README.md

metadata

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

INT8 DistilBERT base uncased finetuned SST-2

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 distilbert-base-uncased-finetuned-sst-2-english.

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-accuracy)	0.9037	0.9106
Model size (MB)	65	255

Load with optimum:

from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSequenceClassification
int8_model = IncQuantizedModelForSequenceClassification.from_pretrained(
    'Intel/distilbert-base-uncased-finetuned-sst-2-english-int8-static',
)

ONNX

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

The original fp32 model comes from the fine-tuned model distilbert-base-uncased-finetuned-sst-2-english.

Test result

	INT8	FP32
Accuracy (eval-f1)	0.9060	0.9106
Model size (MB)	80	256

Load ONNX model:

from optimum.onnxruntime import ORTModelForSequenceClassification
model = ORTModelForSequenceClassification.from_pretrained('Intel/distilbert-base-uncased-finetuned-sst-2-english-int8-static')