README.md

metadata

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

INT8 DistilBERT base uncased finetuned SST-2

Post-training static quantization

This is an INT8 PyTorch model quantified with intel/nlp-toolkit using provider: 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

• Batch size = 8
• Amazon Web Services c6i.xlarge (Intel ICE Lake: 4 vCPUs, 8g Memory) instance.

	INT8	FP32
Throughput (samples/sec)	47.554	23.046
Accuracy (eval-accuracy)	0.9037	0.9106
Model size (MB)	65	255

Load with nlp-toolkit:

from nlp_toolkit import OptimizedModel
int8_model = OptimizedModel.from_pretrained(
    'Intel/distilbert-base-uncased-finetuned-sst-2-english-int8-static',
)

Notes:

• The INT8 model has better performance than the FP32 model when the CPU is fully occupied. Otherwise, there will be the illusion that INT8 is inferior to FP32.