upload int8 onnx model
3518c77
-
1.22 kB
initial commit
-
2.28 kB
upload int8 onnx model
-
1 kB
int8 model
-
32.9 MB
upload int8 onnx model
pytorch_model.bin
Detected Pickle imports (13)
- "neural_compressor.conf.dotdict.DotDict",
- "torch._utils._rebuild_qtensor",
- "torch.quint8",
- "torch.FloatStorage",
- "torch._utils._rebuild_tensor_v2",
- "torch.QUInt8Storage",
- "torch.qint8",
- "torch.per_channel_affine",
- "torch.LongStorage",
- "torch.DoubleStorage",
- "torch.QInt8Storage",
- "torch._utils._rebuild_parameter",
- "collections.OrderedDict"
How to fix it?
14.6 MB
int8 model
-
112 Bytes
int8 model
-
712 kB
int8 model
-
370 Bytes
int8 model
-
232 kB
int8 model