add int8 embedding
533f50a
-
1.22 kB
initial commit
-
1.42 kB
Update README.md
-
860 Bytes
add int8 embedding
-
456 kB
upload int8 model
pytorch_model.bin
Detected Pickle imports (13)
- "torch.LongStorage",
- "torch._utils._rebuild_qtensor",
- "torch.QUInt8Storage",
- "collections.OrderedDict",
- "torch.per_channel_affine",
- "torch.DoubleStorage",
- "torch._utils._rebuild_parameter",
- "neural_compressor.conf.dotdict.DotDict",
- "torch.QInt8Storage",
- "torch._utils._rebuild_tensor_v2",
- "torch.FloatStorage",
- "torch.quint8",
- "torch.qint8"
How to fix it?
127 MB
add int8 embedding
-
239 Bytes
upload int8 model
-
2.11 MB
add int8 embedding
-
360 Bytes
add int8 embedding
-
798 kB
upload int8 model
-
232 kB
add int8 embedding