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
d6a388a
sdxl-quant-int8
4 contributors
History:
13 commits
GiusFra
update quant_params with correct shapes
d6a388a
verified
7 months ago
.gitattributes
1.57 kB
Upload quant_param.json with huggingface_hub
7 months ago
math_model.py
8.12 kB
Fix: set `keepdim=True`
7 months ago
params.safetensors
5.14 GB
LFS
Upload params.safetensors with huggingface_hub
7 months ago
quant_param.json
84.6 MB
LFS
update quant_params with correct shapes
7 months ago
test_quant_conv2d.py
751 Bytes
[test] Fixed shapes to match new `quant_param.json`
7 months ago
test_quant_linear.py
717 Bytes
[test] Fixed shapes to match new `quant_param.json`
7 months ago