Intel
/

bert-base-uncased-mrpc-int8-qat-inc

Text Classification

text-classfication

Intel® Neural Compressor

QuantizationAwareTraining

Inference Endpoints

Model card Files Files and versions Community

bert-base-uncased-mrpc-int8-qat-inc

3 contributors

History: 17 commits

echarlaix's picture

echarlaix HF staff

Fix loading instructions

e916825 9 months ago

.gitattributes

1.22 kB

initial commit over 2 years ago
README.md

1.35 kB

Fix loading instructions 9 months ago
config.json

852 Bytes

int8 embedding over 2 years ago
pytorch_model.bin
Detected Pickle imports (13)
- "torch.qint8",
- "torch.FloatStorage",
- "torch.LongStorage",
- "torch._utils._rebuild_parameter",
- "collections.OrderedDict",
- "torch.QUInt8Storage",
- "neural_compressor.conf.dotdict.DotDict",
- "torch.per_channel_affine",
- "torch._utils._rebuild_qtensor",
- "torch.QInt8Storage",
- "torch._utils._rebuild_tensor_v2",
- "torch.quint8",
- "torch.DoubleStorage"
How to fix it?
112 MB
LFS

int8 embedding epoch 1 over 2 years ago
special_tokens_map.json

112 Bytes

upload int8 model over 2 years ago
tokenizer.json

711 kB

upload int8 model over 2 years ago
tokenizer_config.json

332 Bytes

upload int8 model over 2 years ago
vocab.txt

232 kB

upload int8 model over 2 years ago