Intel
/

bert-base-uncased-mrpc-int8-static-inc

Text Classification

text-classfication

Intel® Neural Compressor

neural-compressor

PostTrainingStatic

Inference Endpoints

Model card Files Files and versions Community

bert-base-uncased-mrpc-int8-static-inc

5 contributors

History: 13 commits

1pikachu1111's picture

update int8 onnx model and readme

8dc66f1 over 1 year ago

.gitattributes

1.22 kB

initial commit over 2 years ago
README.md

1.92 kB

update int8 onnx model and readme over 1 year ago
config.json

852 Bytes

remove one fallback by increasing calib samples over 2 years ago
model.onnx

247 MB
LFS

update int8 onnx model and readme over 1 year ago
pytorch_model.bin
Detected Pickle imports (13)
- "torch._utils._rebuild_tensor_v2",
- "torch._utils._rebuild_parameter",
- "neural_compressor.conf.dotdict.DotDict",
- "torch.quint8",
- "torch._utils._rebuild_qtensor",
- "torch.qint8",
- "torch.DoubleStorage",
- "torch.FloatStorage",
- "torch.per_channel_affine",
- "torch.LongStorage",
- "torch.QUInt8Storage",
- "collections.OrderedDict",
- "torch.QInt8Storage"
How to fix it?
119 MB
LFS

remove one fallback by increasing calib samples over 2 years ago
special_tokens_map.json

125 Bytes

remove one fallback by increasing calib samples over 2 years ago
tokenizer.json

712 kB

remove one fallback by increasing calib samples over 2 years ago
tokenizer_config.json

359 Bytes

remove one fallback by increasing calib samples over 2 years ago
vocab.txt

232 kB

asym kl 2 fallback 304 cal-samples over 2 years ago