-
1.17 kB
initial commit
-
1.97 kB
fix README
-
823 Bytes
int8 model
-
34 MB
update int8 onnx model and readme
pytorch_model.bin
Detected Pickle imports (13)
- "neural_compressor.conf.dotdict.DotDict",
- "collections.OrderedDict",
- "torch.LongStorage",
- "torch._utils._rebuild_qtensor",
- "torch.QUInt8Storage",
- "torch._utils._rebuild_parameter",
- "torch.qint8",
- "torch.DoubleStorage",
- "torch.per_channel_affine",
- "torch.QInt8Storage",
- "torch.quint8",
- "torch._utils._rebuild_tensor_v2",
- "torch.FloatStorage"
How to fix it?
35.2 MB
int8 model
-
112 Bytes
upload int8 model
-
712 kB
upload int8 model
-
533 Bytes
upload int8 model
-
232 kB
upload int8 model