INT8 electra-small-discriminator-mrpc
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 electra-small-discriminator-mrpc.
The calibration dataloader is the train dataloader. The default calibration sampling size 300 isn't divisible exactly by batch size 8, so the real sampling size is 304.
Test result
| INT8 | FP32 | |
|---|---|---|
| Accuracy (eval-f1) | 0.9007 | 0.8983 |
| Model size (MB) | 14 | 51.8 |
Load with optimum:
from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSequenceClassification
int8_model = IncQuantizedModelForSequenceClassification.from_pretrained(
'Intel/electra-small-discriminator-mrpc-int8-static',
)
ONNX
This is an INT8 ONNX model quantized with Intel® Neural Compressor.
The original fp32 model comes from the fine-tuned model electra-small-discriminator-mrpc.
The calibration dataloader is the eval dataloader. The calibration sampling size is 100.
Test result
| INT8 | FP32 | |
|---|---|---|
| Accuracy (eval-f1) | 0.8957 | 0.8983 |
| Model size (MB) | 16 | 52 |
Load ONNX model:
from optimum.onnxruntime import ORTModelForSequenceClassification
model = ORTModelForSequenceClassification.from_pretrained('Intel/electra-small-discriminator-mrpc-int8-static')
