Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
vuiseng9
/
gptq-w4-gs32-sparse-compressed-oc14336-ic4096
like
0
Model card
Files
Files and versions
Community
main
gptq-w4-gs32-sparse-compressed-oc14336-ic4096
/
internal
/
donttouch_unpacking_autogptq
2 contributors
History:
1 commit
Vui Seng Chua
Add content
cfb9114
2 months ago
__pycache__
Add content
2 months ago
autogpt_sample.py
438 Bytes
Add content
2 months ago
blob_manipulate.py
2.53 kB
Add content
2 months ago
fake_dequantize.py
2.29 kB
Add content
2 months ago
opt-125m-gptq4.pth
pickle
Detected Pickle imports (10)
"collections.OrderedDict"
,
"numpy.ndarray"
,
"_codecs.encode"
,
"torch.HalfStorage"
,
"numpy.core.multiarray._reconstruct"
,
"torch.IntStorage"
,
"numpy.dtype"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"torch._utils._rebuild_parameter"
How to fix it?
46.7 MB
LFS
Add content
2 months ago
qlinear_cuda_old.py
14.1 kB
Add content
2 months ago
qlinear_cuda_old.py.ori.py
14.1 kB
Add content
2 months ago
quantizer.py
38.8 kB
Add content
2 months ago
quantizer.py.ori.py
37.9 kB
Add content
2 months ago
readme.md
402 Bytes
Add content
2 months ago
run_sqft.py
3.75 kB
Add content
2 months ago
verify_unpacking_logic.py
2.57 kB
Add content
2 months ago