Intel
/

distilbert-base-uncased-finetuned-sst-2-english-int8-dynamic

Text Classification PyTorch ONNX Transformers

English distilbert text-classfication int8 Intel® Neural Compressor License: apache-2.0

Model card Files Files and versions Community

distilbert-base-uncased-finetuned-sst-2-english-int8-dynamic

3 contributors

History: 8 commits

yuwenz's picture

Update README.md

532f947 3 months ago

.gitattributes

1.34 kB

initial commit 10 months ago
README.md

2.05 kB

Update README.md 3 months ago
config.json

809 Bytes

Upload model 10 months ago
eval_results.json

184 Bytes

Upload model 10 months ago
model.onnx

76.1 MB
LFS

upload int8 onnx model 5 months ago
pytorch_model.bin
Detected Pickle imports (10)
- "neural_compressor.conf.dotdict.DotDict",
- "torch._utils._rebuild_qtensor",
- "torch._utils._rebuild_tensor_v2",
- "torch.LongStorage",
- "collections.OrderedDict",
- "torch.qint8",
- "torch.FloatStorage",
- "torch.DoubleStorage",
- "torch.per_channel_affine",
- "torch.QInt8Storage"
How to fix it?
139 MB
LFS

Upload model 10 months ago
quantization.yml

237 Bytes

Upload model 10 months ago
tokenizer_config.json

48 Bytes

Add tokenizer 9 months ago
vocab.txt

232 kB

Add vocab 9 months ago