Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
AmdGoose
/
FLUX.2-dev-transformer-int8wo
like
0
Text-to-Image
Diffusers
image-generation
quantization
int8
torchao
amd
rocm
License:
other
Model card
Files
Files and versions
xet
Community
Use this model
main
FLUX.2-dev-transformer-int8wo
/
transformer_int8wo
32.2 GB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
AmdGoose
Add INT8 weight-only quantized transformer for FLUX.2-dev
d98adcb
verified
4 months ago
config.json
Safe
491 Bytes
Add INT8 weight-only quantized transformer for FLUX.2-dev
4 months ago
diffusion_pytorch_model-00001-of-00004.bin
pickle
Detected Pickle imports (10)
"torchao.quantization.Int8Tensor"
,
"torch.serialization._get_layout"
,
"torch.bfloat16"
,
"torch.CharStorage"
,
"torch._tensor._rebuild_from_type_v2"
,
"collections.OrderedDict"
,
"torch.device"
,
"torch._utils._rebuild_wrapper_subclass"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.BFloat16Storage"
How to fix it?
9.92 GB
xet
Add INT8 weight-only quantized transformer for FLUX.2-dev
4 months ago
diffusion_pytorch_model-00002-of-00004.bin
pickle
Detected Pickle imports (10)
"torch._utils._rebuild_wrapper_subclass"
,
"torch.CharStorage"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.BFloat16Storage"
,
"torch._tensor._rebuild_from_type_v2"
,
"torch.bfloat16"
,
"torchao.quantization.Int8Tensor"
,
"torch.serialization._get_layout"
,
"torch.device"
How to fix it?
9.97 GB
xet
Add INT8 weight-only quantized transformer for FLUX.2-dev
4 months ago
diffusion_pytorch_model-00003-of-00004.bin
pickle
Detected Pickle imports (10)
"torchao.quantization.Int8Tensor"
,
"torch.serialization._get_layout"
,
"torch.bfloat16"
,
"torch.CharStorage"
,
"torch._tensor._rebuild_from_type_v2"
,
"collections.OrderedDict"
,
"torch.device"
,
"torch._utils._rebuild_wrapper_subclass"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.BFloat16Storage"
How to fix it?
9.82 GB
xet
Add INT8 weight-only quantized transformer for FLUX.2-dev
4 months ago
diffusion_pytorch_model-00004-of-00004.bin
pickle
Detected Pickle imports (10)
"torch._utils._rebuild_wrapper_subclass"
,
"torch.CharStorage"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.BFloat16Storage"
,
"torch._tensor._rebuild_from_type_v2"
,
"torch.bfloat16"
,
"torchao.quantization.Int8Tensor"
,
"torch.serialization._get_layout"
,
"torch.device"
How to fix it?
2.53 GB
xet
Add INT8 weight-only quantized transformer for FLUX.2-dev
4 months ago
diffusion_pytorch_model.bin.index.json
Safe
33.1 kB
Add INT8 weight-only quantized transformer for FLUX.2-dev
4 months ago
