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 Intel/MiniLM-L12-H384-uncased-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.
The linear module bert.encoder.layer.6.attention.self.key falls back to fp32 to meet the 1% relative accuracy loss.
|Model size (MB)||33.5||127|
from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSequenceClassification int8_model = IncQuantizedModelForSequenceClassification( 'Intel/MiniLM-L12-H384-uncased-mrpc-int8-static', )
- Downloads last month