Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Intel
/
gpt-neox-japanese-2.7b-int8-inc
like
0
Follow
Intel
1,939
Text Generation
oscar
Japanese
japanese
gpt_neox
gpt
lm
nlp
int8
neural-compressor
Intel® Neural Compressor
PostTrainingStatic
Eval Results
License:
mit
Model card
Files
Files and versions
Community
1e61ddd
gpt-neox-japanese-2.7b-int8-inc
2 contributors
History:
4 commits
echarlaix
HF staff
update loading instructions
1e61ddd
8 months ago
.gitattributes
Safe
1.48 kB
initial commit
over 1 year ago
README.md
Safe
1.34 kB
update loading instructions
8 months ago
best_model.pt
pickle
Detected Pickle imports (11)
"torch.LongStorage"
,
"torch.per_channel_affine"
,
"collections.OrderedDict"
,
"torch.QInt8Storage"
,
"torch._utils._rebuild_tensor_v2"
,
"torch._utils._rebuild_qtensor"
,
"torch.FloatStorage"
,
"torch.quint8"
,
"torch.QUInt8Storage"
,
"torch.qint8"
,
"torch.DoubleStorage"
How to fix it?
2.69 GB
LFS
add int8 model
over 1 year ago