Intel
/

t5-small-xsum-int8-dynamic-inc

Text2Text Generation

Intel® Neural Compressor

neural-compressor

PostTrainingDynamic

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

t5-small-xsum-int8-dynamic-inc

4 contributors

History: 3 commits

lvkaokao's picture

upload int8 model and config.

0a9ad76 about 2 years ago

.gitattributes

1.38 kB

initial commit about 2 years ago
README.md

1.07 kB

add model card. about 2 years ago
config.json

1.48 kB

upload int8 model and config. about 2 years ago
pytorch_model.bin
Detected Pickle imports (12)
- "torch.DoubleStorage",
- "torch._utils._rebuild_qtensor",
- "torch.qint8",
- "neural_compressor.conf.dotdict.DotDict",
- "torch.QUInt8Storage",
- "collections.OrderedDict",
- "torch.per_channel_affine",
- "torch._utils._rebuild_tensor_v2",
- "torch.quint8",
- "torch.FloatStorage",
- "torch.QInt8Storage",
- "torch.LongStorage"
How to fix it?
161 MB
LFS

upload int8 model and config. about 2 years ago
special_tokens_map.json

2.2 kB

upload int8 model and config. about 2 years ago
spiece.model

792 kB
LFS

upload int8 model and config. about 2 years ago
tokenizer.json

2.42 MB

upload int8 model and config. about 2 years ago
tokenizer_config.json

2.39 kB

upload int8 model and config. about 2 years ago