upload int8 model.
4299403
-
1.34 kB
initial commit
-
1.17 kB
update README.md.
-
960 Bytes
upload int8 model.
-
456 kB
upload int8 model.
pytorch_model.bin
Detected Pickle imports (13)
- "torch.FloatStorage",
- "collections.OrderedDict",
- "torch.QUInt8Storage",
- "torch.quint8",
- "torch._utils._rebuild_tensor_v2",
- "torch._utils._rebuild_parameter",
- "torch._utils._rebuild_qtensor",
- "torch.per_channel_affine",
- "torch.LongStorage",
- "torch.QInt8Storage",
- "neural_compressor.conf.dotdict.DotDict",
- "torch.qint8",
- "torch.DoubleStorage"
How to fix it?
399 MB
upload int8 model.
-
280 Bytes
upload int8 model.
-
2.11 MB
upload int8 model.
-
386 Bytes
upload int8 model.
training_args.bin
Detected Pickle imports (6)
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.IntervalStrategy",
- "torch.device",
- "transformers.training_args.TrainingArguments",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.SchedulerType"
How to fix it?
3.31 kB
upload int8 model.
-
798 kB
upload int8 model.