RoBERTa
Collection
8 items
•
Updated
This is an INT8 ONNX model quantized with Intel® Neural Compressor.
The original fp32 model comes from the fine-tuned model Intel/xlm-roberta-base-mrpc.
INT8 | FP32 | |
---|---|---|
Accuracy (eval-f1) | 0.8966 | 0.9010 |
Model size (MB) | 354 | 1061 |
from optimum.onnxruntime import ORTModelForSequenceClassification
model = ORTModelForSequenceClassification.from_pretrained('Intel/xlm-roberta-base-mrpc-int8-dynamic')