DistilBERT
Collection
Smaller BERT models for question answering and text classification
•
13 items
•
Updated
Model Description: This model is a DistilBERT fine-tuned on MPRC dynamically quantized with optimum-intel through the usage of huggingface/optimum-intel through the usage of Intel® Neural Compressor.
To load the quantized model, you can do as follows:
from optimum.intel import INCModelForSequenceClassification
model_id = "Intel/distilbert-base-uncased-MRPC-int8-dynamic"
model = INCModelForSequenceClassification.from_pretrained(model_id)
INT8 | FP32 | |
---|---|---|
Accuracy (eval-f1) | 0.8983 | 0.9027 |
Model size (MB) | 75 | 268 |