Intel/bert-large-uncased-rte-int8-static-inc

INT8 bert-large-uncased-rte-int8-static

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 yoshitomo-matsubara/bert-large-uncased-rte.

Test result

	INT8	FP32
Accuracy (eval-f1)	0.7365	0.7401
Model size (MB)	1244	1349

Load with Intel® Neural Compressor:

from optimum.intel import INCModelForSequenceClassification

model_id = "Intel/bert-large-uncased-rte-int8-static"
int8_model = INCModelForSequenceClassification.from_pretrained(model_id)