5 GB
Ctrl+K
Ctrl+K
4 contributors
History:
42 commits
GiusFra
QKV fused and sym
f20a0bf
verified
almost 2 years ago
all_linear_sym
QKV fused and all linear layers sym
almost 2 years ago
full_sym
Full symmetric
almost 2 years ago
fused_qkv
Fused QKV quant_params.json with zp
almost 2 years ago
qkv_sym
QKV fused and sym
almost 2 years ago
quant_sdxl
Fix model loading
almost 2 years ago
.gitattributes
Safe
1.63 kB
Updated quant_params
almost 2 years ago
config.json
Safe
1.68 kB
Add config.json from stable-diffusion-xl-base-1.0/unet
almost 2 years ago
math_model.py
Safe
9.05 kB
Update quant params structure (#2)
almost 2 years ago
out.safetensors
Safe
7.11 GB
xet
Output reference tensors
almost 2 years ago
params.safetensors
Safe
5.14 GB
xet
Updated params.safetensors
almost 2 years ago
punet_inputs.safetensors
Safe
661 kB
xet
Reference inputs
almost 2 years ago
quant_param.json
85.1 MB
xet
add missing smoothquant factors
almost 2 years ago
quant_params.json
Safe
86.8 MB
xet
Updated quant_params
almost 2 years ago
test_quant_conv2d.py
Safe
1.18 kB
Update quant params structure (#2)
almost 2 years ago
test_quant_linear.py
Safe
1.04 kB
Update quant params structure (#2)
almost 2 years ago
vae.safetensors
Safe
167 MB
xet
Added vae weights with FP16 fix.
almost 2 years ago
