README.md

metadata

language: en
license: apache-2.0
tags:
  - text-classfication
  - int8
  - Intel® Neural Compressor
  - PostTrainingStatic
  - bert
datasets:
  - mrpc
  - sst2
metrics:
  - f1

INT8 BERT base uncased finetuned sst2

Post-training static quantization

PyTorch

This is an INT8 PyTorch model quantized with huggingface/optimum-intel through the usage of Intel® Neural Compressor.

The original fp32 model comes from the fine-tuned model gchhablani/bert-base-cased-finetuned-sst2.

Test result

	INT8	FP32
Accuracy (eval-f1)	0.9151	0.9232
Model size (MB)	111	433

Load with optimum:

from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSequenceClassification
int8_model = IncQuantizedModelForSequenceClassification.from_pretrained(
    'Intel/bert-base-cased-finetuned-sst2-int8',
)