INT8 roberta-base-mrpc
Post-training static quantization
PyTorch
This is an INT8 PyTorch model quantized with Intel® Neural Compressor.
The original fp32 model comes from the fine-tuned model roberta-base-mrpc.
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:
from optimum.intel.neural_compressor import IncQuantizedModelForSequenceClassification
model_id = "Intel/roberta-base-mrpc-int8-static"
int8_model = IncQuantizedModelForSequenceClassification.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:
from optimum.onnxruntime import ORTModelForSequenceClassification
model = ORTModelForSequenceClassification.from_pretrained('Intel/roberta-base-mrpc-int8-static')
