Intel/bert-base-uncased-mrpc-int8-dynamic-inc

INT8 BERT base uncased finetuned MRPC

Post-training dynamic 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 Intel/bert-base-uncased-mrpc.

Test result

	INT8	FP32
Accuracy (eval-f1)	0.8997	0.9042
Model size (MB)	174	418

Load with optimum:

from optimum.intel import INCModelForSequenceClassification

model_id = "Intel/bert-base-uncased-mrpc-int8-dynamic"
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 Intel/bert-base-uncased-mrpc.

Test result

	INT8	FP32
Accuracy (eval-f1)	0.8958	0.9042
Model size (MB)	107	418

Load ONNX model:

from optimum.onnxruntime import ORTModelForSequenceClassification
model = ORTModelForSequenceClassification.from_pretrained('Intel/bert-base-uncased-mrpc-int8-dynamic')