The calibration dataloader is the train dataloader. The default calibration sampling size 100 isn't divisible exactly by batch size 8, so the real sampling size is 104.

Test result

	INT8	FP32
Accuracy (eval-f1)	0.9177	0.9138
Model size (MB)	127	499

Load with Intel® Neural Compressor:

python

from optimum.intel import INCModelForSequenceClassification

model_id = "Intel/roberta-base-mrpc-int8-static"
int8_model = INCModelForSequenceClassification.from_pretrained(model_id)

ONNX

This is an INT8 ONNX model quantized with Intel® Neural Compressor.

The original fp32 model comes from the fine-tuned model roberta-base-mrpc.

The calibration dataloader is the eval dataloader. The calibration sampling size is 100.

Test result

	INT8	FP32
Accuracy (eval-f1)	0.9100	0.9138
Model size (MB)	294	476

Load ONNX model:

python

from optimum.onnxruntime import ORTModelForSequenceClassification
model = ORTModelForSequenceClassification.from_pretrained('Intel/roberta-base-mrpc-int8-static')

INC4AI/roberta-base-mrpc-int8-static-inc

INT8 roberta-base-mrpc

Post-training static quantization

PyTorch

Test result

Load with Intel® Neural Compressor:

ONNX

Test result

Load ONNX model:

INC4AI/
roberta-base-mrpc-int8-static-inc